# Signing In ## Sign-In Methods InterMIND supports the following sign-in methods: ![InterMIND login page](https://intermind.com/img/docs/getting-started/login-page.png) | Method | How | | ---------------- | --------------------------------------------------------------------- | | **Google** | Click **Continue with Google** → select account | | **Microsoft** | Click **Continue with Microsoft** → sign in | | **Email (code)** | Enter email → click **Continue with Email** → enter the 6-digit code | | **SSO** | Click **Sign in with SSO** → enter work email → continue via your IdP | All methods lead to the same account if you use the same email address. There is no password-based sign-in — every email login uses a one-time code. ## Staying Signed In Once signed in, your session persists across browser tabs and restarts. You don't need to sign in every time you visit InterMIND. ## Signing Out 1. Open the sidebar (click the hamburger menu on mobile, or see the sidebar on desktop) 2. Click your profile avatar at the bottom of the sidebar 3. Select **Log out** ## Troubleshooting | Issue | Solution | | ------------------------------- | --------------------------------------------------------------------------------------- | | "Account not found" | Make sure you're using the same email and sign-in method you used to create the account | | Google/Microsoft popup blocked | Allow popups for the InterMIND domain in your browser settings | | Verification code didn't arrive | Check your spam folder, then click **Resend code** | | Code rejected as invalid | Codes are 6 digits and expire — request a fresh code with **Resend code** | | Session keeps expiring | Check that cookies are enabled and not blocked by browser extensions | ## What's Next - [Start your first meeting](https://intermind.com/first-meeting) — Create a meeting and invite participants - [Configure your profile](https://intermind.com/../settings/profile) — Set your name, avatar, and language # Creating an Account You can create an InterMIND account using any of the following methods. ## Sign Up with Google ![Login page — Google, Microsoft, or a one-time email code](https://intermind.com/img/docs/getting-started/login-page.png) ::steps ### Go to the login page Open the InterMIND login page. ### Click Continue with Google A popup will appear for Google account selection. ### Select your Google account Choose the account you want to use. ### Done You're signed in — your profile name and avatar are imported automatically. :: ## Sign Up with Microsoft ::steps ### Go to the login page Open the InterMIND login page. ### Click Continue with Microsoft A popup will appear for Microsoft sign-in. ### Sign in with your Microsoft account You can use a personal, work, or school account. ### Grant permissions Approve the requested permissions. ### Done You're signed in — your profile name is imported automatically. :: ## Sign Up with Email (Verification Code) InterMIND email sign-in is passwordless — you receive a 6-digit code in your inbox each time. ::steps ### Go to the login page Open the InterMIND login page. ### Enter your work email Type your email address in the **Work email** field. ### Click Continue with Email A 6-digit verification code is sent to that address. ### Check your inbox Open the email from InterMIND and copy the 6-digit code (or follow the confirmation link to enter the code on a second device). ### Enter the code Paste the code into the **Verification code** field and click **Verify Code**. ### Done You're signed in. If it's your first time, an account is created automatically. :: ## Sign In with SSO If your organization has configured SSO, click **Sign in with SSO** on the login page and enter your work email. You'll be redirected to your identity provider. ![Sign in with SSO — work email step](https://intermind.com/img/docs/getting-started/login-sso.png) ## What Happens After Sign-Up After creating your account: - You start on the free **Basic** plan — no card required - A team is automatically created for you - You can immediately [start your first meeting](https://intermind.com/first-meeting) - A **14-day free trial** of a paid plan is available when you subscribe through the [Pricing](https://intermind.com/pricing) page (one trial per account — see [Billing & Plans](https://intermind.com/../billing)) ## Joining via Team Invitation If someone invited you to their team: ::steps ### Click the invitation link Open the link in the email you received. ### Sign in or create an account Use any of the methods described above. ### You're added to the team You are automatically added to the team that invited you. The team admin's subscription covers your access. :: ::callout{type="info"} Each user belongs to **at most one team** at a time. Accepting a new team's invitation leaves your current team (an owner with an active subscription must cancel and wait for it to end first). :: # Your First Meeting This guide walks you through creating and running your first meeting with real-time translation. ::steps{level="2"} ## Start a Meeting After signing in, open the **Meetings** page from the sidebar: ![Meetings page — New meeting button and the join / invite field](https://intermind.com/img/docs/getting-started/meetings-hub.png) - **New meeting** — Click **New meeting**. The meeting is created and you go straight into it, through the pre-join screen. To get the link without joining, use **Copy link** in the row's **⋯** menu. - **Join or invite** — Paste a meeting ID or URL into the search field to join — or type a contact's name or email to send them an invite. - **Schedule for Later** — Click the **calendar button** on the meeting's row to open Google Calendar or Outlook with the meeting link pre-filled. ## Pre-Join Setup Before entering the meeting room, you'll see the **Pre-Join Setup** screen: - **Camera preview** — See how you look before joining - **Microphone selection** — Choose which microphone to use - **Camera selection** — Choose which camera to use - **Mute/unmute** — Start with camera or microphone off Click **Join** when you're ready. :::callout{type="tip"} There is no switch for this screen — InterMIND skips it by itself once you've joined with a given camera / microphone / speaker setup, and shows it again when that setup changes. See [Meeting Defaults](https://intermind.com/../settings/meeting-defaults). ::: ## Enable Translation Once in the meeting: 1. Open the **More** menu in the control bar at the bottom of the screen 2. Click **Enable translation** (language icon) to turn on real-time translation — this item appears only when the meeting has more than one language in play 3. Set your language from the **Translate for me into** submenu in the same **More** menu — this is the language you want to hear 4. When other participants speak, their words are translated into your chosen language in real-time You'll hear the translated audio automatically. You can also enable **subtitles** to see the translation as text. ## Invite Others Share the meeting with others: - **Copy the meeting link** from the address bar or the share button - **Send it to participants** via email, chat, or any messaging app - Participants with accounts can **click the link and join directly** - Participants without accounts can **join as guests** (the meeting host must approve them) ## Use Meeting Controls The control bar at the bottom provides quick access to: | Control | Function | | --------------- | ----------------------------------------------------------------- | | 📹 Camera | Turn camera on/off | | 🎤 Microphone | Mute/unmute your microphone | | 💬 Chat | Open the in-meeting chat sidebar | | 👥 Participants | Open the participants panel | | 🖥️ Screen | Share your screen | | ⋯ More | Reactions, raise hand, translation, subtitles, recording, devices | | 🚪 Leave | Leave the meeting | For details on each control, see [Meeting Controls](https://intermind.com/../meetings/controls). :: ## What's Next - [Learn about meeting controls](https://intermind.com/../meetings/controls) — Camera, microphone, screen sharing, and more - [Set up translation](https://intermind.com/../translation) — Choose languages and configure subtitles - [Use the chat](https://intermind.com/../chat) — Send messages during and outside meetings - [Invite your team](https://intermind.com/../users/inviting) — Add team members to your organization # System Requirements InterMIND runs fully in the browser — no installation, no plugins. Prefer a native app? Optional [desktop and mobile apps](https://intermind.com/apps) are available for macOS, Windows, iOS, and Android. ## Supported Browsers | Browser | Minimum version | Notes | | --------------------- | --------------------- | --------------------------------------------- | | **Chrome** | 90+ | Best support | | **Edge** | 90+ | Same engine as Chrome | | **Safari** | 15+ | Screen sharing requires Safari 17+ | | **Firefox** | 100+ | Works; some codec fallbacks on older hardware | | **Opera, Brave, Arc** | Chrome 90+ equivalent | Works (Chromium-based) | Internet Explorer and legacy (pre-Chromium) Edge are not supported. ::callout{type="tip"} For the best experience, use Google Chrome or Microsoft Edge with a stable internet connection. :: ## Bandwidth | Activity | Minimum | Recommended | | ----------------------------------- | -------------- | -------------- | | Audio-only meeting with translation | 1 Mbps up/down | 2 Mbps up/down | | HD video meeting with translation | 2 Mbps up/down | 5 Mbps up/down | | Screen sharing | +1 Mbps up | +2 Mbps up | Run a [speed test](https://fast.com){rel=""nofollow""} to check your real bandwidth — not the rated speed of your plan. ## Devices | Device | Required | | -------------------------- | ---------------------------------------------------------------------------------- | | **Microphone** | Required for speaking | | **Camera** | Optional — audio-only mode is supported | | **Speakers or headphones** | Required to hear translation | | **Headset** | Recommended in noisy environments — reduces echo and improves translation accuracy | ## Mobile | Feature | iOS Safari | Android Chrome | | ---------------------- | ----------- | -------------- | | Audio + video meetings | ✓ | ✓ | | Real-time translation | ✓ | ✓ | | Screen sharing | ✗ | ✗ | | Picture-in-picture | ✓ (iOS 15+) | ✓ | For meetings longer than 30 minutes or with screen sharing, use desktop. On Android, the [InterMIND app](https://intermind.com/apps) keeps the call alive in the background and adds push notifications. ## Verify Before an Important Meeting Run the [WebRTC Browser Test](https://intermind.com/browser-test) — it checks microphone, camera, network reachability, and codec support in 30 seconds. If any check fails, see [Troubleshooting](https://intermind.com/../troubleshooting). ![WebRTC Browser Test — all checks passed](https://intermind.com/img/docs/getting-started/browser-test.png) ## Related - [Desktop & Mobile Apps](https://intermind.com/apps) — Optional native apps for macOS, Windows, iOS, and Android - [Troubleshooting → Browsers & Devices](https://intermind.com/../troubleshooting/browsers) — When the requirements are met but something still doesn't work - [Troubleshooting → Network & Connection](https://intermind.com/../troubleshooting/network) — Firewall and VPN settings # Desktop & Mobile Apps On a computer InterMIND works fully in the browser — the desktop apps are optional. Install one when you want the call to survive a minimized window or native message and call alerts. On a phone the browser is for the website only: a meeting link, an invite link or the sign-in page opens the InterMIND app, and offers its store when the app is not installed yet. The link you tapped travels with the install — after the first launch the app opens the meeting you were invited to. Tablets keep the browser. Get them from the [Downloads page](https://intermind.com/downloads): ![Downloads page — the apps for desktop, mobile and the browser](https://intermind.com/img/docs/getting-started/downloads.png) | Platform | Package | Requirements | | --------------------- | --------------------------------------------------------------------------------------- | --------------------------------------------------------------------------- | | **macOS** | Universal DMG (Apple silicon & Intel) | macOS 11 or later | | **Windows** | x64 installer | Windows 10 or later | | **Android** | Google Play · Huawei AppGallery (phones without Google services) · Samsung Galaxy Store | Android 8 or later | | **iOS** | App Store | iPhone & iPad | | **Browser extension** | Chrome Web Store · Edge Add-ons | Chrome or Edge — opens the call in the browser side panel while you present | The desktop builds are signed, so they open without security warnings. The Samsung Galaxy Store version of the Android app is refreshed about once a quarter and gets no over-the-air updates in between — on a Samsung phone, Google Play has the newest one. ## What's Different from the Browser Inside a meeting, the apps and the browser are identical — same translation engine, same controls. The differences are around the meeting window: | Capability | Web | Desktop | Mobile | | ------------------------------------ | ------------------------- | ------------------------------------------- | ---------------------------------------------------------------------------------- | | Join & translate live meetings | Full | Full | Full | | Screen sharing | Full | Full | Full — share your phone screen from iOS and Android; pinch to zoom a shared screen | | Call stays alive when minimized | Tab is throttled | Runs unthrottled | Foreground service | | Native notifications | In-tab only | System + dock badge | Push notifications — on Android they need Google services (see below) | | Share into InterMIND from other apps | Paste or drag into a chat | macOS Share menu; Windows: paste or drag | iOS and Android share sheet — text, links, images, video, and files | | Updates | Always latest, no restart | Downloads in background, applies on restart | Applies on next launch; the store you installed from for native changes | ## Huawei Phones Without Google Services The Android app is the same package on Google Play, Huawei AppGallery and Samsung Galaxy Store. On a Huawei phone without Google services, meetings, live translation, chat, sign-in with Google or Microsoft (it opens in the phone's browser) and over-the-air updates all work. What does not work is push notifications: alerts about incoming calls and new messages rely on Google services, so on those phones they arrive only while the app is open. ## When to Use Which - **Web** — no install, always the latest version. The default. - **Desktop** — you keep InterMIND open all day: background calls aren't throttled, and alerts arrive even when the window is hidden. - **Mobile** — meetings on the go with push notifications; the foreground service keeps the call running when you switch apps. - **Browser extension** (Chrome, Edge) — opens InterMIND in the browser side panel, so you can see the call while presenting: the side panel stays out of the shared tab. ## Related - [System Requirements](https://intermind.com/system-requirements) — Browsers, bandwidth, and devices for the web version - [Joining a Meeting](https://intermind.com/../meetings/join) — The same inside the meeting in the browser and the apps; on a phone the link opens the app # Welcome to InterMIND InterMIND is a space for everyday communication in the language you think in: meetings, chat, files and the recap after every call, each in the member's own language. Every participant speaks, hears and reads in their own language, and the history stays readable that way. It sits next to the tools your team already runs on — Microsoft 365, Google Workspace, Slack, Telegram — rather than replacing them. ## What You Can Do - **Meetings** — Start or join meetings with 50 to 300 participants by plan (1,500 on Enterprise); each participant hears the others in their own language, live - **Subtitles and transcripts** — Read translated subtitles during the call and keep the full transcript afterwards - **Recap after every call** — A summary with action items in each member's language, by email too - **Team chat and channels** — Messages, files and images, readable in each member's language; a channel keeps the history of its meetings — recaps, chat, files (document translation is a paid feature, Pro and above) - **Screen sharing and recording** — Share your screen and record meetings - **Guests** — Anyone joins by link, without an account; participants pay nothing - **Next to your stack** — Meetings from Outlook or Google Calendar, a meeting started from Slack with the recap in the thread, Telegram groups mirrored into channels, Drive and OneDrive files opened in the call ## Quick Start 1. **[Create an account](https://intermind.com/getting-started/account)** — Sign up with Google, Microsoft, or email 2. **[Sign in](https://intermind.com/getting-started/sign-in)** — Access the platform 3. **[Start your first meeting](https://intermind.com/getting-started/first-meeting)** — Create a meeting and invite participants ![Meetings page — the hub you land on after signing in](https://intermind.com/img/docs/getting-started/meetings-hub.png) ## Supported Languages InterMIND supports **23 languages** live for voice, chat, notes and recaps: | Language | Language | Language | | -------- | --------- | ---------- | | English | Spanish | French | | German | Italian | Portuguese | | Dutch | Russian | Polish | | Czech | Hungarian | Japanese | | Korean | Chinese | Danish | | Finnish | Icelandic | Norwegian | | Romanian | Swedish | Ukrainian | | Turkish | Hindi | | On-demand file translation in chat — a paid feature available on Pro and above — covers a wider list of 30 languages via DeepL. The marketing site itself is localized to 17 (three of which — Arabic, Indonesian and Vietnamese — are site-only for now: in-meeting translation doesn't cover them). See [Choosing Languages](https://intermind.com/translation/languages) for the full per-surface breakdown, or read [How many languages do we support — six numbers, not one](https://intermind.com/blog/how-many-languages-do-you-support) for the methodology. ## System Requirements InterMIND runs fully in the browser — no installation needed. Optional [desktop and mobile apps](https://intermind.com/getting-started/apps) add background calls and native notifications. See [System Requirements](https://intermind.com/getting-started/system-requirements) for the supported browsers, bandwidth, and devices. # Choosing Languages ## Selecting Your Language The language you hear and read in determines what language you hear when translation is active. What you say is recognized automatically — there is no speaking language to set. Each listener picks their own — how this replaces an interpreting booth is explained on the [AI Simultaneous Interpretation feature page](https://intermind.com/features/simultaneous-interpretation). ### During a Meeting 1. Open the **More** menu in the control bar 2. Hover **Translate for me into** — the submenu lists all 23 languages, with the current one checked 3. Click a language to select it 4. Translation immediately switches to the new language ### From the Sidebar By default the language you hear and read in follows your **interface language**. To use a different language for translation only: 1. Open the menu on your **account entry** at the bottom of the sidebar 2. Pick **Translate for me into** and choose a language from the submenu 3. Your account entry now shows the chosen language — the choice is saved to your profile and syncs across devices ![The Translate for me into submenu of the account menu, listing the languages to choose from](https://intermind.com/img/docs/translation/languages.png) Choosing the same language as your interface clears the override. The pre-join screen **shows** the language you'll be listening in, but it is read-only there — change it from the sidebar (or, if you're joining as a guest, on the join page). This single setting is used for: - Real-time voice translation in meetings - Automatic chat message translation - Subtitles language ## Supported Languages InterMIND currently supports **23 languages** for real-time translation (voice, chat messages, and shared notes — one set, three surfaces): | Language | Native Name | Region | | ----------------------- | ----------- | -------- | | English | English | Global | | Russian | Русский | Europe | | Spanish (Latin America) | Español | Americas | | French | Français | Europe | | German | Deutsch | Europe | | Italian | Italiano | Europe | | Portuguese (Brazilian) | Português | Americas | | Polish | Polski | Europe | | Dutch | Nederlands | Europe | | Czech | Čeština | Europe | | Hungarian | Magyar | Europe | | Danish | Dansk | Europe | | Finnish | Suomi | Europe | | Icelandic | Íslenska | Europe | | Norwegian | Norsk | Europe | | Romanian | Română | Europe | | Swedish | Svenska | Europe | | Ukrainian | Українська | Europe | | Japanese | 日本語 | Asia | | Korean | 한국어 | Asia | | Turkish | Türkçe | Europe | | Chinese (Simplified) | 中文 | Asia | | Hindi | हिन्दी | Asia | ::callout{type="info"} **File translation in chat uses a wider list of 30 languages** (DeepL Document API) — including Bulgarian, Greek, Estonian, Indonesian, and several other European languages not available for live voice. The platform API accepts all 23 real-time codes plus the file-only ones. Per-pair quality — including newer pairs like Hindi — is published openly on [`/benchmark`](https://intermind.com/benchmark). Full breakdown: [How many languages do we support — six numbers, not one](https://intermind.com/blog/how-many-languages-do-you-support). :: ::callout{type="info"} All 23 languages are available on every plan — pair availability is not limited by tier. Monthly translation time and text-translation word budget depend on your plan; see [Usage & Limits](https://intermind.com/../billing/usage) for details. :: ## Tips - **Set your language before the meeting** from the sidebar account menu to avoid configuring it every time - **Browser language fallback** — If you haven't set a language, InterMIND uses your browser's default language - The language setting is **per-user**, not per-meeting. Each participant in the same meeting can use a different language # Live Subtitles Live subtitles show the translated text of what participants are saying, displayed at the bottom of the meeting screen in real-time. ## Enabling Subtitles 1. Join a meeting with translation enabled 2. Open the **More** menu in the control bar and click **Show subtitles** 3. Translated text appears at the bottom of the screen as participants speak 4. The same item becomes **Hide subtitles** — click it to turn them off ![The More menu of a meeting with translation enabled: Disable translation and Show subtitles](https://intermind.com/img/docs/translation/subtitles.png) ## How Subtitles Work - Subtitles show the **translated** text, not the original speech - They appear in the language you chose to hear and read in - Subtitles update in real-time as words are recognized and translated - Each subtitle line shows what the current speaker is saying - When no one is speaking, subtitles fade away ## RTL Language Support The subtitle layout automatically flips to right-to-left when an RTL language is detected, so future RTL languages will render correctly. The current translation target list is left-to-right (see [Choosing Languages](https://intermind.com/languages) for the full list). ## Subtitle Appearance - Subtitles appear as a **banner at the bottom** of the meeting screen - They have a semi-transparent dark background for readability - Font size is optimized for screen reading at typical viewing distances - Subtitles don't overlap with the meeting control bar ## Default Setting Subtitle on/off state is **remembered between meetings** based on whatever you last set in the cockpit (per browser). There is no separate Settings toggle — the last state of the **Show subtitles** item in the **More** menu is what you'll get when you join the next meeting. ## Tips for Using Subtitles - **Presentations** — Enable subtitles during presentations for participants who prefer reading - **Noisy environments** — Subtitles help when audio quality is poor - **Language learning** — Read the translation while hearing the original to learn new languages - **Accessibility** — Subtitles make meetings more accessible for participants with hearing difficulties # Transcription Transcription captures all spoken words during a meeting and makes them available as a transcript after the meeting, with speaker attribution. ## How Transcription Works Transcription is **automatic** — there is no Start/Stop button. Whenever a meeting is live, speech is captured in real time: - Every word is transcribed and attributed to the speaker who said it - Words are collected on the server as the meeting runs - The transcript is in each speaker's original language ## Viewing the Transcript After the meeting ends, a **recap** message appears in the meeting chat. Open it and switch to the **Transcript** tab to read the full transcript on its own page — see [Meeting Recap](https://intermind.com/../meetings/recap). ![The Transcript tab of a meeting recap, with each turn attributed to its speaker and timestamped](https://intermind.com/img/docs/translation/transcript.png) The transcript page can show the transcript **translated into your language** — it's generated in the speakers' original languages and translated on demand when you open it in a different language. ## Use Cases - **Meeting minutes** — Capture everything said for reference - **Compliance** — Keep records of discussions for regulatory purposes - **Absent participants** — Share the transcript with people who couldn't attend - **Review** — Go back and review specific parts of the discussion ## Important Notes - The quality of transcription depends on audio quality — use a good microphone and minimize background noise - The transcript is captured in each speaker's original language; open the transcript page in your own language to read it translated - The transcript is produced once the meeting ends and reached from the recap in the meeting chat ## Related - [Meeting Recap](https://intermind.com/../meetings/recap) — Summary, transcript, and recording after the call - [Meeting Controls](https://intermind.com/../meetings/controls) — In-meeting control bar - [Chat](https://intermind.com/../chat) — Where the post-meeting recap lives # Your Own Voice When InterMIND translates your speech for another participant, they don't hear a robotic text-to-speech narrator. They hear a voice that's **recognizably yours** — carrying your timbre and your way of speaking — now saying the words in their language. This works in both directions and for every participant independently. In a meeting where five people speak five languages, each person hears the other four in their own language, and each of those four still sounds like themselves. ## What It Sounds Like Most live-translation tools replace the speaker with a single generic synthetic voice. The result is intelligible but flat — you lose who is talking, the emphasis, the personality. InterMIND keeps the speaker's voice, so a translated meeting feels like a conversation between the people who are actually in it, not a queue of announcements read by a machine. ## How It Works InterMIND uses a **cascaded pipeline**, and the voice step is the last stage: 1. **Speech recognition** — your words are transcribed in your own language, as you speak. 2. **Segmentation** — the transcript is grouped into stable sentence fragments (clauses) so translation can begin before you finish the sentence. 3. **Translation** — each fragment is translated progressively into the listener's language. 4. **Voice synthesis** — each translated fragment is spoken back using a sample of **your own voice**, and sent to the listener. While the meeting is still gathering enough of your speech to model your voice (roughly the first **5–10 seconds**), the synthesis uses the audio fragment that matches what you just said in your source language. Once there's a long enough sample, it switches to using that sample for everything after. In practice you don't notice a switch — the translation sounds more like you as the call goes on. It won't be a flawless impression of your voice, but it's recognizably you rather than a generic narrator — and it keeps improving as the model hears more of you. ## Languages Your-own-voice translation is available for **all 23 voice languages** — the same set listed in [Choosing Languages](https://intermind.com/languages). There's nothing to enable separately: when [translation is on](https://intermind.com/../translation), participants automatically hear you in your own voice. ## Your Saved Voice Sample (Optional) Signed-in users can skip the warm-up by recording a voice sample once in [Settings → Your voice in translation](https://intermind.com/docs/settings/profile): press **Record my voice**, say the numbers from one to ten in any order, and the sample saves itself when all ten light up. From your next meeting your translated speech is voiced with it from the first sentence. ![The Your voice in translation card in Settings: the numbers one to ten and the Record my voice button](https://intermind.com/img/docs/translation/own-voice.png) ## Privacy Two samples, two lifetimes. The **live** sample used for the in-meeting warm-up is ephemeral: it exists only for the duration of the live meeting and is not stored anywhere; the Mind API and SDK that power the real-time session keep no data once the conference session ends. The **saved** sample from Settings is stored with your account for one purpose, voicing your translated speech, is sent to the translation engine each time you join a meeting, and is deleted the moment you remove it or delete your account. Neither is one of InterMIND's video-and-voice **recording** features, which are separate, explicit recordings you start on purpose. ## On the Roadmap: Lip-Sync Hearing the translation in your own voice is the first half of a larger goal. The next step we're working toward is **lip-sync** — re-timing the speaker's mouth on camera to match the translated audio, so each participant appears to be speaking the other's language. Combined with own-voice translation, the aim is a call where people who share no common language see and hear each other as if each spoke the other's language natively. This is a roadmap item, not a shipped feature yet — own-voice translation above is live today. ::callout{type="info"} Want the full technical picture? See [Speak in your own voice — in a language you don't speak](https://intermind.com/blog/own-voice-translation) on the blog. :: # Real-Time Translation InterMIND's core feature is **AI-powered real-time speech translation**. During video meetings, every participant speaks their own language and hears others translated into theirs — live, with minimal delay. For the product view — what gets translated beyond voice and how it compares to other platforms — see the [Real-Time Translation feature page](https://intermind.com/features/realtime-translation). ## How It Works 1. You speak in your own language 2. InterMIND's AI captures your speech 3. The speech is translated into the target language of each listener 4. Each participant hears the translated audio in real-time — [in the original speaker's own voice](https://intermind.com/translation/own-voice), not a synthetic narrator 5. Optionally, translated subtitles appear on screen Each participant independently chooses their own language. In a meeting with 5 people speaking 5 different languages, everyone hears the translation in their own language simultaneously. ## Key Features | Feature | Description | | ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **23 languages** | Voice, chat, and shared notes (file translation: 30, a paid feature on Pro and above) — [why these counts vary](https://intermind.com/blog/how-many-languages-do-you-support) | | **Real-time** | Minimal delay between speech and translation | | **Per-participant** | Each person chooses their own target language | | **Bidirectional** | Works in both directions — you hear others and they hear you | | **Own voice** | Each participant hears the translation in the [speaker's own voice](https://intermind.com/translation/own-voice), not a robotic narrator | | **Subtitles** | Optional text subtitles for the translation | | **Transcription** | Save the full transcript of a meeting | ## Enabling Translation 1. Join a meeting 2. Open the **More** menu in the control bar and click **Enable translation** (or press Alt+T) — only available when the room has at least two languages 3. Set your language from the **Translate for me into** submenu in the same **More** menu 4. Start speaking — other participants will hear you in their chosen language ![The More menu of a meeting with two languages in the room: Enable translation, Show subtitles and the Translate for me into submenu](https://intermind.com/img/docs/translation/more-menu.png) When translation is enabled: - You hear a **translated audio stream** on top of the original - The original speech stays underneath at 20 % of its volume: the translation runs a few seconds behind the speaker, and the quiet original tells you who is talking and when they stop - You can toggle it off at any time to hear the original speech ## Glossary Your organization's own words — a product, a brand, a job title, an internal acronym — are translated the way you say, not the way a dictionary would. There is no list to maintain: tell Mia, in the ⌘/ panel or from the AI assistant you connected through [MCP](https://intermind.com/integrations/mcp), and she remembers it for the whole organization: - «Translate *Atlas* into French as *Atlas*» — one rendering for one language - «Never translate *ACME*» — the term stays exactly as written in every language - «In the last recap *pipeline* came out as *tuyau*; it should be *pipeline*» — a correction overwrites the earlier rule From the next translation on, recaps, transcripts, shared documents, chat and notes render the term as told. Ask Mia «what terms do you know» to read the list back, or tell her to forget one. Available to organizations with AI features on. ## In This Section - [Choosing Languages](https://intermind.com/translation/languages) — Choose and change the language you hear and read in - [Live Subtitles](https://intermind.com/translation/subtitles) — Display translated text during meetings - [Transcription](https://intermind.com/translation/transcription) — Record and save meeting transcripts - [Usage & Limits](https://intermind.com/billing/usage) — Translation time limits by plan, tracked on the Billing page # Starting a Meeting ## Quick Start ![Meetings page](https://intermind.com/img/docs/meetings/meetings-page.png) ::steps ### Navigate to Meetings Go to the **Meetings** page from the sidebar. ### Click New meeting The **New meeting** button is a split button. The main half creates a meeting and takes you straight into it. The calendar half creates a meeting **without** entering it and opens your calendar with the event pre-filled — for scheduling instead of meeting now. The list names the meeting after its participants; use the row's rename action to set your own title. ### Share the link Send it via email, messaging app, or any other channel — or use the field next to the button: it accepts a **meeting ID or link** (the button turns into **Join**) or a **contact's name or email**. Pick one or more contacts and the button becomes **Meet now** — it creates the meeting, sends the invites (email, plus a push notification on mobile), and puts you in the room. ### Join the meeting Click the **Join** button next to the meeting in the list (or open the copied link). You're taken to the pre-join setup screen. ### Configure your devices Set up your camera and microphone, then click **Join**. :: ## Scheduling a Meeting Any meeting can be added to your calendar — including one that has already met (the link is permanent, so a one-off room can become a recurring one without losing its chat and recaps): ::steps ### Go to the Meetings page Open the **Meetings** page from the sidebar. ### Click the calendar button on the meeting's row Your configured calendar provider opens in a new tab with the event pre-filled (title, join link, and recap link). Pick the date, invitees, and — for a regular meeting — the recurrence right there. ### Done The calendar event includes the meeting link for participants. The meeting row picks up the date and any later changes from your calendar; once the event is observed, the same button opens it for editing. :: ::callout{type="tip"} The calendar provider (Google Calendar or Outlook) is connected in **Integrations → Calendar** — there is no provider picker on the Meetings page itself. :: ## The Meetings List Meetings are grouped into **Scheduled** and **Recent** (the last 10). Useful controls on each row: - **Pin to top** (Recent rows, in the **⋯** menu) — keeps a meeting first in the list; pins follow your account on every device you sign in on - **Hide from list** (eye-slash on hover) — removes the meeting from your own list on every device you sign in on. If you created the meeting, the action becomes **Hide for everyone** and removes it from every participant's list - **Starting soon** — a scheduled meeting shows a live countdown ("In N min") for 30 minutes before start, and **"Now"** while it's in its scheduled window ## Meeting Host The person who creates a meeting becomes the **host**. The host has additional privileges: - Approve or deny guest access requests - Mute other participants' microphones remotely - All files and recordings produced in the meeting count toward the host's storage quota ## Meeting Capacity The maximum number of participants depends on your plan: | Plan | Max Participants | | -------------- | ---------------- | | 🆓 Basic | 50 | | ⭐ Pro | 100 | | 🏢 Business | 300 | | 🏛️ Enterprise | 1,500 | # Whiteboard A shared drawing board for sketches, diagrams and quick annotations, open on everyone's stage next to the video tiles. The [Whiteboard feature page](https://intermind.com/features/whiteboard) shows this in action. It is a paid-plan feature (Pro, Business, Enterprise) and is **off by default**: a team owner or admin switches it on under **Integrations → Whiteboard**. Until then nobody in the organization sees it. ## Opening the board 1. During a live meeting, open **More** in the cockpit and choose **Whiteboard** 2. The board opens on everyone's stage, next to the video tiles — every participant can draw, add shapes and text 3. Someone joining later sees the current drawing 4. Close the board with the close button; the drawing is not stored after the meeting ## Who can draw The board is available in meetings hosted by an organization that switched it on; guests and members of other organizations in that meeting can draw too — drawing is not limited to the host's own team. Everyone draws at the same time; there is no turn-taking or a single pen holder. The engine is [Excalidraw](https://github.com/excalidraw/excalidraw){rel=""nofollow""} (MIT), loaded only when a board is opened, so a meeting that never opens one never downloads it. ## Related - [Sharing Documents & Notes In-Call](https://intermind.com/shared-documents) — Open a document or a live note next to the video tiles - [Screen Sharing & Recording](https://intermind.com/screen-sharing) — Push what you're sharing onto every participant's main stage - [Meeting Recap](https://intermind.com/recap) — Summary, transcript, and recording after the meeting # Joining a Meeting ## Join via Link The most common way to join a meeting: 1. Click the meeting link shared with you (e.g., `https://intermind.com/abc-def-hij`) 2. If you're signed in, you go directly to the pre-join setup 3. Configure your camera and microphone 4. Click **Join** On a phone the link opens the InterMIND app — the browser only shows **Open in the app**, and the app's store when it is not installed yet. The link travels with the install: after the first launch the app opens this meeting. Tablets and computers stay in the browser. ## Join via Meeting ID If you have a meeting ID instead of a link: 1. Go to the **Meetings** page 2. Click **Join Meeting** 3. Enter the meeting ID or paste the full URL 4. Click **Join** 5. Configure your camera and microphone in the pre-join setup 6. Click **Join** to enter the meeting ## Join as a Guest If you don't have an InterMIND account, you can join ad-hoc meetings as a guest: 1. Click the meeting link — the **Pre-Join Setup** screen opens on the meeting page itself, with your camera and mic preview 2. Enter your **display name**; your browser remembers it for the next link 3. Optionally pick the language you hear and read in (defaults to your interface language) 4. Click **Join** — a host-approval request is sent and you enter the **waiting room** ("Waiting for approval") 5. Once the host clicks **Admit**, you enter the meeting On a phone the link opens the app instead, and you join as a guest there — no account needed. If the host clicks **Deny**, or does not respond within **5 minutes**, the request is declined and you can leave. ::callout{type="info"} Guest access is only available for ad-hoc meetings. Channels require a team account. :: ## Join Channel Meetings For team channels: 1. Navigate to the channel from the **Channels** page 2. Click to join the channel meeting 3. You must be a member of the team that owns the channel — if not, the meeting URL returns a 404 4. No host approval needed — team members have direct access ### Arrived first? You will be told when the next person joins :preview-mark{slug="participant-join-notification"} If you enter a meeting before the others, you do not have to sit and watch the empty room. Switch to another tab or app: when the next participant joins, you get a notification — a browser notification in the web app, a system notification in the desktop app, a push on the phone — and a tap on it brings you back to the room. The notification is only sent while the room is not on your screen; if you are looking at the meeting, the arrival is visible live. The web app asks for the browser's notification permission when you join. ## Pre-Join Setup The first time you join on a device — and again whenever your camera / microphone / speaker setup has changed since — you see the pre-join setup screen, where you can: - **Preview your camera** — See how you look - **Select microphone** — Choose from available input devices - **Select camera** — Choose from available cameras - **Select speakers** — Choose audio output device - **Start muted** — Toggle microphone and camera off before joining There is no switch for it — once you've joined with a given device setup, later joins go straight into the meeting. See [Meeting Defaults](https://intermind.com/../settings/meeting-defaults). ## Troubleshooting Joining | Issue | Solution | | ---------------------- | ------------------------------------------------------------------------------------------- | | "Meeting not found" | Check that the meeting ID or link is correct | | Camera/mic not working | Make sure you've granted browser permissions for camera and microphone | | Stuck in waiting room | The host hasn't approved your request yet — wait or contact them | | "Access denied" | The host denied your join request, or you're not a member of the team that owns the channel | # Meeting Controls During a meeting, a control bar at the bottom of the screen gives you access to all meeting functions. ## Audio & Video ### Microphone - Click the **microphone icon** to mute/unmute - Click the **arrow next to the microphone** to select a different microphone device - When muted, a red indicator shows on your video tile - An audio level indicator shows when your microphone is picking up sound ### Camera - Click the **camera icon** to turn on/off - Click the **arrow next to the camera** to select a different camera - When off, your video tile shows your avatar instead ### Speaker - Select your preferred audio output device from the settings - This controls where you hear other participants and translations ## Translation Controls ### Real-Time Translation - Open the **More** menu in the control bar and click **Enable translation** (Alt+T) — the menu uses the language icon - When enabled, you hear other participants' speech translated into your chosen language - The original audio is turned down to 20 % under the translated version, so you still hear who is speaking and when - Only available when the meeting has at least two languages in play (the menu item is hidden in single-language rooms) ### Language Selector - Open the cockpit **Settings** panel (gear icon in the More menu) and pick the language under **Translate for me into** - Choose from 23 supported languages (see [Choosing Languages](https://intermind.com/../translation/languages)) - Your choice is saved on your account and persists across sessions - The picker is disabled when your translation usage limit is reached ### Subtitles - Open the **More** menu and click **Show subtitles** to toggle live subtitles - Subtitles appear at the bottom of the meeting screen - They show the translated text in real-time - Layout adapts automatically for right-to-left (RTL) scripts ### Transcription - Transcription is **automatic** — there is no button to start or stop it - Speech is captured as text throughout the meeting, attributed to each speaker - After the meeting, the transcript is reachable from the recap in the meeting chat — see [Meeting Recap](https://intermind.com/recap) - For more details, see [Transcription](https://intermind.com/../translation/transcription) ## Screen & Video Controls ### Self-View - Toggle to show or hide your own video feed - Useful to reduce distraction while presenting ### Resolution - Choose the maximum video resolution - Lower resolution saves bandwidth on slow connections - Options are Auto, 720p, 360p, 180p ## Presentation Tools ### Screen Sharing See [Screen Sharing & Recording](https://intermind.com/screen-sharing) for details. ### Laser Pointer - Available during screen sharing presentations - Point at specific areas on the shared screen - Other participants see your pointer in real-time — details on the [Screen Share & Laser Pointer feature page](https://intermind.com/features/laser-pointer) ## Participant Management ### Participants Sidebar - Click to open the participants panel on the right side - See all participants in the meeting - View each participant's audio/video status ### Host Controls If you are the meeting host, you have additional controls: - **Mute participant** — Remotely mute any participant's microphone - **Admit / Deny guests** — Accept or reject guest access requests from the toast notification - **Make host** — Open a teammate's row in the participants menu and choose **Make host** to hand the meeting over on the spot; they become moderator immediately and you continue as a regular participant. See [Transferring the host](https://intermind.com/../chat/channels#transferring-the-host) for who can do this and the requirements. When you mute a participant, they see a notification: *"Your microphone was disabled by the host."* ### Participant Permissions The host can limit what participants may do in the meeting. Open the cockpit **Settings** panel (gear icon in the More menu) — the **Participant permissions** section lists the toggles: - **Microphone** — allow participants to unmute themselves - **Camera** — allow participants to turn their camera on - **Screen sharing** — allow participants to share their screen - **Reactions** — allow participants to send emoji reactions - **Chat** — allow guests to send chat messages How they work: - Settings apply to **all non-host participants at once** and are **saved for this meeting link** — a lock set today is still in force the next time the same link meets. Only the host is unrestricted. - Locks block **enabling**, never disabling: a participant can always mute themselves or turn their own camera off. If the host revokes a permission mid-call, live devices are switched off immediately. - A locked participant sees the control disabled with the explanation **"Disabled by the host"**; a locked chat input shows the same text as its placeholder. Raise hand always stays available. - In channel (team) meetings only the **Screen sharing** toggle is shown — the others assume an untrusted-guest context. ### End Meeting for All The host's **More** menu has an **End meeting for all** item (shown to the host only). It finalizes the meeting and disconnects every participant; signed-in participants are returned to their meeting list, and the recap is produced as usual. If a recording or screencast is running, ending for all is blocked until you stop it — a notice explains which one. ## Empty Stage Clicking video tiles moves them between the main stage and the sidebar. If you move **every** tile to the sidebar, the empty stage shows a getting-started panel: shortcut reminders for translation, layout, chat, and devices, plus a **Copy Link** button. Click anywhere on the background (or press `Alt + L`) to bring the tiles back. ## Reactions & Hand Raise - Click the **Reactions** button to send emoji reactions visible to all participants - Click the **Hand Raise** button to signal you want to speak - For more details, see [Reactions & Hand Raise](https://intermind.com/reactions) ## Meeting Chat - Click the **chat icon** to open the in-meeting chat sidebar - Send messages to all participants during the meeting - The chat sidebar is resizable by dragging its edge - Chat messages are persisted and available after the meeting For full chat features, see [Chat](https://intermind.com/../chat). ## Leaving a Meeting - Click the **Leave** button (door icon) to exit the meeting - The meeting continues for other participants — this is true for the host as well; to end the session for everyone, use **End meeting for all** (above) - Your chat messages and transcription are preserved ## Keyboard Shortcuts All in-meeting shortcuts use **Alt** (or **Option ⌥** on Mac) plus a letter: | Shortcut | Action | | --------- | ------------------------------------------- | | `Alt + M` | Toggle microphone | | `Alt + C` | Toggle camera | | `Alt + T` | Toggle translation | | `Alt + H` | Toggle chat sidebar | | `Alt + P` | Toggle participants sidebar | | `Alt + L` | Reset layout to defaults | | `Alt + R` | Resize the open chat / participants sidebar | | `Esc` | Close cockpit / chat / participants panel | The same list is available in-call via the **Help** modal in the cockpit menu. # Screen Sharing & Recording ## Screen Sharing Share your screen to present documents, slides, or applications during a meeting. ### How to Share Your Screen 1. Click the **Share screen** button in the meeting control bar (on a narrow window it moves into the **More** menu) 2. Your browser will show a screen sharing dialog 3. Choose what to share: - **Entire Screen** — Share everything visible on your screen - **Application Window** — Share a specific application - **Browser Tab** — Share a single browser tab (audio included) 4. Click **Share** ### During Screen Sharing - Other participants see your shared screen as the main display - Your camera video moves to a smaller tile - You can use the **laser pointer** to highlight areas on your shared screen — see the [Screen Share & Laser Pointer feature page](https://intermind.com/features/laser-pointer) for how it lands on every display - Click **Stop screen sharing** to end the screen share ### Presenter Modes While you are sharing, the arrow next to the **Share** button opens **Presenter mode** — how your camera sits with your content on everyone else's screen. You pick it; every participant sees the layout you chose, including people who join after you picked it. | Mode | What everyone sees | | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------- | | **Content only** | Your content fills the stage; your camera stays in the filmstrip with everyone else. This is the default. | | **Standout** | Your camera floats over the content in the bottom-left corner. | | **Side by side** | The stage splits: content on the left, your camera on the right. On a narrow phone screen the camera moves under the content instead. | Notes: - The mode needs your camera on. With the camera off, everyone stays on **Content only** until you turn it back on. - Your camera is shown as it is — InterMIND does not cut you out of your background. - The mode applies to your own share. If several people are sharing at once, each share carries the mode its presenter picked. - Viewers keep their own zoom (**Zoom to fit** / **Original size**) and the laser pointer in every mode — the content is never re-encoded, so it stays as sharp as what you captured. ### Tips for Screen Sharing - Close notifications and private content before sharing your entire screen - Sharing a browser tab includes tab audio, which is useful for sharing videos - The shared content quality depends on the video resolution setting ## Mobile Screen Sharing Share your screen from the InterMIND app on iOS and Android — no desktop needed. ### How to Share Your Screen 1. Open the **···** (More) menu during a meeting 2. Tap **Share screen** 3. Your phone's system dialog appears — on iOS this is the screen broadcast picker, on Android the screen-capture consent prompt 4. Confirm to start Unlike sharing a window or tab on desktop, a mobile share always sends your **entire screen** — that's a platform limit (iOS ReplayKit and Android MediaProjection both only capture the full screen). ### During Screen Sharing - Other participants see your screen the same way they would a desktop share - Tap **Stop screen sharing** in the **···** menu to end it — or use your phone's own system control (the recording indicator in the status bar on Android, or the red bar at the top of the screen on iOS) - If the host has turned off screen sharing for participants, the option shows an explanation instead of starting a share ## Recording Record meetings for later review or to share with people who couldn't attend. Both recording modes live in the **More** menu, and there are two of them: | Item | Who sees it | Where the file goes | | -------------------------- | --------------------------------------------- | ----------------------------- | | **Start server recording** | Moderators (the host and promoted moderators) | Your team's cloud storage | | **Start local recording** | Anyone whose browser supports screen capture | Downloaded to your own device | ### Server Recording 1. Open the **More** menu and click **Start server recording** 2. A **Recording** indicator appears in the control bar for everyone in the room 3. Click **Stop server recording** in the same menu to end it Before it starts, InterMIND checks the **meeting host's** storage: if the team is at capacity the recording is refused with an explanation, and if the host can't be resolved you get a "couldn't verify the storage limit" notice instead. ### Local Recording 1. Open the **More** menu and click **Start local recording** 2. Your browser asks for permission to capture your screen — select your screen or tab 3. The recording captures your microphone audio, tab audio (other participants' voices and translations), and the screen content 4. The item turns into **Stop local recording** with a running timer; you can also stop it with the browser's own "Stop sharing" button 5. On stop, the file downloads to your device as `.webm` (or `.mp4`, depending on your browser) A local recording never touches team storage, so no storage check applies to it. ### Important Notes About Recording - **Browser protection** — If you try to close the browser tab during recording, a warning dialog appears to prevent accidental data loss - **Recording status** — Other participants can see that a server recording is running - **Host ownership** — Server recordings count toward the meeting host's storage quota, regardless of who started them ### Recording Storage Server recordings are stored in your team's shared cloud storage. Storage limits depend on your plan: | Plan | Storage Limit | | ---------- | ------------- | | Basic | 1 GB | | Pro | 30 GB | | Business | 1 TB | | Enterprise | 5 TB | To manage recordings and storage, see [Team Storage](https://intermind.com/../users/storage). ## Present to Everyone (Stage Sync) When two or more things are shared at once — screens, a [document or note](https://intermind.com/shared-documents), a recap — each participant can look at whichever one they want without affecting anyone else. Click a share's tile in the sidebar to bring it into your own main area; that choice is private and changes only what you see. **Present to everyone** pushes what you're currently looking at onto every participant's main stage at once: 1. Bring the share you want onto your main area 2. Click **Present to everyone** above the main stage 3. That share becomes the main-area view for every participant, immediately — including someone who joins the meeting afterwards The button only appears when your current main-area view isn't already the one presented to the room, and only while two or more things are shared — with a single share, it's already everyone's default main view. ### Scrolling and Zooming a Shared Tab If you share a browser tab (not a full screen or an application window), you can scroll its content for everyone without switching back to that tab yourself: 1. Share a browser tab 2. Make sure your preview is in **fit** view (the magnifying-glass button toggles between **fit** and **original size**) 3. Scroll with your mouse wheel over your own share preview — the tab you're sharing scrolls, and everyone watching sees it move The first scroll asks your browser for permission. If it's blocked, allow **"Scrolling & zooming of shared tabs"** in your browser's site permissions and share the tab again. This only works for the person sharing the tab, in Chromium-based desktop browsers (Chrome, Edge) — everywhere else scrolling stays local to you. Viewers keep their own **fit** / **original size** choice and the laser pointer regardless of what the sharer scrolls to. ## Related - [Sharing Documents & Notes In-Call](https://intermind.com/shared-documents) — Share a document, note, or recap into the meeting # Reactions & Hand Raise Express yourself during meetings without interrupting the speaker. ![Reactions and Raise hand in the More menu](https://intermind.com/img/docs/meetings/reactions-menu.png) ## Emoji Reactions Send quick emoji reactions that appear floating on screen for all participants. ### How to Send a Reaction 1. Open the **More** menu in the control bar — the **Reactions** row is at the top 2. Choose an emoji: 👍 👏 😂 ❤️ 🎉 🤔 3. The emoji appears as a floating animation on everyone's screen 4. Reactions automatically disappear after a few seconds ### When to Use Reactions - 👍 **Thumbs up** — Agree with something or acknowledge - 👏 **Clapping** — Applaud a presentation or idea - 😂 **Laugh** — React to something funny - ❤️ **Heart** — Show appreciation - 🎉 **Celebration** — Celebrate an achievement - 🤔 **Thinking** — Flag a doubt without interrupting Reactions are a great way to provide feedback during presentations without unmuting your microphone. ## Hand Raise Raise your hand to signal that you want to speak, without interrupting the current speaker. ### How to Raise Your Hand 1. Open the **More** menu and click **Raise hand** — it sits right under the reactions row 2. A hand icon appears on your video tile, visible to all participants 3. The host and other participants can see who has their hand raised 4. The item becomes **Lower hand** — click it to lower your hand ### Hand Raise Best Practices - Raise your hand during presentations to queue up for questions - The host can see a list of raised hands and call on participants in order - Lower your hand after you've spoken - Hand raise status persists until you manually lower it or leave the meeting ## Visibility - Both reactions and hand raises are **visible to all participants** in the meeting - Reactions appear as floating animations across the meeting screen - Raised hands show as an indicator on the participant's video tile and in the participants sidebar # Guest Access Guest access allows people without an InterMIND account to join ad-hoc meetings. This is perfect for external participants like clients, interviewees, or collaborators. ![The host's «wants to join» notice with Admit and Deny](https://intermind.com/img/docs/meetings/guest-wants-to-join.png) ## How Guest Access Works ### For Guests 1. **Click the meeting link** shared by the host 2. You're sent to the **Join Meeting** screen 3. Enter your **display name** and click **Join** 4. The **Pre-Join Setup** screen opens — preview your camera and mic 5. Click **Join** again. An anonymous account is created and the host-approval request is sent 6. You enter the **Waiting Room** ("Waiting for approval") 7. Once approved, you enter the meeting with full access to: - Video and audio - Real-time translation - Subtitles - In-meeting chat - Reactions and hand raise ### For the Host When a guest requests to join your meeting: 1. You receive a toast notification: **"{name} wants to join"** 2. You can: - **Admit** — The guest enters the meeting - **Deny** — The guest is informed their request was declined Both the guest and host see updates instantly. ## Guest Limitations Guests have some limitations compared to registered users: | Feature | Registered User | Guest | | ----------------------- | --------------- | -------------------------- | | Join ad-hoc meetings | ✅ | ✅ (host approval required) | | Join team channels | ✅ | ❌ | | Use translation | ✅ | ✅ | | Send chat messages | ✅ | ✅ (in-meeting only) | | Access persistent chats | ✅ | ❌ | | Create meetings | ✅ | ❌ | | Manage settings | ✅ | ❌ | | Team management | ✅ | ❌ | ## After the Meeting When the meeting ends or the guest leaves, the exit screen says what this session leaves behind: the recap in the guest's language (ready a few minutes after the call), the transcript and the recording, which stay with the host's account and its members. The chat of an ad-hoc call is wiped for everyone when the call ends. The guest has two options: - **Keep this meeting** — creates a free account and opens that one session's recap in the guest's language; nothing else of the meeting - **Ask the host to add me** — one tap, nothing to type; the host receives one email and sees the request, with the guest's name, on the recap page. The host enters the address they have for the guest, and the invite goes out by email; accepting it with a free account makes the guest a member, and the next sessions and their recaps reach them A guest who closes the screen keeps nothing, and the anonymous guest identity is deleted within 24 hours. ## Important Notes - Guest access is **only available for ad-hoc meetings**, not channels - Each guest gets a **temporary anonymous account** that is automatically cleaned up - Guests don't need to install anything — it all works in the browser - The host must be present in the meeting to approve guest requests - Multiple guests can request to join simultaneously — the host sees all pending requests - **Guest requests expire after 5 minutes** — if the host doesn't respond within 5 minutes, the request is automatically declined # Sharing Documents & Notes In-Call During a meeting you can put a document or a rich-text note on everyone's screen, next to the video tiles. Any participant can share. The [Document Sharing feature page](https://intermind.com/features/document-sharing) shows this in action. ## Sharing a Document Documents linked from Google Docs or OneDrive in the meeting chat (see [File Sharing](https://intermind.com/../chat/files)) can be opened for the whole conference: 1. During a live meeting, click the linked document in chat 2. It opens in a shared panel for every participant, labeled with who shared it 3. Each participant scrolls and zooms independently 4. The sharer closes the panel for everyone with the close button ## Sharing a Note Rich-text notes from chat can be shared the same way: 1. Open the message menu on a note in the meeting chat 2. Choose **Share to conference** 3. The note opens next to the video tiles for all participants While shared: - **The sharer** edits the note live — everyone sees the changes and the sharer's cursor in real time - **Everyone else** reads it in their own language and can toggle between **Translated**, **Original**, and **Original + translation** views ## Sharing a Meeting Recap A [meeting recap](https://intermind.com/recap) message in chat can also be shared into the conference with the same **Share to conference** action — useful for reviewing the previous session's summary together. Each viewer reads it in their own language. ## Related - [File Sharing](https://intermind.com/../chat/files) — Upload files and link Google Docs / OneDrive documents in chat - [Document Translation](https://intermind.com/../chat/document-translation) — Read shared PDF and Office files in your language - [Meeting Recap](https://intermind.com/recap) — Summary, transcript, and recording after the meeting - [Screen Sharing & Recording](https://intermind.com/screen-sharing) — Push what you're sharing onto every participant's main stage - [Whiteboard](https://intermind.com/whiteboard) — Draw together on a shared board, saved for anyone who joins late # Meeting Recap After a meeting ends, InterMIND produces a **recap** — a single page with everything the session left behind: - **Summary** — an AI-generated summary of the discussion - **Transcript** — the full speaker-by-speaker transcript - **Recording** — the video recording, when the session was recorded The recap is displayed in your language: whatever language the meeting was held in, the summary is translated for you on demand. A worked example is on the [AI Meeting Recap feature page](https://intermind.com/features/recap). ## Where to Find It - **Email** — every signed-in participant of the session receives the recap link by email once processing completes; a guest who joined without an account has no mailbox on file and gets no letter - **Chat** — in channels, a recap document message is posted to the channel chat; click it to open the recap - **Inbox** — after an ad-hoc meeting (a link without a channel) the same recap document lands in each participant's personal Inbox under Chats, so the recaps of your ad-hoc calls stay in one place; the recap email's footer points there - **Calendar** — the calendar event created for a meeting includes the recap link, so it works from day one - **Recap copy (BCC)** — the host can add extra addresses that receive a copy of the recap email, e.g. a CRM inbound address (see below) The recap link (`…/r/…`) is permanent — the same link serves every session of the meeting. ## Who Can Open It Recaps are **members-only**: opening the link requires signing in, and access is limited to the host, the people who participated, and members of the host's team. Forwarding the link to anyone else does not grant access. A guest who joined by link gets nothing after the call unless they **keep the meeting** from the exit screen: that creates a free account and opens this one session's recap — summary, transcript and recording — in the guest's language, nothing else of the meeting. A guest who instead asks the host to add them appears on the host's recap page with a one-click invite; once added, the guest is a member and opens recaps like any other member. ## Editing the Summary Meeting members can correct the AI summary directly on the recap page: 1. Open the recap and click **Edit** under the summary 2. Fix the text and save Every edit creates a new revision. **Version history** shows the AI original and each edit as a word-level diff, with author and timestamp. The recap message title in chat updates to match the edited summary. **Open tasks of the organization.** In an organization with team status pages on, every task and promise a recap records joins the organization's task chain from the day pages were switched on. When a recap is written, the open items the host may read (an admin: the whole organization; a member: the sessions they hosted or attended since joining, plus anything assigned to them) are judged against what was said in this session: an item someone reported as finished is marked done; an item that was discussed but not finished is marked not done, with the reason in the words of the meeting; an item nobody brought up stays open, untouched. These verdicts are not part of the recap — the recap holds only the tasks born in this meeting, as task boxes. The organization's open tasks, with their verdicts and the recap each one rests on, live on the team's status page and in the assistant (`read_team_page`), so one meeting's summary is never a list of everything the organization owes. A session with anyone from outside the organization in it, a guest by link included, judges nothing: the chain is the organization's internal state, and that session's recap reaches the outsider too; its own tasks still join the chain. A member's own verdict on a task beats the model's, and the model never overturns it. At the start of the next session Mia names the open items and their owners, so they are spoken about rather than forgotten. Recaps written before 2026-10-20 may still carry a **Carried over** section; it reads as before. :preview-mark{slug="team-pages"} ## Rating the Summary Under the summary you'll see **"Was this summary useful?"** with thumbs up/down. A thumbs-down offers a quick reason — wrong numbers, missed key points, wrong focus, or made things up. Ratings help improve summary quality. ## Recap Archive - **Channels** keep the recap of **every past session** — open the recap page and switch between sessions - **Ad-hoc meetings** keep only the **latest session's** recap, mirroring how their chat history is purged after each call ## Deleting a Recap The meeting **host** can delete a session's recap artifacts — summary, transcript, recording, and their translations. Deletion is permanent; the recap is not regenerated. ## Recap Copy (BCC to Your CRM) The host can have every recap of a meeting or channel also sent — as a hidden BCC — to extra addresses, typically a CRM or tracker inbound email (e.g. Pipedrive Smart BCC). Where to set it up (host only): - **Meetings page** — expand your meeting's row and fill the **Recap copy:** field - **Channel chat** — display-settings menu (gear icon) → **Recap copy** Each new address must confirm delivery first: InterMIND sends a **test email** shaped like a real recap, and someone has to open it inside the receiving tool and click its confirmation link within **1 hour**. Until then the address is marked pending and no copies are sent. If the window passes, pick the address again in the field for a fresh test. If the test email doesn't arrive, allow `noreply@intermind.com` as a sender in the receiving tool. Details: - Confirmed addresses are saved to your personal address book (up to **10**) and can be reused across your meetings and channels - The copy is the same email participants get: the summary text, plus links to the full recap and transcript — those links still require signing in as a meeting member - Available on every plan ## Requirements A recap is produced from the meeting's transcription — see [Transcription](https://intermind.com/../translation/transcription) for how transcripts are captured. When an ad-hoc meeting ends without a recap — nothing was transcribed, too little was said to summarize, or the summary could not be written — a short note from Mia in each participant's Inbox says which, with the transcript link when there is one; no email is sent. ## Related - [Transcription](https://intermind.com/../translation/transcription) — Where transcripts come from - [Screen Sharing & Recording](https://intermind.com/screen-sharing) — Recordings included in the recap - [Sharing Documents & Notes In-Call](https://intermind.com/shared-documents) — Review a recap together in the next session # Test Room The test room at [/browser-test](https://intermind.com/browser-test) is a meeting-shaped page with nobody else in it. Everything you would check in front of other people — camera, microphone, speakers, screen sharing, network — you check here first, on your own. ![The test room: camera preview, microphone level, speakers, screen sharing and network checks on one page](https://intermind.com/img/docs/meetings/device-test-room.png) It needs no account and no meeting link: open it, allow camera and microphone, and the page runs. ## What it checks ### Camera A live preview of what other participants would see. If you have more than one camera, pick the one you want — the choice is stored in this browser and is the camera your next meeting starts with. ### Microphone A level meter that moves while you speak. Say something: when the bars move, your microphone is heard. Pick a different microphone from the list if the bars stay flat. ### Speakers Play the test sound and confirm you hear it. On browsers that support output selection (Chrome, Edge), you can also choose which speaker or headset plays it; Safari always uses the system default. ### Screen sharing Start a share to confirm your browser allows it, and see exactly what would be sent. Nobody is watching — you are alone in the room. Stop it when you are done, or dismiss the picker to cancel. ### Connection The page also runs the technical checks automatically: - **Codecs** — whether your browser can encode VP9, the codec our meetings publish with - **ICE candidates and STUN** — whether your network lets a call reach the outside world, and how long the first response takes - **Bandwidth** — a five-second estimate, compared against the quality presets (360p, 720p, 1080p) A summary badge at the top says how many checks came back short. ## How to get there - From **Meetings** — the signal icon next to the meeting field - From the **pre-join screen** — the "open the test room" link under the buttons, which opens in a new tab so you do not lose the meeting you were about to join - From the site footer, or directly at `/browser-test` ## If a check fails The test room reports what it sees; the fixes live in [Troubleshooting](https://intermind.com/docs/troubleshooting). Camera and microphone permissions are the most common cause — a blocked permission shows as a denied prompt and no preview. # Meetings & Conferences InterMIND provides two types of video meetings for different use cases. The product view — instant creation, guest access, recording, participant limits — is on the [Ad-hoc Meetings feature page](https://intermind.com/features/meetings). ## Meeting Types ### Ad-hoc Meetings Ad-hoc meetings are **one-time meetings** for quick calls with anyone: - Created instantly — no scheduling required - Shareable link — anyone with the link can request to join - **Guest access** — people without accounts can join (host must approve) - Chat history is purged after the call — the meeting transcript and any attached agenda note/files are preserved (the agenda re-appears in chat at the start of the next conference) - Perfect for client calls, interviews, and external meetings ### Channels Channels are **persistent meeting rooms** for your team: - Always available — join anytime from the **Channels** page - **Members only** — requires team membership; non-members get a 404 on the meeting URL - Chat history is preserved between sessions - Perfect for daily standups, team discussions, and ongoing collaboration ## Creating Meetings The Meetings page in the sidebar is one row of controls plus your meetings: | Control | What Happens | | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **New meeting** | A split button. The main half creates a meeting and takes you straight into it (through the pre-join screen). The calendar half creates the meeting **without** entering it and opens your calendar with the event pre-filled. Copying the link without joining lives in the row's **⋯** menu and inside the room. | | **Search field** | Paste a meeting ID or link to join — or type a contact's name or email and send them an invite (a new meeting is created and the invite goes out by email, plus an in-app notification for registered users). | To schedule a meeting, use the **calendar button** on its row in the list — it opens your configured calendar provider (Google Calendar or Outlook) with the meeting link pre-filled. Dates, invitees, and recurrence are set in the calendar itself; the list picks them up automatically. You can attach a **Note** or a **File** to any of your meetings — expand its row in the list. Attached content is sent to the meeting chat at start. ## In This Section - [Starting a Meeting](https://intermind.com/meetings/start) — Create and launch meetings - [Joining a Meeting](https://intermind.com/meetings/join) — Join via link, ID, or invitation - [Meeting Controls](https://intermind.com/meetings/controls) — Camera, microphone, and all meeting tools - [Screen Sharing & Recording](https://intermind.com/meetings/screen-sharing) — Present your screen and record calls - [Guest Access](https://intermind.com/meetings/guest-access) — How guests join without an account - [Reactions & Hand Raise](https://intermind.com/meetings/reactions) — Emoji reactions and hand raising - [Sharing Documents & Notes In-Call](https://intermind.com/meetings/shared-documents) — Put a document or live note on everyone's screen - [Meeting Recap](https://intermind.com/meetings/recap) — AI summary, transcript, and recording after the call # Messages Learn how to use the InterMIND chat to communicate with your team and meeting participants. ![Channels page](https://intermind.com/img/docs/chat/chats-page.png) ## Sending Messages ### Text Messages 1. Open the **Chat** panel from the meeting sidebar, or pick a channel from the **Channels** page 2. Type your message in the input field at the bottom 3. Press **Enter** or click the **Send** button Messages are delivered instantly to all participants. ### Message Formatting Messages support basic formatting: - Standard text input - Emoji support (use your system emoji picker or type emoji codes) - URLs are automatically converted to clickable links ## Drafts What you have typed but not sent stays with the chat. Switch to another channel, close the tab or relaunch the app and the text, together with the message you were replying to, is back in the input field when you open that chat again. Drafts follow you between devices: start a message in the browser and finish it in the mobile app, or the other way round. Sending the message, or clearing the field, removes the draft everywhere. A draft untouched for 30 days is dropped. Files and pictures waiting in the composer, and a recorded voice note that is not sent yet, are kept only on the device where you added them. ## Undo Send in the Meeting Chat :preview-mark{slug="chat-undo-send"} In the chat of a meeting, a message you send waits five seconds before it reaches the room. A bar above the input field counts down and offers **Undo**: the text, together with its files, voice note and the message you were replying to, returns to the input field, and nobody in the room has seen it. Files and voice notes wait the same five seconds. The delay is your own setting — switch **Undo send** off in the chat's gear menu for instant delivery. The private chat with Mia has no delay. While the message waits, the AI of your organization reads the text. If it looks personal — an opinion about a colleague, money, health, "don't tell the others" — or like a question for Mia, the countdown stops and asks whether to send it to everyone, to Mia only, or to delete it. The check needs AI features switched on for your organization; with them off, the five-second delay still works on its own. ## Editing Messages You can edit your own messages after sending: 1. Hover over the message you want to edit 2. Click the **Edit** (pencil) icon 3. A **fullscreen editor** opens with a rich-text toolbar (bold, italic, strikethrough, headings, lists, blockquotes, links, code blocks) 4. Modify the text 5. Click **Save** to confirm or **Cancel** to discard **Important notes:** - Only the message author can edit their messages - The "(edited)" indicator appears only when the actual text content changes — formatting-only changes (e.g., adding bold) do not mark the message as edited - Translation is re-triggered when text changes, but preserved on format-only edits ### Viewing Edit History Readers can see what changed: open the chat's display-settings menu (gear icon in the chat header) and enable **Show Edit History**. Edited messages then show their previous versions above the current text as word-level diffs, each with its own timestamp. When you read a message in translation, the diff is built between translated versions, not the original language. The preference is per-device. ## Deleting Messages To delete a message you sent: 1. Hover over the message 2. Click the **Delete** (trash) icon 3. Confirm the deletion Deleted messages are removed for all participants. **Host delete:** The meeting host can delete any participant's message — the same **Delete** option in the message menu is available on others' messages when you're the host. ## Replying to Messages Open a message's context menu and choose **Reply**. The reply is staged as a chip above the input; send it like a normal message. The quoted block in the sent message is clickable and scrolls readers to the original. If you select part of a message's text before clicking **Reply**, only the selected text is quoted — otherwise the whole message is. Transcript messages can be replied to as well. ## Forwarding Messages Two ways to forward: - **Context menu** — open a message's menu → **Forward** and pick a target channel from the submenu. Targets are channels you belong to, plus your own **Inbox** (shown as "Saved (Inbox)"). - **Drag and drop** — drag the message bubble onto a channel in the sidebar. The row highlights when it will accept the drop. Forwarding **stages a draft** in the target chat rather than sending immediately: a chip appears above that chat's input ("Forward N messages"), you can type a comment, and the forward goes out with your **Send**. Discard it with the chip's **×**. What to know: - Forwarded messages carry a **"Forwarded from {name}"** label with the original author's name; the copy is sent by you. Click the label to open the original in its chat — if you are not a member of that chat, you see that the original isn't available. The original message itself gets no mark when it is forwarded - Reactions, pins, and edit history do not travel with the forward - Text, images, and files can be forwarded; transcripts can't (the menu explains this) - A recap document forwards as a link — opening it still requires being a member of the source meeting - Forwarding a message that's part of a selection forwards the whole selection; a photo album forwards as one unit ## Selecting Multiple Messages Drag on blank space in the message list (beside or between bubbles) to select whole messages — dragging on the text itself keeps normal text selection. On touch devices, tap messages to toggle them once selection is active. A selection bar appears at the bottom with the count and bulk actions: - **Forward** — forward the whole selection to a channel - **Delete** — delete all selected messages after one confirmation; available only when every selected message is yours (or you're the host). When it's locked, the bar explains why - **Cancel** — or press **Escape**, or click blank space, to clear the selection Right-clicking a selected message shows the same selection-scoped actions instead of the single-message menu. ## Notes Send rich-text notes in the chat for longer, formatted content: 1. Click the **"+"** button next to the message input 2. Select **Add Note** 3. A fullscreen editor opens with a toolbar: headings (H1–H3), bold, italic, strikethrough, lists, blockquotes, links, code blocks 4. Write your note and click **Send** Notes are stored as HTML files and rendered in a sandboxed preview within the chat. You can edit a note later via the **Edit Note** option in the message menu. ## Reactions React to any message with emoji: 1. Right-click a message (or open its menu from the chevron in the bubble's corner) 2. The quick row at the top of the menu is a status on the message: 👍 ✅ 👀 🙏 🎉 🤔 — agreed, done, seen, thanks, congratulations, a question 3. Any other emoji is one tap further: the **Add reaction** button at the end of the row opens a picker with search 4. Your reaction appears below the message; tapping a reaction already there adds yours or takes it back Multiple participants can react to the same message, and reactions are grouped by emoji with the avatars of those who reacted. ## Pinning Messages Pin important messages so they're easy to find: 1. Hover over the message 2. Click the **Pin** icon 3. The message is highlighted and accessible from the pinned messages section To view pinned messages: - Look for the **Pinned** indicator or filter in the chat panel - Pinned messages remain at the top or in a separate section for easy access To unpin: - Click the **Unpin** icon on a pinned message ## Message History ### Viewing History All messages are stored permanently: - Scroll up in the chat to load older messages - Messages load in batches as you scroll - The full history is preserved even after meetings end ### Searching Messages Use the search functionality to find specific messages: - Type keywords in the search bar - Results show matching messages with context - Click a result to jump to that message in the chat ## Chat Notifications You'll receive notifications for new messages: - **In-app badge** — Unread message count appears on the chat icon - **Browser tab title** — The tab title updates to reflect unread chats ## Tips - Use **Enter** to send messages quickly - **Shift + Enter** creates a new line without sending - **Alt + Arrow Up/Down** navigates through your sent message history - **Ctrl/⌘ + F** opens chat search - **Ctrl/⌘ + /** opens the Help panel - Messages are auto-translated if you have a different language set (see [Chat Translation](https://intermind.com/translation)) - React to messages instead of typing short responses like "OK" or "👍" # Chat Translation InterMIND automatically translates chat messages so team members can communicate in their preferred languages without any extra effort. ## How It Works When a message is sent in the chat: 1. The message is stored in its original language 2. The system identifies all participants who use a different language — including those currently offline 3. The message is translated into each required language 4. Online recipients see the translation in real-time; offline participants receive translations when they reconnect 5. The original text is always available if needed Translation happens transparently — you simply type in your language, and everyone reads in theirs. The product view of this mechanism lives on the [Multilingual Chat feature page](https://intermind.com/features/multilingual-chat). ## Setting Your Chat Language The language you read chat in follows your account language settings: 1. Open the menu on your **account entry** at the bottom of the sidebar 2. Keep the default (same as your interface language) or pick a different one under **Translate for me into** 3. All incoming chat messages are translated to that language ![The account menu at the bottom of the sidebar, with Translate for me into next to Interface Language](https://intermind.com/img/docs/chat/translation.png) The same setting also drives in-meeting voice translation. ## Viewing Original Messages The chat panel has a **Show Original with Translation** display toggle. When on, each translated message is shown in a two-column layout with the original text alongside the translation. Notes have their own per-message **Translated / Original / Diff** switch in the preview header. ## Translation Accuracy ### What Works Well - Common business phrases and terminology - Short, clear sentences - Standard greetings and responses ### Best Practices for Clearer Translations - Write in clear, simple sentences - Avoid slang, idioms, or culture-specific references - Use proper punctuation - Break complex ideas into shorter messages - Spell out abbreviations on first use ## Translation and File Messages - Text messages are translated automatically - File names and captions are not translated - Image content is not translated (only accompanying text) ## Chat Translation Limits Chat translation is unlimited on every paid plan. Only the free Basic plan carries a monthly word allowance. Usage is tracked per **meeting host** (the person who created the meeting) using a **rolling 30-day window**. | Plan | Chat Translation | | ---------- | ---------------- | | Basic | 10K words/month | | Pro | Unlimited | | Business | Unlimited | | Enterprise | Unlimited | As older usage expires, your available words increase. When the limit is reached, new messages are still delivered but not translated. You can: - Continue chatting without translation - Upgrade your plan for a higher limit - Wait for older usage to expire ## Supported Languages Chat translation supports the same 23 languages as meeting translation, on every plan. See [Choosing Languages](https://intermind.com/../translation/languages) for the full list. ## Tips - Set your preferred language once in settings — all chats auto-translate - If a translation looks off, check the original message for context - For critical communications, consider sending both the original and a note about key terms - Translation quality is best for commonly spoken language pairs ## Long Messages Messages longer than **1,000 characters** are automatically split by paragraph breaks (`\n\n`) and each chunk is translated separately. A single paragraph that still exceeds 1,000 characters is broken further at sentence, clause, or word boundaries, so long text is always translated in full rather than skipped. # File Sharing Share files, images, and documents directly in InterMIND channels and meeting conversations. Each upload can be up to **25 MB**. ## Uploading Files ### Drag and Drop The easiest way to share a file: 1. Drag a file from your computer 2. Drop it onto the chat area 3. The file uploads automatically and appears in the chat ### Upload Button 1. Click the **+** button to the left of the chat input 2. Choose **Upload File** and pick a file from your computer 3. The file uploads and appears as a message in the chat The **+** menu also offers **Add Note** — a shared note written in chat instead of an uploaded file. ![The + menu next to the chat input: Upload File, Google Docs, OneDrive and Add Note](https://intermind.com/img/docs/chat/files.png) ### Pasting Images You can paste images directly from your clipboard: 1. Copy an image (screenshot, from a webpage, etc.) 2. Click in the chat input 3. Press **Ctrl+V** (or **Cmd+V** on Mac) 4. The image is uploaded and shared ### Linking Cloud Documents The **+** menu can also link documents from cloud storage: 1. Click the **+** button next to the chat input 2. Choose **Google Docs** or **OneDrive** 3. Connect your account (first time only) and pick a document The document appears in chat as a link — recipients open it with their own access rights in the cloud. During a live meeting, a linked document can be opened for the whole conference — see [Sharing Documents & Notes In-Call](https://intermind.com/../meetings/shared-documents). ## Supported File Types ### Images Supported image formats: - JPEG / JPG - PNG - GIF - WebP - SVG Images display as inline previews in the chat. Click an image to view it full-size. ### Documents You can share various document types: - PDF files - Office documents (Word, Excel, PowerPoint) - Text files - Other common file formats Documents appear as download links with file name and size. Documents shared by others open translated into your language — see [Document Translation](https://intermind.com/document-translation) — and each document is summarized automatically, with the key points readable in your language — see [Document Summaries](https://intermind.com/document-summaries). ## Storage Limits File uploads count toward your team's storage quota: | Plan | Storage Limit | | ---------- | ------------- | | Basic | 1 GB | | Pro | 30 GB | | Business | 1 TB | | Enterprise | 5 TB | ### Checking Storage Usage View your team's storage usage: 1. Open the **Users** page from the sidebar (owners) or the **Billing** page 2. The **Storage Usage** banner / card shows used vs. available space 3. A progress bar indicates how close you are to the limit ### When Storage is Full If your team reaches the storage limit: - You cannot upload new files - Existing files remain accessible - Upgrade your plan or delete old files to free up space ## File Management ### Downloading Files - Click on any shared file to download it - Images can be saved by right-clicking and choosing "Save Image" ### File Visibility - Files shared in a meeting chat are visible to all meeting participants - Files shared in a channel are visible to all channel members - Files in channels persist in chat history indefinitely; files in ad-hoc meeting chats are deleted when the meeting chat is purged after the call ## Recording Files Screen recordings made during meetings are also stored as files: - Recordings are saved to the team's storage - They appear in the chat as well as in the team's file browser - See [Screen Sharing & Recording](https://intermind.com/../meetings/screen-sharing) for details ## Tips - Compress large images before sharing to save storage space - Use the team's file browser (see [Team Storage](https://intermind.com/../users/storage)) to manage all shared files - Storage usage is shared across the entire team — coordinate with team members if space is limited ## Related - [Document Summaries](https://intermind.com/document-summaries) — Every shared document, summarized automatically in your language - [Document Translation](https://intermind.com/document-translation) — Read shared PDF and Office files in your language - [Team Storage](https://intermind.com/../users/storage) — Detailed storage management and file browsing - [Screen Sharing & Recording](https://intermind.com/../meetings/screen-sharing) — Recordings also count toward storage - [Billing & Plans](https://intermind.com/../billing) — Upgrade your plan for more storage # Document Translation Documents shared in chat can be read in your own language. When you open a file someone else uploaded, InterMIND translates it into your language first — there is no button to press. Formats, plans, and a demo are on the [Document Translation feature page](https://intermind.com/features/document-translation). ## How It Works 1. A participant shares a document in chat 2. You click it to open 3. If it's in another language, the tile shows **Translating document…** 4. The translated copy opens, marked **Translated** ![A PDF card in chat marked Translated, with the AI summary and Preview links below](https://intermind.com/img/docs/chat/document-translation.png) The sender always sees the original, and if the document is already in your language nothing is translated. Once translated, the copy is cached — reopening it is instant, and so is opening it for teammates with the same language. ## Supported Formats PDF, DOCX, DOC, PPTX, and XLSX, translated into 30 languages via DeepL. Other file types open as-is. ## Plans & Limits Document translation is a **paid feature**, metered per distinct document over a rolling 30-day window: | Plan | Documents / 30 days | | -------------- | ------------------- | | 🆓 Basic | Not available | | ⭐ Pro | 10 | | 🏢 Business | 30 | | 🏛️ Enterprise | 100 | - Usage counts against the **meeting host's** plan, whoever opens the document - Re-translating the same file into additional languages is free — the meter counts distinct files - Track usage on the **Billing** page under the **Document Translation** meter — see [Usage & Invoices](https://intermind.com/../billing/usage) When the quota is reached — or on the Basic plan — the original file still opens, just untranslated. ## Related - [File Sharing](https://intermind.com/files) — Upload and link documents in chat - [Document Summaries](https://intermind.com/document-summaries) — The key points of every shared document, in your language - [Sharing Documents & Notes In-Call](https://intermind.com/../meetings/shared-documents) — Open a document for the whole conference - [Usage & Invoices](https://intermind.com/../billing/usage) — All usage meters in one place # Document Summaries Every document shared in an InterMIND channel or meeting chat is summarized automatically — there is no button to press. A few moments after the file lands, its card offers an **AI summary**: the key points as short bullets, each linked back to the exact paragraph it came from, readable in your own language. The [feature page](https://intermind.com/features/document-summaries) shows what that looks like. Summaries are included on **every plan**, at no cost and with no quota. ## Reading a Summary Each file card in chat carries a status strip with two labeled links: - **AI summary** — opens the summary - **Preview** — opens the document itself ![A document card in chat with the AI summary and Preview links in its status strip](https://intermind.com/img/docs/chat/document-summaries.png) Clicking the card body also opens the document, like in any messenger. While the summary is being prepared, the strip shows **Preparing summary…** and flips on its own when it's ready — no reload needed. ### The Summary View The summary opens in a resizable window with two tabs: - **Summary** — the key points as bullets. Each bullet ends with a **¶ link**; clicking it jumps to the exact source paragraph, so every claim can be checked against the document. - **Extracted text** — the document's full text as it was read from the file. The **Open document** button in the header opens the original file in the built-in preview — with [document translation](https://intermind.com/document-translation) applied if the file is in another language. ## Your Language The summary is written in the document's own language first, then translated for each reader: - You see the summary in **your language** — the same language your meeting translation uses - If your translation isn't ready yet, the original appears first and is replaced automatically a few seconds later - The **extracted text is never translated** — it stays the document's source of truth, so the ¶ links always land on the author's exact words ## Supported Files Summaries cover the document formats shared in chat: | Family | Extensions | | --------------------- | -------------------------- | | Word / text documents | DOC, DOCX, DOCM, ODT, RTF | | PDF | PDF (with a text layer) | | Presentations | PPT, PPTX, PPSX, PPTM, ODP | | Spreadsheets | XLS, XLSX, XLSM, ODS, CSV | | Plain text | TXT, MD, Markdown | | E-books | EPUB | Very large documents are summarized from the beginning of the text; the **Extracted text** tab notes when the text was truncated. ## Card Statuses When a summary can't be produced, the card says why instead of showing a broken link: | Status | Meaning | | -------------------------------------------------- | -------------------------------------------------------------------------------------------------- | | Preparing summary… | Extraction succeeded; the summary is being written | | Scanned document | The pages are images — there is no text layer to read (OCR is not performed yet) | | This file has no readable text | The file opened, but contained no extractable text | | Password-protected file | Encrypted documents are not opened | | File is too large for text extraction | Over the extraction size ceiling | | Text extraction isn't supported for this file type | Format outside the table above | | No summarizable content found | Text was extracted but held no summarizable substance — the **Extracted text** link still opens it | | Sent from mobile / Sent via Telegram | Files arriving from the mobile app or Telegram aren't extracted yet | | Linked document | Google Drive / OneDrive links share a pointer, not the file — content stays with its provider | | Summary generation failed | The summary was retried and gave up; the extracted text remains available | Files shared before the feature launched are not summarized retroactively. ## Privacy Document content shared into a meeting is treated with the same care as the meeting transcript: - Text extraction runs **in your browser** — the file's text is read on your machine, not mailed to a third party for parsing - The summary is written by **the AI gateway your organization selects** — Azure OpenAI in the EU Data Zone by default, Vertex AI EU or Amazon Bedrock Frankfurt by choice, or your own endpoint — with zero data retention and no training on your content; the gateways and regions are listed under [AI features](https://intermind.com/../settings/ai-features) - Extracted text and summaries are stored on InterMIND servers only, never in public file storage, and are readable **only by members** of the meeting or channel ## Summaries and the Meeting Recap Document summaries feed the [meeting recap](https://intermind.com/../meetings/recap): when a recap is written, the documents shared during the session contribute their summaries alongside what was said. A session with no speech but with shared documents still produces a recap. ## Related - [File Sharing](https://intermind.com/files) — Upload and share files in chat - [Document Translation](https://intermind.com/document-translation) — Read shared files in your language - [Meeting Recap](https://intermind.com/../meetings/recap) — Where document summaries surface after the call # Channels & Members Channels are persistent team chats on the **Channels** page. This page covers managing them: members, invite links, renaming, archiving, and deletion. ## Managing members Open the member drawer either way: - Click the **participant avatars** in the chat header - Right-click the channel in the sidebar → **Manage group** (host only) ### Adding people The search field at the top of the drawer looks across your team, contacts, people you've met in meetings, and your organization directory. Clicking a person adds them immediately — no confirm step. People already in the channel are shown with an **In channel** badge; already-invited ones with **Pending**. Adding someone external creates a **pending invite** (they get an email) rather than an instant member row. People you've met in a finished meeting are badged **Met before**; others outside your team are badged **External**. ### Removing people Tap a member row to remove that person. The **Host** row is fixed — the host can't be removed, but the role can be transferred (below). ### Transferring the host The channel's host — badged **Host** in the member list — is the person the channel bills to, and the one who manages members and settings. The host, or an admin of the host's team, can hand the role to another member: 1. Click the **star icon** next to the member's row 2. Confirm **Make host** The target must already be a member of the channel and a licensed member of the same team — changing the host is available on paid plans. The new host takes over managing members and settings; the previous host becomes a regular participant. Everyone in the channel sees "*name* is now the host", and the change is recorded in the [team audit log](https://intermind.com/../users/audit-log). Host transfer isn't available for the team's shared default channel or for Inbox conversations. The same action is available mid-call from the participants menu — see [Meeting Controls](https://intermind.com/../meetings/controls). ### Pending invites Hosts see an **Invited — pending** section listing outstanding invites, each with a **Revoke invite** button. Registered users are added the moment they're invited; everyone else joins on sign-up via the emailed link. ## Invite link & email invites The **Invite members** button (person-plus icon) in the drawer opens a dialog with both invite methods: - **Invitation Link** — anyone with the link can join the channel. **Copy** it, or **Regenerate** to rotate the token — the old link stops working immediately. Useful if a link leaked. - **Email invites** — paste addresses separated by commas, spaces, or new lines and click **Send Email Invites**. Each recipient gets a link to join this channel. Addresses already in the channel or already invited are flagged before anything is sent. ## Renaming a channel Right-click the channel in the sidebar → **Rename** (host only), or edit the title inline in the chat header. Leave the name empty to fall back to the default title built from participant names. Channels created from a calendar-synced meeting take their title from the calendar event. ## Archiving Right-click a channel → **Archive**. Archived chats: - move out of the main list into the **archive view** — the archive-box button in the sidebar header (it turns red when archived chats hold unread messages) - are muted: their unread counts stay per-chat but leave the global badge - lose their pinned position The archive view has its own search box. To bring a chat back, open its menu in the archive and click **Restore**. ## Deleting a channel Deletion is available from the **archive view** only: archive the channel first, then open its menu → **Delete**. A confirmation dialog warns that all messages, files, and channel history are permanently deleted — this cannot be undone. ## Related - [Chat overview](https://intermind.com/docs/chat) — channels, Inbox, and chat types - [Inviting Members](https://intermind.com/../users/inviting) — team-level invitations - [Telegram](https://intermind.com/../integrations/telegram) — mirror a Telegram group into a channel # Voice Notes Some things are faster to say than to type — a thought after a call, a decision taken in the hallway, a status for the team while you walk. A voice note records it into the channel, and InterMIND turns it into a text message on its own — one everybody reads in their own language. Voice notes are included on **every plan**. ## Recording a Voice Note In the web app and in the InterMIND mobile apps, the composer of every channel and direct chat shows a **microphone** button in place of **send** while the message field is empty. The chat of a live meeting has no microphone button: there you are already speaking to the room, and the room already hears you in its languages. 1. Tap the microphone. The browser or the phone asks for microphone access the first time. 2. Speak — while you record, a red dot pulses at the message field, the field says **Recording…** and the button turns into **send**. The field stays open: anything you type meanwhile goes out with the note. 3. Tap **send** to stop the recording and send the note. The note goes first, your text follows it as a message. A voice note can be up to ten minutes long. At the limit the recording stops on its own and waits in the composer for your next **send**. ## What Everyone Gets A voice note is an ordinary chat message. Its text is what you said — transcribed within seconds — and, like every message in InterMIND, each teammate reads it in their own language. A **play** button on the message plays the recording itself, with elapsed and total time next to it. Everything a message can do, a voice note can do: search finds it, it can be quoted, forwarded and copied, and **Show original** in the message menu shows the transcript as it was spoken. While the transcript is on its way the message shows **Transcribing…**; if nothing was said, or speech recognition is unavailable, it says so in the same place and the recording stays playable. Voice notes work in any channel, including the channel you keep for yourself — a quick way to dictate notes for later. ## Where the Audio Goes Speech recognition for voice notes runs on Azure AI Speech in InterMIND's own Azure tenant — the speech service of the default AI gateway, the same EU gateway that writes InterMIND's meeting summaries. Organizations whose AI gateway is Vertex AI or Amazon Bedrock get the recording without a transcript for now. The recogniser is told the speaker's own language, so a short note is never mistaken for another language. The transcript is translated by InterMIND's own engine like every chat message. The recording is stored with the channel's other files and is deleted with the message. Every hop is listed on the [trust page](https://intermind.com/trust). # Chat InterMIND includes a built-in chat system designed for multilingual teams. Messages are synchronized in real-time and can be automatically translated into each participant's preferred language — the [Multilingual Chat feature page](https://intermind.com/features/multilingual-chat) shows what that looks like for a reader. ## How Chat Works - Messages appear instantly for all participants - All messages are stored on the server — if you join a meeting late, you see the full chat history - Chat is available both during meetings (sidebar panel) and as standalone **Channels** on the **Channels** page ## Key Features | Feature | Description | | -------------------- | ------------------------------------------------------------------------------------------------------------------- | | Real-time messaging | Messages appear instantly for all participants | | Auto-translation | Messages automatically translated to your language | | File sharing | Share images and documents in chat | | Document summaries | Every shared document summarized automatically, readable in your language | | Replies & forwarding | Quote-reply to any message; forward messages to another channel or your Inbox | | Reactions | React to messages with emoji | | Pin messages | Pin important messages for easy reference | | Rich-text notes | Add formatted notes with headings, lists, and code | | Edit & delete | Modify or remove your messages — with a viewable edit history; select several messages to delete or forward at once | | Member management | Add and remove channel members, invite by link or email | | Archive | Move finished chats to the archive view; restore them anytime | | Telegram & Inbox | Forward Telegram messages into your personal Inbox and mirror groups into channels | | History | Full message history preserved | ## Chat Types ### Meeting Chat (ad-hoc) Every ad-hoc meeting has a chat panel in the sidebar: - Messages sent during the meeting are linked to that meeting - For ad-hoc meetings, the chat history is deleted after the call (except any agenda note or file the host attached at meeting creation, which is preserved) ### Channels Channels are persistent team chats that live on the **Channels** page, independent of any single meeting: - Use them for ongoing team communication - Start a meeting directly from a channel - All members see the full message history, which is kept indefinitely - Members, invite links, renaming, and archiving are covered in [Channels & Members](https://intermind.com/chat/channels) ### Inbox Your personal **Inbox** appears in the channel list the first time something arrives in it. Ways in: - **Telegram** — everything you forward to the InterMIND bot lands there. See [Telegram](https://intermind.com/integrations/telegram). - **Share from any app** — on iOS or Android (share sheet) or macOS (system **Share** menu → **InterMIND**, with the desktop app installed) share text, a link or files; InterMIND asks whether it goes to your Inbox or to a channel. Messages in the Inbox can be routed on to your channels. ## Getting Started - [Sending Messages](https://intermind.com/chat/messages) — How to send, edit, reply, forward, and manage messages - [Sharing Files](https://intermind.com/chat/files) — Upload and share files in chat - [Chat Translation](https://intermind.com/chat/translation) — Automatic message translation - [Document Translation](https://intermind.com/chat/document-translation) — Read shared files in your language - [Document Summaries](https://intermind.com/chat/document-summaries) — The key points of every shared document, in your language - [Channels & Members](https://intermind.com/chat/channels) — Members, invite links, renaming, archiving ## Related - [Meeting Controls](https://intermind.com/meetings/controls) — Access chat during meetings - [Meeting Defaults](https://intermind.com/settings/meeting-defaults) — Configure chat display settings # Profile Settings Your profile settings control how you appear to other participants and which language is used for translation. ![Settings page with the User section at the top](https://intermind.com/img/docs/settings/settings-page.png) ## Accessing Profile Settings 1. Click **Settings** in the sidebar 2. The **User** section is at the top of the page ## Avatar ### Uploading an Avatar 1. Click the **Upload** button in the User section 2. Select an image from your computer 3. The image is automatically cropped to a square and resized to 256×256 pixels **Supported formats:** JPEG, PNG, GIF, WebP :br**Maximum file size:** 10 MB Your avatar is automatically optimized (compressed to JPEG quality 0.85) for fast loading. ### Default Avatar If you don't upload a photo, a default avatar is generated from your initials with a colored background. This appears everywhere your profile picture is shown. ### Removing Your Avatar Click **Remove** next to your avatar to revert to the auto-generated initials avatar. This button only appears if you've uploaded a custom photo. ## Display Name Your display name is shown to other participants in meetings, chat, and team views. 1. Type your name in the **Name** field 2. Your name is saved automatically (with a brief delay) 3. If you leave the field empty, your email address is used as a fallback ## Email Your email address is displayed as read-only. It's set during account creation and cannot be changed from the settings page. ## The Language You Hear and Read In The language you hear and read in determines what you hear when translation is active in a meeting and what language incoming chat messages are translated to. What you say is recognized automatically — there is no speaking language to set. By default, the language you hear and read in **follows your interface language**. It is not on the Settings page — set it from the **sidebar account menu**: open the menu on your account entry at the bottom of the sidebar and pick **Translate for me into**; the submenu lists all 23 languages. Choosing a language different from your interface language sets an override (your account entry shows the language you hear and read in); choosing the same one clears it. Changing your **interface language** later does not silently change the language you hear and read in. You can also change it on the pre-join screen before joining and in the call: **More** → **Translate for me into**. It's the same account-wide setting everywhere. ### Supported Languages InterMIND supports 23 languages for real-time translation (voice, chat, and shared notes). On-demand file translation in chat — a paid feature, available on Pro and above — covers a wider 30. Full breakdown: [How many languages do we support — six numbers, not one](https://intermind.com/blog/how-many-languages-do-you-support). | Language | Native Name | | ----------------------- | ----------- | | English | English | | Russian | Русский | | Spanish (Latin America) | Español | | French | Français | | German | Deutsch | | Italian | Italiano | | Portuguese (Brazilian) | Português | | Polish | Polski | | Dutch | Nederlands | | Czech | Čeština | | Hungarian | Magyar | | Danish | Dansk | | Finnish | Suomi | | Icelandic | Íslenska | | Norwegian | Norsk | | Romanian | Română | | Swedish | Svenska | | Ukrainian | Українська | | Japanese | 日本語 | | Korean | 한국어 | | Turkish | Türkçe | | Chinese (Simplified) | 中文 | | Hindi | हिन्दी | ### Default Language If you haven't set a language yet, InterMIND uses your browser's language setting. If your browser language isn't in the supported list, it defaults to English. ## Your Voice in Translation When your speech is translated for other participants, it is spoken by a synthesized voice. Record a short sample and that voice is built from yours, so people hear your words in their language in a voice that sounds like you. ### Recording a Sample 1. In **Your voice in translation**, click **Record my voice**. After a moment the card says **Speak now**. 2. Say the numbers from one to ten in any order, in the language the card shows them in, and numbers heard in another language do not count. Each number lights up as the speech engine hears it. 3. When all ten are lit, the take is checked and saved by itself: **Done. Your voice is saved.** Nothing else to click. Take your time — there is no countdown; the card keeps the stretch of your take that holds the numbers, up to the ten seconds the voice engine reads. If the engine did not catch every number within 10 seconds (the sample's upper limit), or the recording is too quiet, distorted, mostly silence, or too noisy, the card says why and you simply record again. A quiet room and a headset give the best result. From the next meeting you join, your translated speech is voiced with your sample. There is no separate switch: a saved sample is on, no sample means the standard voice. ### Removing the Sample Click **Remove** on the card. Your translated speech returns to the standard voice immediately. The sample is stored with your account only for this purpose, is sent to the translation engine each time you join a meeting, and is deleted together with your account. Guests cannot record a sample — sign in to use your own voice. ## Syncing Across Devices Your profile settings (name, avatar, language) are stored in the cloud and sync across all devices where you're signed in. Changes take effect immediately on all sessions. # Appearance InterMIND lets you toggle between light and dark mode from the sidebar, and customize the primary and secondary accent colors used in each mode from the Settings page. ## Color Mode (Light / Dark) Color mode is toggled from the sidebar, not the Settings page: 1. Look for the **Toggle theme** button in the app sidebar (or the sun/moon icon in the header on landing pages) 2. Click to cycle between the available modes The mode follows your system preference by default. Switching dark/light during a meeting is handled separately — the meeting room is always rendered in dark, and sidebars (chat, participants) follow your preference inside it. ## Theme Colors You can customize the primary and secondary accent colors for both light and dark themes independently. This is done from the **Application preferences** card on the **Settings** page. ![Application preferences card — theme colors for light and dark mode](https://intermind.com/img/docs/settings/appearance.png) ### What Can Be Customized | Setting | Affects | | ----------------------- | --------------------------------------------- | | Light theme — Primary | Buttons, links, active elements in light mode | | Light theme — Secondary | Accents, badges, secondary UI in light mode | | Dark theme — Primary | Buttons, links, active elements in dark mode | | Dark theme — Secondary | Accents, badges, secondary UI in dark mode | ### Changing Theme Colors 1. Go to **Settings** → **Application preferences** 2. Each theme (Light / Dark) shows a **Primary** and **Secondary** swatch 3. Click a swatch to open the color picker 4. Pick a color — the change applies immediately ### Resetting Colors Click the **Reset** (circular arrow) button at the top of the Application preferences card to restore all four color settings to their defaults. ### Syncing Colors Across Devices Theme colors are stored on your account and follow you across devices when you sign in. # Meeting Defaults InterMIND remembers your in-meeting preferences between sessions. Anything tied to hardware or to a window — the chosen camera, microphone and speaker, their on/off state, panel widths — is **stored locally in your browser**, so it's per-browser/per-device. What describes how you want to take part follows your **account** on every device you sign in on (web, desktop, mobile): your translation **language**, the translation and subtitles on/off switches, your per-meeting display names, and the pinned and hidden rows of the Meetings list. ## Pre-Join Setup There is no toggle for the Pre-Join Setup screen. InterMIND shows it automatically the **first time** you join on a device, and again whenever your camera / microphone / speaker configuration has changed since your last join. Once you've joined with a given device setup, later joins skip straight into the meeting until that setup changes. ## Device Defaults The selected camera, microphone, and speaker are remembered the next time you join a meeting: 1. Open the **Pre-Join Setup** screen before entering, or open the cockpit's device dropdowns during a meeting 2. Pick a camera / microphone / speaker 3. Your last selection is reused on the next join Camera and microphone **on/off state** at join time follows whatever you last set in the Pre-Join Setup or cockpit. ## Translation & Subtitles The on/off state of translation and subtitles is remembered between meetings and synced to your account — switched off on your phone, they stay off on your desktop too: - Open the **More** menu in the cockpit and click **Enable translation** (Alt+T) to toggle real-time translation - Open the **More** menu and click **Show subtitles** to show/hide live subtitles Transcription is **automatic** — there is no toggle. Speech is captured throughout the meeting and the transcript is reachable from the recap card afterward (see [Transcription](https://intermind.com/../translation/transcription)). Your translation **language** is set from the account menu at the bottom of the sidebar (see [Profile Settings](https://intermind.com/profile)). ## Sidebar Widths The widths of in-meeting sidebars (chat panel, participants panel) are remembered between sessions. Resize a panel by dragging its edge, or cycle through preset widths with **Alt + R** while the panel is open. ## Resetting Defaults There's no global "reset" button. To reset most defaults, clear your browser's local storage for the InterMIND site — all `inter-mind:`-prefixed entries belong to these device defaults. # Keyboard Shortcuts InterMIND uses the physical **Alt** key (called **Option** on macOS) for most in-meeting shortcuts, so they work the same on every keyboard layout. ![Keyboard shortcuts and controls — the in-meeting reference](https://intermind.com/img/docs/settings/keyboard-shortcuts.png) ## Global These work anywhere in the app. | Shortcut | Action | | ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- | | **Cmd/Ctrl + /** | Open the Help panel: how InterMIND works and, signed in on a paid plan, your meetings, chats and files | | **Esc** | Close the topmost panel — the chat sidebar first, then the participants sidebar. Skipped while a dialog is open, so the dialog handles its own Esc. | ## In a Meeting Active only inside a meeting room. Disabled while a modal dialog is open. | Shortcut | Action | | ------------------ | --------------------------------------- | | **Alt/Option + M** | Toggle your microphone | | **Alt/Option + C** | Toggle your camera | | **Alt/Option + T** | Toggle real-time translation | | **Alt/Option + H** | Toggle the chat sidebar | | **Alt/Option + P** | Toggle the participants sidebar | | **Alt/Option + L** | Reset the stage layout to defaults | | **Alt/Option + R** | Cycle chat / participants sidebar width | ## In Chat When the chat surface is focused (in-meeting sidebar or a standalone channel on the Channels page). | Shortcut | Action | | ---------------------------------- | ---------------------------------- | | **Cmd/Ctrl + F** | Open chat search | | **Enter** (in message box) | Send the message | | **Shift + Enter** (in message box) | Insert a newline | | **Alt/Option + ↑** | Recall your previous message | | **Alt/Option + ↓** | Recall the next message in history | ### Scrolling the History | Shortcut | Action | | ------------------------- | ------------------------------------------------------------------------------------------------------- | | **PageUp** / **PageDown** | Page the message history — works even while you're typing | | **↑** / **↓** | Scroll the history a line at a time (only when the message box is empty; otherwise they move the caret) | | **Home** / **End** | Jump to the oldest / newest message (same rule as ↑ / ↓) | ### Inside Chat Search | Shortcut | Action | | ----------------------- | -------------------------- | | **Enter** | Jump to the next match | | **Shift + Enter** | Jump to the previous match | | **↑** / **↓** | Navigate search history | | **Esc** | Close search | ## Notes - **Alt vs Option** — same physical key. On macOS it's labelled **Option**; on Windows / Linux it's **Alt**. Shortcuts use the key's physical position, so they work regardless of language layout. - **Modals take priority** — when a dialog is open (sign-in, settings, file picker), meeting shortcuts are suspended so you can type freely. - **No conflict with the browser** — InterMIND avoids Cmd/Ctrl combos that overlap with browser shortcuts (Ctrl+T, Ctrl+W, etc.), except for Cmd/Ctrl+F in chat (intentional) and Cmd/Ctrl+/ for help. ## Related - [Meeting Controls](https://intermind.com/../meetings/controls) — Visual equivalents in the control bar - [Messages](https://intermind.com/../chat/messages) — Chat message basics # Calendar The **Calendar Integration** card on the **Integrations** page keeps meetings created in InterMIND synchronized with your calendar. What two-way sync gives you day to day is summarized on the [Calendar Sync feature page](https://intermind.com/features/calendar). ## Connecting a Calendar ![Calendar Integration card on the Integrations page](https://intermind.com/img/docs/settings/calendar.png) 1. Open the **Integrations** page from the sidebar 2. In the **Calendar Integration** card, click **Connect** next to **Google Calendar** or **Microsoft Outlook Calendar** 3. Sign in with your account in the OAuth popup 4. The card shows the connected account's email Click **Disconnect** next to a connected calendar to remove the connection. ## Default Calendar With both calendars connected, click **Make default** to pick which one is used for scheduled meetings. The current default carries a **Default for scheduled meetings** badge. ## How It Works - Every meeting you host has a calendar button on its row in the Meetings list. Clicking it opens your default calendar with the event pre-filled: title, join link, and the meeting recap link. - Scheduled meetings pick up their dates and changes from your calendar. If the calendar is disconnected, meeting rows keep showing the date from the last sync until you reconnect. # Backup & Restore The **Backup & Restore** card on the **Settings** page lets you save all your chats as a ZIP and bring them back later. The card is shown when your plan includes data export — currently every plan does, including the free Basic tier. ![Backup & Restore card on the Settings page](https://intermind.com/img/docs/settings/data-export.png) ## What's Included | Data Type | Description | | -------------- | ------------------------------------ | | Chat messages | All text messages from your channels | | Transcriptions | Meeting transcription records | | Files | Uploaded files and documents | | Images | Shared images | | Recordings | Conference screen recordings | ## Creating a Backup 1. Open the **Settings** page from the sidebar 2. In the **Backup & Restore** card, click **Create Backup** 3. A real-time progress bar tracks each step: scanning meetings → downloading files → compressing 4. When complete, click **Download** to save the ZIP file ## Restoring from a Backup Restore selected chats from a previously created backup. | Data Type | Description | | ------------- | ------------------------------------------------------- | | Chat messages | All message types (chat, transcription, image, file) | | Files | Uploaded back to your team's Storage | | Recordings | Conference recordings uploaded to Storage | | Metadata | Pins, reactions, translations, file names, sizes, types | 1. Open the **Settings** page from the sidebar 2. In the **Backup & Restore** card, click **Restore from Backup** 3. Select a ZIP archive 4. Pick which chats to restore (others stay untouched) 5. Confirm — a full-screen overlay shows restore progress 6. After restore, a summary shows the results along with any errors or warnings ::callout{type="warning"} Selected chats are replaced with the backup snapshot — any newer messages, files, or recordings added after the backup was made will be lost. Chats you don't select stay as they are. :: ## Bringing Channels Over from Slack The same **Restore from Backup** button accepts a standard Slack workspace export — the ZIP a Slack owner or admin downloads from **Settings & administration → Workspace settings → Import/Export Data**. InterMIND recognizes it by its contents; there is nothing to convert. | Slack data | What happens in InterMIND | | --------------------------- | ---------------------------------------------------------------------------------------------- | | Public and private channels | One InterMIND channel each, named `#channel`, with the channel purpose as its note | | Messages and threads | Imported in order with their original timestamps; each member reads them in their own language | | Authors | Matched to your team by e-mail; everyone else keeps their Slack name on the message | | Reactions and pins | Kept | | Shared files | Kept as links (a Slack export carries no file contents) | | Direct messages | Not imported | 1. Export the workspace in Slack (public channels on every plan; private channels need a paid plan and Slack's approval) 2. In InterMIND, open **Settings → Backup & Restore → Restore from Backup** and select the export ZIP 3. Pick the channels to bring over and confirm 4. Invite your teammates to the imported channels — members are not added automatically Uploading the same export again updates the imported channels instead of duplicating them. # AI Features The **AI features** card on the **Integrations** page is where an organization owner or admin decides two things: whether the organization's AI features run at all, and **on which cloud gateway** they run. The choice applies to every AI feature at once — meeting recaps, document summaries, the writing assistant, Ask AI and Mia in meetings. ![AI features card on the Integrations page](https://intermind.com/img/docs/settings/ai-features.png) ## Switching AI features off Turn the **AI features** switch off to keep your organization's content away from any language model. Meetings still get transcribed and translated, and chats and documents keep working — only the AI-generated parts stop: recaps arrive without a summary, documents are shared without an AI summary, the writing assistant and Ask AI are hidden, and Mia does not listen. Switch it back on at any time. ## Choosing the gateway Every AI feature runs on a **language-model gateway of a hyperscaler, in InterMIND's own tenant**. Pick the one your organization already uses for its own AI, so no new AI subprocessor enters your compliance perimeter: | Gateway | Where it runs | Notes | | ----------------------------------- | -------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Azure OpenAI** (Microsoft) | EU Data Zone | The default for every organization | | **Google Vertex AI** (Google Cloud) | EU multi-region endpoint | Available on request from the same card | | **Amazon Bedrock** (AWS) | The AWS region you choose, in your own AWS account | Enter the region, the model or inference profile and an IAM access key with `bedrock:InvokeModel` and `bedrock:InvokeModelWithResponseStream` rights; models, quotas and billing stay in your account, the secret key is stored encrypted and never shown again | All gateways are configured with zero data retention and no training on your content. What an AI call sends is only what the feature needs: the meeting transcript and chat window at meeting end for a recap, a shared document for its summary, the editor text for the writing assistant, the question for Ask AI. The list of vendors and regions is on the [subprocessors page](https://intermind.com/legal/subprocessors) and the [Security](https://intermind.com/docs/security) page. ## Your own endpoint Organizations that run their own model — vLLM in their data centre, or a model deployment in their own cloud tenant — choose **Your own endpoint** and enter the server URL, the model name and, if the server needs one, an API key. From then on every AI feature of the organization calls that server and nothing else. The key is stored encrypted and is never shown again; leave the field empty on later edits to keep it. Mia answers in text on your own endpoint, because the voice comes from the gateway's vendor. ## Help from any screen The panel on the right is Help: open it with **Cmd/Ctrl + /** or **Help** in the sidebar, on any page and in a meeting. It knows the screen you are on, so *«what does this button do?»* is answered for that screen, and it explains how InterMIND works. Signed in, on any plan, it also answers from your meetings, chats and files and can prepare a meeting link or a message for you to confirm; that conversation is saved for you and is there again on any page and after a reload. Every member has their own daily budget for these answers, set by their organization's plan: about ten questions a day on Basic, more on Pro and Business, no daily limit on Enterprise. It renews at midnight UTC; when it is spent the panel says so and names the time, and the rest of the panel — the saved conversation, the documentation — stays. Without an account, or when the organization has switched AI features off, the panel answers from the documentation. The panel follows what is open. With a channel open it reads that channel's chat, files and meeting recaps; in a meeting it also reads the live transcript. The header of the panel names the channel or meeting it is answering about — or *Your account* when nothing is open — and every answer keeps the mark of where it was asked. There is one thread: a question asked in a channel is there again on any other screen. ## Mia searches the web In the Help panel, Mia can look outside your organization when a question needs it: news, prices, a company, a law, the documentation of another product. She searches the web, reads the public pages worth reading, and gives the address of every fact she takes from them. Aloud in a meeting she does not search. What leaves InterMIND is **the search phrase Mia words herself** — never your documents, recaps or chats, and nothing that identifies you or your organization. The search runs on the Brave Search API (see [Subprocessors](https://intermind.com/legal/subprocessors)). Pages are read as any visitor would read them: public pages only, within the site's robots.txt, no sign-in, no cookies, up to one megabyte of HTML, plain text or PDF; scanned PDFs without a text layer and pages built entirely by scripts are not read. What a page says is treated as data — a page cannot give Mia instructions. An owner or admin turns this off under **Settings → AI features → Mia searches the web**. Off means the two tools do not exist for anyone in the organization: Mia answers from your organization's material and from what she knows, and says plainly when a question would need the web. ## Mia in meetings ::callout{type="warning"} **Preview.** Mia in meetings is being tested inside InterMIND; any account can switch her on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). What follows describes how she works in the preview; it is not part of any plan until the preview ends. :: :preview-mark{slug="mia-in-meetings"} Mia is the organization's AI participant in a meeting. She listens through the meeting transcript and answers when someone addresses her by name — *«Mia, what did we agree on last time?»* — or writes to her in the Help panel (**Cmd/Ctrl + /**) while the meeting is open. She answers from this meeting's transcript, chat and shared documents, and from the recaps of the previous sessions of the same room. The answer follows the question. Asked **aloud**, Mia answers **aloud to the whole room**, each participant in their own language: the answer is written natively in each language present and voiced on each participant's device, so Mia is not a participant of the call itself — she is not in the recording or the transcript. Start talking and Mia stops; tap the cross next to her name to cut an answer short. Her name is needed once, to start: after her answer the conversation stays open for about a minute, and every exchange keeps it open — you can go on without her name — *«and what about the deadline?»* — and she decides whether that was for her or a word to someone in the room. Silence closes it. Alone in the room with Mia you never need her name: everything you say is for her. Asked **in the Help panel**, she answers **there only**: every line you write there is for her — no name, no prefix — and nobody else in the meeting sees the exchange. The panel's header names the meeting, and the answer keeps that mark. Send her a document or a screenshot with the **+** button and she reads it. The thread is yours, not the meeting's: it is there again on any screen and after a reload. What Mia records on your word — a decision, an action item, a follow-up link — stays in the room chat for everyone and goes into the recap. Mia uses the host organization's gateway and its voice (Azure AI Speech or Google Cloud Text-to-Speech, EU regions), and runs while AI features are on for that organization. Aloud she answers **licensed participants of paid plans**: a participant on a paid plan has her voice in every meeting they join, whoever hosts it. Guests and participants on the free plan hear her answers to others, but aloud she does not answer them. The Help panel is every signed-in member's on any plan, in a meeting as on any other screen; a guest has no account and no panel thread. ### Mia speaks up on her own Her answers go to members of paid organizations, and her own notes, acting on the host's word and proposing the next step run when the host is one. Switching **AI features** off for the organization turns her off together with every other AI feature. Without being asked, Mia writes short notes into the meeting chat — text only, in every language present in the room, never over someone's voice: - **At the start** — what the previous session of this room decided and left open, and what is on today's agenda (the meeting's agenda note). - **Halfway and five minutes before the end** — what has been decided so far, what is still open, and which agenda items have not been touched. Without a scheduled end she assumes a 45-minute meeting. - **When someone takes something on** — *«I'll send the estimate by Friday»* becomes *«Noted: Anna — send the estimate by Friday»*, and the note goes into the recap. - **When a question hangs** — nobody answered and the answer is in a previous recap, a shared document or the chat: Mia posts it with its source. She never guesses and never searches the web. Tell her to stay out of the talk — *«Mia, be quiet»*, *«Mia, don't interrupt»* — and she does: from then on she speaks only when someone calls her by name, follows no conversation without her name, and writes no notes of her own. Anyone she answers can say it, not only the host. *«Mia, go on»* brings her back. Mia posts at most twenty notes an hour. ### Mia does things on the host's word The meeting host and moderators can tell Mia to act; other participants can ask her questions, but she will not act for them. She does it right away and confirms aloud and in the chat, where the host sees an **Undo** button for as long as the meeting lasts (*«Mia, undo that»* works too): - **Schedule the follow-up** — *«Mia, set up a follow-up next Thursday at three»*: a new meeting appears, the link lands in the chat and the event goes into the commander's connected Google or Microsoft calendar in their own time zone. Without a connected calendar the meeting and the link are created anyway. - **Record a decision, an action item or an open question** — *«Mia, note the decision: we go with vendor B»*: the note appears in the chat and is part of the recap. - **Send the recap to the CRM** — *«Mia, send the recap to Pipedrive»*: the recap of this meeting also goes to that address from the host's confirmed [recap address book](https://intermind.com/docs/meetings/recap#recap-copy-bcc-to-your-crm). ### Mia proposes the next step Before the meeting ends Mia weighs the agenda against what was said and proposes one concrete next step — a follow-up meeting for the items not covered, or an owner for a decision that was made but not stated. The host confirms with *«Mia, yes»* and she executes it exactly as above. # Settings The Settings page lets you personalize your InterMIND experience. Everything you connect — calendar, Slack, Telegram, API keys — and the team-level controls (SSO, domains, directory sync) live on the **Integrations** page. ![Settings page](https://intermind.com/img/docs/settings/settings-page.png) ## Settings Page The **Settings** page in the sidebar contains these cards, stacked top to bottom: | Card | What You Can Configure | | ----------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | | **User** | Avatar, display name, email (read-only) | | **Email preferences** | Toggle whether you receive product emails | | **Your voice in translation** | Record a short voice sample so your translated speech keeps your voice — see [Your Own Voice](https://intermind.com/docs/translation/own-voice) | | **Application preferences** | Theme color customization (primary and secondary, light and dark) | | **Active sessions** | See every device signed into your account, with its place and last-active time, and end any session (or all but this one) | | **Backup & Restore** | Export and import your data (shown when your plan includes data export) | | **Delete Account** | Permanently delete your account and associated data | Color **mode** (light / dark / system) is toggled via the theme button in the app sidebar, not from the Settings page. Your **interface language** and the language we **translate into for you** are also set from the sidebar: open the menu on your account entry at the bottom — both have their own submenus there. ::callout{type="info"} Directory Integration, Domain Management, and SSO are configured on the separate [Integrations](https://intermind.com/docs/integrations) page. :: ## Quick Links - [Profile Settings](https://intermind.com/settings/profile) — Avatar, display name, and where the language you hear and read in lives - [Appearance](https://intermind.com/settings/appearance) — Theme color customization - [Meeting Defaults](https://intermind.com/settings/meeting-defaults) — Device and feature defaults - [Keyboard Shortcuts](https://intermind.com/settings/keyboard-shortcuts) — Every shortcut, global and in-meeting - [Calendar](https://intermind.com/settings/calendar) — Connect Google or Outlook calendar and pick your default - [Backup & Restore](https://intermind.com/settings/data-export) — Export your chats as a ZIP and restore them later # Inviting Members InterMIND offers multiple ways to add people to your team — from individual email invitations to bulk imports and directory syncing (see also the [Contacts Sync feature page](https://intermind.com/features/contacts-sync)). ![Users page](https://intermind.com/img/docs/users/users-page.png) ## Invitation Methods The **Users** page header has one invite field plus an **Invite Users** dropdown for the rarer paths. ### 1. Invite People Directly The field in the page header — *Search contacts or type an email to invite…* — is the everyday path: 1. Start typing a name or an email address 2. Pick people from the suggestions (your contacts plus your organization's directory, if it's connected), or just type any address 3. Selected people become chips; the primary button turns into **Invite N** 4. Click it — directory people are added to the team directly, everyone else gets an email invite with a link to join Recipients you couldn't reach keep their chips, so the action can be retried as-is. ### 2. Invitation Link Generate a shareable link that anyone can use to join: 1. Click **Invite Users** → **Invitation Link** 2. Copy the generated link 3. Share it via any channel (Slack, email, etc.) The link can be regenerated if you want to invalidate the old one. ### 3. Bulk Import Import multiple users from a file: 1. Click **Invite Users** → **Bulk Import** 2. Upload a file (.txt, .csv, or .json) 3. Review the parsed list of emails 4. Send invitations **File format examples:** **TXT (one email per line):** ```text alice@company.com [design] bob@company.com [engineering] carol@company.com ``` **CSV:** ```csv email,tags alice@company.com,"design,ui" bob@company.com,"engineering" ``` **JSON:** ```json [ { "email": "alice@company.com", "tags": ["design"] }, { "email": "bob@company.com", "tags": ["engineering"] } ] ``` For Excel files (.xls/.xlsx), save them as CSV first. ### 4. From Directory (Google Workspace / Microsoft 365) Add members straight from your corporate directory, without typing email addresses: 1. Connect a directory on the **Integrations** page (owners and admins only). Until one is connected, the invite field on the **Users** page offers a shortcut to that page. 2. On the **Users** page, type a colleague's name or email into the invite field — the connected directory is searched live, alongside your contacts. 3. Each directory result shows the person's job title and department. People already on the team are not listed; pending invitations are marked "Invited". 4. Pick the people you want and click **Invite** — directory contacts with an existing InterMIND account become members right away; colleagues without one get an invite email and join once they accept it. ### 5. Domain Auto-Join Users from your verified domain can join automatically: 1. Verify your domain in **Integrations** → **Domain Management** 2. When someone creates an account with an email matching your domain (e.g., `@yourcompany.com`), they are automatically added as a **Member** 3. The team owner receives a notification Email aliases (e.g., `user+tag@domain.com`) are excluded from auto-join. ## Invitation Details ### Expiration - Email invitations expire after **7 days** - The expiration is shown in the Pending Invitations table - Expired invitations can be resent ### Accepting an Invitation When someone receives an invitation: 1. They click the link in the email or see a banner in the app 2. If not signed in, they're prompted to create an account or sign in 3. The invitation banner shows with an **Accept** button 4. Clicking **Accept** adds them to the team as a **Member** ### Pending Invitations Track all outstanding invitations on the Team Users page: | Column | Description | | ----------- | ------------------------------- | | **Email** | Invited email address | | **Status** | Pending, Accepted, or Expired | | **Expires** | When the invitation expires | | **Tags** | Tags assigned during invitation | ## Tips - Use tags when inviting to organize members from the start (e.g., `[engineering]`, `[marketing]`) - The invitation link is great for large groups — share it in a team channel - Connect your directory for the easiest experience with large organizations - Verify your domain to enable automatic onboarding for new employees # Managing Members The Users page gives you a comprehensive view of all team members with tools for organizing, searching, and managing roles. ![A member row's Actions menu — Make Admin, Make Member, Delete](https://intermind.com/img/docs/users/member-actions-menu.png) ## Member Table The team member table shows: | Column | Description | | ----------- | --------------------------------------------------- | | **Select** | Checkbox for bulk actions (not shown for the owner) | | **User** | Avatar, display name, and email address | | **Tags** | Editable tags for organizing members | | **Role** | Color-coded role badge (sortable) | | **Storage** | Amount of storage used by this member | | **Actions** | Dropdown menu with management options | ### User Details Each user row displays: - **Avatar** — Profile picture or auto-generated initials - **Display name** — Their chosen name - **Email** — With the domain highlighted in color if it matches a verified domain - **Tooltip** — Shows the team name and when they joined on hover - **Expand button** — Click to see the user's files (if any) ## Tags Tags help you organize team members by department, project, or any custom category. ### Adding Tags 1. Click in the **Tags** column for any member 2. Type a tag name 3. Press **Enter** to add it 4. Add as many tags as needed Tags are saved automatically. ### Assigning Tags During Invitations You can assign tags when inviting users: ```text alice@company.com [design, frontend] bob@company.com [engineering, backend] ``` ### Searching by Tags Use the search bar at the top of the member table: 1. Type in the **Search by tags** field 2. Members are filtered in real-time 3. The search uses AND logic — all words must match at least one tag 4. Partial matches work (e.g., "eng" matches "engineering") ## Sorting Click the **Role** column header to sort members by role: | Sort Order | Role | | ---------- | ------ | | 1st | Owner | | 2nd | Admin | | 3rd | Member | | 4th | Guest | The default sort is by role in ascending order. Click again to toggle sort direction. You can also sort by **Storage** to see who uses the most space. ## Individual Actions Click the **Actions** dropdown (⋮) on any member row: | Action | Description | | --------------- | -------------------------------------------------------------- | | **Make Admin** | Promote to admin role (shown when current role is member) | | **Make Member** | Set role to standard member (shown when current role is admin) | | **Delete** | Remove from the team | The owner cannot be deleted or have their role changed, and the owner row also has no action menu for self-actions. Who may change a role: - **Make Admin** — any admin (owner or admin-member) can promote a member - **Make Member** — demoting an existing admin is **owner-only** - Nobody can change **their own** role — ask the owner or another admin to do it ## Bulk Actions Select multiple members using the checkboxes, then use the bulk action buttons: 1. Check the boxes next to the members you want to manage 2. A toolbar appears with available actions: - **Make Admin (N)** / **Make Member (N)** — change role for all selected - **Delete (N)** — remove all selected from the team The owner row doesn't have a checkbox and is excluded from bulk actions. ### What Happens When a Member Is Removed When you delete a member from the team: - They're removed from the team's member list - They're removed from the team chat - The team ID is removed from their user profile - They can be re-invited later ## Verified Domains Email addresses matching your verified domains get special visual treatment: - The domain part is highlighted in the primary UI color - This makes it easy to identify which members are from your organization vs. external guests ## Tips - Use tags consistently across your team (e.g., always use "engineering" not "eng" or "developers") - Promote trusted team members to Admin for help with team management - Sort by Storage to identify which users consume the most space - Use the search function with tags to quickly find specific groups of people # Team Storage InterMIND provides a shared storage pool for your team. All uploaded files, images, and screen recordings count toward your team's storage limit. ![Users page, with the per-member Storage column](https://intermind.com/img/docs/users/users-page.png) ## Storage Limits by Plan | Plan | Storage Limit | | -------------- | ------------- | | 🆓 Basic | 1 GB | | ⭐ Pro | 30 GB | | 🏢 Business | 1 TB | | 🏛️ Enterprise | 5 TB | Storage is a **shared team pool** — the total is shared by all team members, regardless of the number of users. ## Storage Warnings The Users page shows warning banners based on storage usage: | Usage | Banner | Impact | | ---------- | -------------------------------------------------------- | --------------------------------------- | | **≥ 80%** | Info — "Storage Usage: X / Y (Z%)" | No restrictions, awareness alert | | **≥ 95%** | Warning — "Storage Almost Full" + "Upgrade Plan" button | Consider upgrading soon | | **≥ 100%** | Error — "Storage Limit Exceeded" + "Upgrade Plan" button | **File uploads and recordings blocked** | You also receive email notifications at the 80%, 95%, and 100% thresholds. ## How Storage Is Counted ### What Counts - **Uploaded files** — Documents, spreadsheets, etc. shared in chat - **Shared images** — Photos and screenshots shared in chat - **Screen recordings** — Recordings made during meetings - **Meeting files** — Any files associated with meetings ### Who Owns What - **Uploaded files** — Counted against the person who uploaded them - **Screen recordings** — Counted against the meeting host (creator) ### Per-User Storage View On the Users page, the **Storage** column shows how much space each member uses. This helps identify who's consuming the most storage. ## Browsing Files ### Expanding User Files To see a team member's files: 1. Go to the **Team Users** page 2. Find the member in the table 3. Click the **expand** button (▸) next to their name 4. Their files appear in a list below their row Each file shows: - **Icon** — Based on file type (video, image, document) - **Name** — File name (or ID for recordings and images) - **Date** — When the file was uploaded or created - **Size** — File size in MB ### Previewing Files Click on any file to open a preview modal: | File Type | Preview | | --------------------------------------------- | --------------------------------------- | | **Images** (JPEG, PNG, GIF, WebP) | Full-size image viewer | | **Videos / Recordings** | Video player with controls and autoplay | | **Audio** | Audio player with musical note icon | | **PDF** | Embedded PDF viewer | | **Office docs** (.doc, .xlsx, .ppt) | Google Docs Viewer | | **Text files** (.txt, .md, .json, .csv, etc.) | Embedded text viewer | | **Other formats** | "Open in new tab" link | ## Managing Storage ### When Storage Is Full If your team exceeds the storage limit: 1. **Uploads are blocked** — No new files can be uploaded 2. **Recording is blocked** — Screen recording during meetings is disabled 3. **Existing files remain accessible** — You can still view and download files ### Freeing Up Space To reclaim storage: - Delete old or unnecessary files - Download important recordings locally and remove them from InterMIND - Ask team members to review their uploaded files ### Upgrading Storage To get more storage: 1. Click the **Upgrade Plan** button in the storage warning banner 2. Or go to [Pricing](https://intermind.com/pricing) and select a higher plan 3. Storage increases immediately after upgrading ## Real-Time Updates Storage information updates in real-time: - New file uploads and deletions are reflected immediately - Storage usage bars and numbers refresh automatically - Warning banners appear and disappear based on current usage ## Tips - Monitor the storage banner on the Users page regularly - Sort the member table by **Storage** column to find the biggest consumers - Screen recordings tend to be the largest files — download them locally if you need to free space - Encourage team members to avoid uploading unnecessarily large files - Choose a yearly plan for both cost savings and sufficient storage for your needs # Team Audit Log InterMIND keeps an audit trail of security-relevant actions in your team. Every event is recorded with the actor, the timestamp, and the affected target, so an admin can answer "who did what, and when" — for internal review or a compliance questionnaire. **Availability:** Pro, Business, and Enterprise plans. Only team **owners and admins** can export the log. ![Export audit log (CSV) in the Invite Users dropdown](https://intermind.com/img/docs/users/audit-log-export.png) ## What is recorded | Event | Details captured | | --------------------- | ------------------------------------------------------------ | | Sign-in / sign-out | Method: SSO, Google/Microsoft account, email code, or mobile | | Member joined | Via invitation link or a named email invite | | Member removed | Including self-leave | | Role changed | Previous and new role, who changed it | | Invitation created | Invited email address | | Invitation revoked | Which invitation | | Team settings changed | Which fields were changed | | Plan changed | New plan and seat count (recorded by the billing system) | Audit writes never block the action they document — they are a record, not a gate. ## Exporting the log 1. Open the **Users** page (you need the owner or admin role). 2. Click the **Invite Users** dropdown → **Export audit log (CSV)**. The export covers the last 90 days by default and up to one year on request (`?days=366` on the export URL). Each CSV row carries the timestamp, action, actor id and email, target id, and a details column with the event metadata. A JSON format is available with `?format=json`. ## Audit log and SSO If your team uses [Single Sign-On](https://intermind.com/docs/integrations/sso-setup), every SSO sign-in lands in the audit log as `auth.login` with method `sso` — SSO itself is a Business/Enterprise feature, while the audit log is available from the Pro plan. # Users & Organization This section is for **owners and admins**. Regular members can skip it — your role gives you everything you need by default. Member management lives on the **Users** page (invitations, roles, storage, the [team audit log](https://intermind.com/docs/users/audit-log)), while your organization name is set on the **Billing** page. What members get out of a shared organization — chat, storage, integrations — is summarized on the [Team & Collaboration feature page](https://intermind.com/features/collaboration). ![Users page](https://intermind.com/img/docs/users/users-page.png) ## How It Works - Every user automatically belongs to an **organization** (named "{Your Name}'s Team" by default) - You can invite others to join via email, link, bulk import, or directory sync - Members share a storage pool and can participate in shared channels - Each user belongs to **at most one organization** at a time — accepting another invitation replaces the current one ## Roles | Role | Badge Color | Description | | ---------- | ----------- | ------------------------------------------ | | **Owner** | Primary | The organization creator; full control | | **Admin** | Info | Elevated privileges, assigned by the owner | | **Member** | Neutral | Standard member (default role) | | **Guest** | Warning | Joined via meeting link; limited access | ### Role Assignment - **Owner** — Automatically set for the person who created the organization; the role is immutable and cannot be reassigned - **Admin** — Promoted from the Users page by the owner **or by another admin**. Demoting an admin back to member is **owner-only**, and nobody can change their own role - **Member** — Default role when joining via invitation or domain auto-join - **Guest** — Automatically assigned when someone joins a meeting via link without being a member ## Organization Name You can customize your organization name on the **Billing** page (owners and admins only) — see [Usage & Invoices](https://intermind.com/billing/usage). The name shows up to teammates and on shared invitations. ## Quick Links - [Inviting Members](https://intermind.com/users/inviting) — All ways to add people - [Managing Members](https://intermind.com/users/managing) — Roles, tags, search, and bulk actions - [Storage](https://intermind.com/users/storage) — Shared storage pool and file management # SSO Setup This guide is for the IT admin connecting a company identity provider (IdP) to InterMIND. After setup, members sign in from the regular login page: **Sign in with SSO** → work email → your IdP → back in InterMIND. For the non-technical overview, see the [Single Sign-On feature page](https://intermind.com/features/sso). **Available on:** Business and Enterprise plans **Configured by:** team owner or admin **Protocol:** OpenID Connect (OIDC) only. SAML 2.0 is not offered — Okta, Microsoft Entra ID and Google Workspace all support OIDC. ![SSO card on the Integrations page](https://intermind.com/img/docs/integrations/sso-setup.png) ## Prerequisites 1. A **verified domain** — verify your email domain via DNS TXT record first (see [Domain Management](https://intermind.com/docs/integrations#domain-management)). SSO sign-in only accepts accounts whose email domain your team has verified; this is the tenant boundary. 2. An IdP that supports **OIDC with discovery** — it must serve `/.well-known/openid-configuration` under the Issuer URL. Okta, Microsoft Entra ID, and Google all do. ## What to register in your IdP Create an **OIDC Web Application** in your IdP with: | Setting | Value | | ----------------------- | ------------------------------------------------------------------------------------------------ | | Redirect URI (callback) | `https://intermind.com/api/auth/sso/callback` — also shown in the SSO card after you select OIDC | | Grant type | Authorization Code (PKCE S256 is used automatically) | | Scopes | `openid email profile` | The ID token your IdP issues must include the user's `email`, and the email's domain must be one of your verified domains — otherwise sign-in is refused. Then fill in the **SSO** card on the Integrations page: | Field | What to paste | | ------------------------- | --------------------------------------------------------------------------- | | Display Name | Any label your members will recognize | | Issuer URL | Your IdP's issuer — the URL that serves `/.well-known/openid-configuration` | | Authorization URL | The `authorization_endpoint` from that discovery document | | Client ID / Client Secret | From the app you registered | The client secret is encrypted at rest and never returned to the browser after saving. ## Okta 1. Admin console → **Applications → Create App Integration** → sign-in method **OIDC**, application type **Web Application** 2. **Sign-in redirect URI:** `https://intermind.com/api/auth/sso/callback` 3. Assign the users or groups who should have access 4. Copy the **Client ID** and **Client Secret** 5. In InterMIND: Issuer URL = your Okta org URL (e.g. `https://acme.okta.com`, or your authorization server's issuer such as `https://acme.okta.com/oauth2/default` if you use one); Authorization URL = the `authorization_endpoint` from `/.well-known/openid-configuration` ## Microsoft Entra ID (Azure AD) 1. Entra admin center → **App registrations → New registration** 2. Platform **Web**, redirect URI `https://intermind.com/api/auth/sso/callback` 3. **Certificates & secrets → New client secret** — copy the secret **Value** immediately 4. Client ID = the **Application (client) ID** on the Overview page 5. Make sure the ID token carries the user's email: **Token configuration → Add optional claim → ID → email** 6. In InterMIND: Issuer URL = `https://login.microsoftonline.com//v2.0`; Authorization URL = `https://login.microsoftonline.com//oauth2/v2.0/authorize` ## Google Workspace No app registration needed. In the SSO card choose the **Google Workspace** provider type and save — members on your verified domains sign in with their Google account and join your team automatically. (Google can also be connected as a generic OIDC provider with issuer `https://accounts.google.com` if you prefer explicit client credentials.) ## Test the connection 1. Open the login page in a private/incognito window 2. Click **Sign in with SSO** and enter a work email on your verified domain 3. You are redirected to your IdP; after authenticating, you land back in InterMIND signed in 4. The sign-in is recorded in the [team audit log](https://intermind.com/docs/users/audit-log) (exportable from the **Users** page) as `auth.login` with method `sso` ## Troubleshooting | Symptom | Cause | | ------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | | "SSO is not configured" after entering the email | No enabled SSO config matches that email domain — check the domain is verified and the SSO card is saved | | `SSO login is not available: plan` | The team's plan no longer includes SSO | | `SSO login is not available: domain-not-verified` | The domain is still pending DNS verification | | `SSO login is not available: config-incomplete` | Client ID or Client Secret missing — re-save the SSO card | | `SSO login is not available: type-unsupported` | The stored provider type is not one the sign-in flow implements — delete the SSO configuration and create it again as OIDC or Google Workspace | | `SSO IdP discovery failed` | Issuer URL is wrong or doesn't serve `/.well-known/openid-configuration` | | "login session expired, start again" | More than 5 minutes passed between starting sign-in and the IdP callback | | Sign-in refused after the IdP redirects back | The IdP returned an email outside your verified domains, or no `email` claim at all (Entra: add the optional email claim) | ## Security properties For security questionnaires: the SSO flow is Authorization Code with **PKCE (S256)**, **state**, and **nonce**; the ID token's **signature is validated against the IdP's JWKS**, along with issuer and audience; the IdP is authoritative only for **domains verified via DNS** — an assertion for any other email never produces a session; the OIDC client secret is **encrypted at rest**; every SSO sign-in lands in the team **audit log**. Plan, domain, and configuration gates are enforced server-side on both the sign-in start and the callback. # Telegram Connect your Telegram account to InterMIND and everything you forward to the InterMIND bot lands in your personal **Inbox** — a system chat only you can see. Add the bot to a Telegram group and it mirrors the group's messages into your channel with the same name. Message flow is **one-way**: Telegram → InterMIND. Replying inside an InterMIND channel does not post back to the Telegram chat. []{#connecting} ## Connecting 1. Open **Integrations** from the sidebar 2. In the **Telegram Integration** card, click **Connect** 3. A Telegram tab opens on the InterMIND bot — press **Start** 4. The bot confirms: *"Connected to \"* The connect link is single-use and works for **15 minutes**; if it expires, start again from Integrations. One Telegram account can be linked to one InterMIND account at a time — if yours is already linked elsewhere, send `/stop` to the bot first. The card shows **Connected** / **Not connected**, refreshed every time you return to the tab. ## Your Inbox The Inbox is created automatically the first time something arrives. It appears in the regular chat list on the **Channels** page, titled **Inbox**, and behaves like a normal chat with two exceptions: it's personal (nobody can be invited into it) and it's the default destination for everything Telegram sends you. What lands there: - Anything you forward or send directly to the bot — text, links, photos, documents, video, voice messages - Group and Secretary-mode messages that don't match a routing rule (see below) A file forwarded with a caption arrives as two messages: the file, then the caption. Messages edited in Telegram are updated in InterMIND too, with the previous text kept in the edit history. ## Mirroring a Telegram group Add the InterMIND bot to a Telegram group (you must be connected first). From then on, group messages flow into **your channel whose name exactly matches the group title**. If no channel matches — or several do — messages go to your Inbox instead; name a channel after the group (or pin the chat, below) to route them. The bot announces the destination in the group when it joins. Removing the bot from the group stops the mirror. ## Secretary mode (Telegram Business) If you have Telegram Premium, you can connect the InterMIND bot as a chatbot for selected personal chats: 1. Open Telegram **Settings → Telegram Business → Chatbots** 2. Tap **Add Bot** and enter the InterMIND bot's username (the same one you connected to in [Connecting](https://intermind.com/#connecting)) 3. Choose **Only Selected Chats** and pick the chats to route 4. Save — the bot confirms with **"Secretary mode is on"** in your chat with it Incoming messages from those chats flow into InterMIND automatically: - into your **shared direct channel** with that person, when the sender is on InterMIND and you share exactly one - into your **Inbox** otherwise Only the other person's messages are ingested — your own outgoing replies are not. Telegram Business is a Telegram Premium feature and covers personal chats only, not groups. ## Routing a chat to a channel To pin a Telegram chat to a specific channel permanently: 1. In your **Inbox**, open the context menu on a message from that chat 2. Click **Always deliver to a channel…** 3. Pick one of your channels and save New messages from that chat now land in the chosen channel. Pins override the name-matching rules and are not retroactive — already-delivered messages stay where they are. Active pins are listed in **Integrations → Telegram Integration** under **Chat routing**; remove one with the **×** button and the chat returns to rule-based routing. ## Disconnecting Two equivalent ways: - **Integrations → Telegram Integration → Disconnect** - Send `/stop` to the bot in Telegram Disconnecting only unlinks the account — already-ingested messages, routing pins, and group connections are kept, but nothing new arrives until you reconnect. ## Limits - Incoming files count toward your team's storage pool. When storage is full, the file is not saved and the bot warns you; text keeps flowing. - Telegram is available on every plan — there is no plan gating. ## Related - [Chat](https://intermind.com/../chat) — channels, messages, and translation - [Email to Channel](https://intermind.com/email-in) — the same one-way route for anything that sends email - [Sharing Files](https://intermind.com/../chat/files) — storage and file handling # API & Zapier Every recap InterMIND produces can land in the tool where you work — your CRM, help desk, task tracker or a spreadsheet — without anyone copying it by hand. Three ways in: - **Your AI assistant** (Claude, ChatGPT, Copilot, Gemini and any other MCP client): see [AI assistants (MCP)](https://intermind.com/docs/integrations/mcp). - **Zapier** (no code): connect InterMIND once with an API key, then build Zaps on the *Meeting Recap Ready* trigger and the *Create Meeting Link* action. The same integration also works from Make, n8n or Pipedream through their generic webhook and HTTP modules, using the API below. - **The API** (for developers): a personal key, one webhook event and a dozen endpoints — meetings, recaps, transcripts, channels, documents. **Available on:** every registered account. Guests cannot create keys. **Where:** Integrations → API keys. ::callout{type="info"} Recaps also reach any tool that has an inbound email address — add it as a recap copy recipient on the meeting or channel, no integration needed. See [Recap copy](https://intermind.com/docs/meetings/recap). :: ## API keys 1. Open **Integrations** and find the **API keys** card. 2. Click **Create key**, give it a label (the tool that will use it, e.g. "Zapier") and copy the key. It starts with `imk_` and is shown **once** — InterMIND stores only a hash. 3. Revoke a key from the same card at any time. Webhook subscriptions created with that key stop immediately. Up to 10 keys per account. Send the key as a bearer token: ```http Authorization: Bearer imk_… ``` Keys work only on the `/api/v1` endpoints below; they never grant access to the web application's own API. ## Zapier 1. In Zapier, add the **InterMIND** app to a Zap and paste your API key when asked. The connection is labelled with your account email. 2. Trigger **Meeting Recap Ready** — fires once per finished meeting you hosted, as soon as the summary exists. Fields: meeting title and link, recap link, transcript link, the summary in Markdown, summary language, start and end time, participants (name, email), host. 3. Action **Create Meeting Link** — creates an ad-hoc meeting you own and returns its URL. Put it in a CRM deal, a support ticket or a calendar invite; anyone who opens the link knocks and you approve them in the room. Typical Zaps: recap → new note on the HubSpot deal; recap → internal comment on the Zendesk ticket; recap → row in Google Sheets; new Pipedrive deal → meeting link written back to the deal. ## Endpoints Base URL: `https://intermind.com/api/v1`. All responses are JSON. Machine-readable contract (OpenAPI 3.1, for Make, n8n, Pipedream and AI agents): `https://intermind.com/api/v1/openapi.json`. | Method | Path | Purpose | | -------- | ---------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `GET` | `/me` | Who owns the key: `{ id, email, name }` | | `POST` | `/meetings` | Create an ad-hoc meeting link. Body `{ "title": "…" }` (optional). Returns `201 { id, url, title, created_at }`. With `starts_at` (`YYYY-MM-DDTHH:mm`), `time_zone`, optional `duration_min` and `invitees`, the meeting is also written to your connected calendar; the response adds the window and `calendar: created / not_connected / failed` | | `GET` | `/meetings?kind=recent|upcoming&type=&limit=10` | Meetings you host or attend: `recent` by last activity, `upcoming` scheduled in the future | | `GET` | `/meetings/{id}/transcript?session=&max_chars=60000` | Latest finalized transcript as Markdown by speaker, in the spoken language (or your cached translation); `truncated` when cut | | `GET` | `/recaps?limit=3` | Your newest recaps (1–10), newest first, in the webhook payload shape | | `GET` | `/recaps/search?q=&limit=5` | Recaps whose title or current summary mentions the words (word forms match), with a highlighted snippet and links | | `GET` | `/channels?limit=20` | Team chats and inboxes you belong to | | `GET` | `/channels/{id}/messages?limit=50&before=` | One page of a channel's chat, oldest first, with the cached translation into your chat language when the room made one | | `POST` | `/channels/{id}/messages` | Post `{ "text": "…" }` as you → `201 { id, sent_at, text }`; fanned out live and translated for every reader | | `GET` | `/documents?meeting_id=&limit=50` | Files shared in your meetings — uploads and linked Drive / OneDrive files | | `GET` | `/webhooks` | Your webhook subscriptions | | `POST` | `/webhooks` | Subscribe: `{ "target_url": "https://…", "event": "recap.ready" }` → `201 { id, event, target_url, secret, created_at }` | | `DELETE` | `/webhooks/{id}` | Unsubscribe → `204` | A key carries the rights it was created with: keys created before September 2026 open `/me`, `POST /meetings`, `/recaps` and `/webhooks` only — the newer endpoints answer `403` until you create a new key (or reconnect the app). Reading is limited to meetings you host or attend: another meeting's id answers `404`. Limits: 10 keys and 20 webhook subscriptions per account. `target_url` must be `https://` and publicly reachable — private network addresses are refused. ## Webhook: `recap.ready` Sent as `POST` JSON to every subscribed `target_url` the moment a recap for a meeting **you hosted** is finalised with a non-empty summary. It is sent once per meeting session. Headers: | Header | Value | | ----------------------- | ------------------------------------------------------------------------- | | `X-InterMIND-Event` | `recap.ready` | | `X-InterMIND-Delivery` | Unique id of this event (`.`) — deduplicate on it | | `X-InterMIND-Signature` | `sha256=` | | `User-Agent` | `InterMIND-Webhooks/1` | Payload: ```json { "id": "abc-def-ghi.conf_01", "event": "recap.ready", "occurred_at": "2026-09-04T10:32:11.000Z", "meeting": { "id": "abc-def-ghi", "title": "Weekly sync with Acme", "url": "https://intermind.com/abc-def-ghi", "type": "adhoc" }, "recap": { "url": "https://intermind.com/r/abc-def-ghi/…", "transcript_url": "https://intermind.com/t/abc-def-ghi/…", "summary_md": "## Decisions\n- …", "language": "en" }, "session": { "started_at": "2026-09-04T10:00:03.000Z", "ended_at": "2026-09-04T10:31:40.000Z" }, "participants": [{ "name": "Anna Müller", "email": "anna@acme.example" }], "host": { "name": "Anna Müller", "email": "anna@acme.example" } } ``` Delivery rules: your endpoint should answer `2xx` within 8 seconds. A network error, `5xx` or `429` is retried once immediately. A `410` or `404` deletes the subscription. Any other failure is logged and the event is not resent — the recap email and the recap page remain the durable record. Recap and transcript links open for meeting participants who are signed in. # Email to Channel Every channel can have its own email address, and so can your personal **Inbox**. Anything that sends email — monitoring alerts, ticketing systems, CRMs, billing, CI pipelines, newsletters, a colleague forwarding a thread — lands there as a regular message: the sender named, attachments kept, signatures and quoted reply tails stripped. Members see it live on web and desktop, get a push on mobile, and read it in their own language. The [Email to Channel feature page](https://intermind.com/features/email-in) shows this in action. Message flow is **one-way**: email → InterMIND. Replying inside the channel does not send email back. ## Creating a channel address Only the channel **host** can create, see, or remove the address: 1. Open the channel and click the display-settings **gear icon** in the chat header 2. Choose **Email to channel** 3. Click **Create address** — you get a private address of the form `@in.intermind.com` 4. **Copy** it and paste it wherever a tool asks for a notification email The same dialog offers **New address** (rotate) and **Remove address**. Rotating or removing takes effect immediately — the old address stops working. ## Your Inbox address Your personal Inbox has an address too: open the Inbox chat, gear icon → **Email to Inbox**. Emails sent there are visible to you alone. Use it for things only you should see; use a channel address for things the team should see. ## Keep the address private The address is a capability: anyone who has it can post into the channel, so treat it like a password. If it leaks, issue a new one. Mail to an address that does not exist is dropped silently — no bounce, no reply — so a guessed address gives an attacker nothing to go on. ## What arrives, and how - **Text** — the plain-text part is used; an HTML-only email is converted to text. Bodies are capped at 100,000 characters - **Sender** — the message is attributed to the sender's name and address, not to the channel host, and translated for each reader like any external message - **Subject** — kept as the first line of the message - **Signatures and quoted tails** — stripped, so a forwarded thread shows the new content rather than the whole history - **Attachments** — kept as file messages, each up to **25 MB** ## Limits - Attachments count toward your team's storage pool. When storage is full the text still arrives and the attachment is skipped, with a note in the message saying so - Up to **30 emails per hour** per address; anything beyond that in the same hour is dropped - Email to channel is available on every plan ## Related - [Email to channel: how any service posts into your team chat without a bot](https://intermind.com/blog/email-to-channel-no-bot) — the mechanics and the comparison with bot tokens - [Telegram](https://intermind.com/telegram) — forward messages and mirror groups the same one-way route - [Channels & Members](https://intermind.com/../chat/channels) — hosts, members, invites - [File Sharing](https://intermind.com/../chat/files) — storage and file handling # AI assistants (MCP) InterMIND ships a remote [Model Context Protocol](https://modelcontextprotocol.io){rel=""nofollow""} server. Add it once to your assistant and it can create and schedule meetings, read your recaps and transcripts, find what was decided, read your channels and post in them, and see the documents shared in your meetings — from the same conversation where it works with your CRM, help desk or calendar. **Server URL:** `https://intermind.com/api/mcp`**Available on:** every registered account. Guests cannot connect apps. **Works with:** any MCP client — Claude (claude.ai, Desktop, Code), ChatGPT, Microsoft 365 Copilot (Copilot Studio), Gemini, Cursor, Windsurf, VS Code, Le Chat, Perplexity and agent SDKs. ## Tools | Tool | What it does | | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `create_meeting_link` | Creates an ad-hoc meeting you own and returns its URL. Put it in a calendar invite, a deal or a ticket; anyone who opens it knocks and you admit them. | | `schedule_meeting` | Creates a meeting at a local time and puts it in your connected Google or Microsoft calendar with the invitees. Without a connected calendar the link still works but carries no time. | | `list_meetings` | Meetings you host or attend: recent by activity, or upcoming (scheduled in the future). | | `list_recaps` | Your newest recaps (1–10) over the meetings you host or attend, newest first: title, when, links to the recap and transcript pages, and the summary in Markdown. | | `search_recaps` | Finds recaps whose title or summary mentions the words (word forms match: "pricing" finds "price"), over the meetings you attend — "what did we decide about Acme". Returns a snippet with the matches in bold and the links. | | `get_transcript` | The transcript of a meeting you attend, grouped by speaker, in the spoken language (or your cached translation). Long ones are cut at a limit with a link to the full page. | | `list_channels` | The team chats and inboxes you belong to. | | `get_channel_messages` | A page of a channel's chat: sender, time, the text as written and, when the room already translated it, the text in your language. | | `post_channel_message` | Writes a message in a channel as you. Every member reads it in their own language; it goes into the channel's recap. The answer carries the channel link and the message id. | | `list_documents` | Files shared in a meeting or channel you attend — uploads and linked Drive / OneDrive files. | | `search_knowledge` | Searches everything you can see at once — recaps, transcripts, chats and the text of shared files — by meaning and by words, and returns the best-matching passages with the meeting, the date and the file each comes from. For organizations with AI features on. | | `read_document` | The extracted text of a shared file — by the document id from `list_documents` or a document passage of `search_knowledge`; a file name is not an id. Long texts are cut at a limit. | | `search_docs` | How InterMIND itself works — features, plans, settings, integrations — from this documentation. | | `list_team_pages` | Your organization's status pages, computed from its meeting recaps — tasks, problems, important and urgent, money at stake, requests by cohort — and whether pages are on for the account. The assistant calls it first to pick a page. | | `read_team_page` | One status page over the last 7, 28 or 90 days: every row carries the verbatim quote from the recap it rests on and the link to that recap; grouped by assignee or cohort where the page says so. | | `add_glossary_term` | Remembers how a term must be translated for your organization — «translate X into French as Y», «never translate X», «the recap rendered X as Y, it should be Z». The translator applies it in recaps, transcripts, documents, chat and notes. | | `list_glossary_terms` | The rules the translator reads, with their ids. | | `remove_glossary_term` | Drops one rule by id. | Every participant takes part in their own language — the assistant does not need to know which. Reading is limited to meetings you host or attend; the assistant never sees a meeting you are not in. Team status pages follow the same line: a member sees the rows of sessions they hosted or attended plus the rows assigned to them, an organization admin sees the whole organization. On plans billed per active member, a call through the assistant counts as your activity for that period, the same as joining a meeting. :preview-mark{slug="team-pages"} **Connections made before September 2026** carry only the first two tools' rights (meeting links, recaps). To use the rest, reconnect InterMIND in your assistant, or create a new key in **Integrations → API keys** — a tool the connection lacks answers with that exact instruction. ## Connect Two ways to sign in. Most assistants use the first one automatically. - **Sign in with InterMIND (OAuth).** Add the server URL; the assistant opens an InterMIND page where you allow the connection. It appears in **Integrations → API keys** under the assistant's name — revoke it there at any time and the assistant asks you to reconnect. - **API key.** Create a key in **Integrations → API keys** and give it to clients that take a static header (Claude Code, Cursor, Gemini CLI, Copilot Studio): `Authorization: Bearer imk_…`. ### Claude (claude.ai, Desktop) InterMIND is listed in the [Claude Connectors Directory](https://claude.ai/directory/connectors/intermind){rel=""nofollow""}: open the listing, click **Connect** and allow the connection on the InterMIND page. To add it by URL instead, go to **Customize → Connectors → Add custom connector**, paste `https://intermind.com/api/mcp`, click **Add**, then **Connect**. On Team and Enterprise plans an organization owner adds the connector under **Organization settings → Connectors**. ### Claude Code ```bash claude mcp add --transport http intermind https://intermind.com/api/mcp ``` Run `/mcp` inside Claude Code to sign in, or pass a key instead: `claude mcp add --transport http intermind https://intermind.com/api/mcp --header "Authorization: Bearer imk_…"`. ### ChatGPT Turn on **Settings → Apps & Connectors → Advanced → Developer mode** (Plus, Pro, Business, Enterprise or Edu; in a workspace an admin has to allow custom connectors). Then **Create** a connector with the server URL, authentication **OAuth**, and allow the connection on the InterMIND page. ### Cursor, Windsurf, VS Code Add a remote MCP server with the URL above. With OAuth the editor opens the InterMIND page; with a key, put `Authorization: Bearer imk_…` in the server's headers. ### Microsoft 365 Copilot (Copilot Studio) In your agent: **Tools → Add a tool → New tool → Model Context Protocol**, paste the server URL and choose **OAuth 2.0 → Dynamic discovery**, or **API key** (header `Authorization`, value `Bearer imk_…`). ### Gemini (personal account) In the Gemini web app: **Settings & help → Connected apps → Custom apps for Spark → Add a custom app** with the server URL, then allow the connection on the InterMIND page. Google offers custom apps to personal accounts only; a work or school account uses Gemini Enterprise below. Gemini CLI takes the URL plus an `Authorization` header in its MCP settings. ### Gemini Enterprise (team) A team administrator adds the server once for the team in **Settings & help → Team → Manage team → Connected apps → Add MCP Server**. Gemini Enterprise does not register itself, so create a client for it first — one request, no account needed: ```bash curl -s https://intermind.com/oauth/register -H "Content-Type: application/json" -d '{ "client_name": "Gemini Enterprise", "redirect_uris": ["https://vertexaisearch.cloud.google.com/oauth-redirect"], "token_endpoint_auth_method": "client_secret_post" }' ``` The reply carries `client_id` and `client_secret`; the secret is shown once. Fill in the form: | Field | Value | | ------------------------ | --------------------------------------- | | MCP server URL | `https://intermind.com/api/mcp` | | Authorization URL | `https://intermind.com/oauth/authorize` | | Token URL | `https://intermind.com/oauth/token` | | Client ID, Client secret | from the reply above | | Scopes | leave empty | | PKCE | on (required) | Enable the tools you want the team to use — new servers start with every action off. Each member signs in with their own InterMIND account on first use, so the assistant sees that member's meetings, not the administrator's. Gemini inside Gmail, Docs and Meet (the Workspace bundle) only takes the integrations Google ships itself; it does not connect custom servers. ## Ask your assistant - "Create an InterMIND meeting link for tomorrow's call with Acme and put it in the deal." - "What did we agree with Acme last week? Check my InterMIND recaps." - "Summarise my last three InterMIND meetings and add the action items to my task list." ## Security and privacy - The assistant acts as you within the [public API](https://intermind.com/docs/integrations/api-zapier): it can see your account name and email, create and schedule meetings you own, read recaps and transcripts of meetings you attend, search your recaps, read and post in your channels, and list the documents shared there — including receiving new recaps by webhook, as any API key can. It cannot join a meeting, speak in it, change your settings, or read anything from a meeting you are not in. - A connection never gains rights after the fact: what you allowed on the consent page is what it keeps. New tools ask you to reconnect. - Access is a per-connection credential you can revoke in **Integrations → API keys**. There are no shared organization tokens. - Recap and transcript links open for meeting participants who are signed in. - What InterMIND stores and for how long: [Privacy Policy](https://intermind.com/privacy). Developers: the underlying endpoints are the [public API](https://intermind.com/docs/integrations/api-zapier); discovery documents live at `/.well-known/oauth-protected-resource` and `/.well-known/oauth-authorization-server`. ## Related - [Your meetings, from the assistant you already use](https://intermind.com/blog/connect-your-ai-assistant-to-intermind) — what to ask, how each assistant connects, and where the connector stops. - [Best MCP servers for meetings (2026)](https://intermind.com/blog/mcp-servers-for-meeting-tools) — what Zoom, Teams, Fireflies, Otter, Granola and InterMIND expose to an assistant, from vendor documentation. # Slack The InterMIND app for Slack does three things: `/intermind` starts a meeting from the channel you are in — now, or at a time you name — the recap of that meeting comes back to Slack when it is ready, and a pasted InterMIND link becomes a card. Your team keeps working in Slack; the meeting and its recap are InterMIND's. The public page of the app is [intermind.com/slack](https://intermind.com/slack). Messages are **not** synced between Slack channels and InterMIND channels. To move a workspace's history over, use the [Slack import](https://intermind.com/migrate-from-slack). ## Adding the app to a workspace 1. Open **Integrations** from the sidebar 2. In the **Slack** card, click **Add to Slack** 3. Pick the workspace and approve ![Slack card in Integrations](https://intermind.com/img/docs/integrations/slack-card.png) The app asks for five permissions: adding the `/intermind` command, posting messages as InterMIND, posting to public channels it has not been invited to, receiving the links to intermind.com that are posted, and replacing such a link with a card. It cannot read messages, files, or the member list. The app is installed per workspace. The person who adds it is connected right away; everyone else connects their own account the first time they use the command. A workspace that installed the app before link previews existed sees **Update permissions** in the Slack card — the same approval flow, once. ## Connecting your account The first time you run `/intermind`, Slack shows you — and only you — a **Connect your InterMIND account** link. Open it, sign in, and confirm. The link works for **10 minutes**; run the command again for a fresh one. The Home tab of the app offers the same link. Meetings you start from Slack are hosted by your InterMIND account: your plan, your meeting list, your recap. ## Commands | Command | What it does | | ------------------------------------- | --------------------------------------------------------------- | | `/intermind` | Starts a meeting and posts the join link in the channel | | `/intermind Weekly sync` | Same, with a title | | `/intermind tomorrow 3pm Weekly sync` | Schedules the meeting for that time and posts the join link now | | `/intermind timezone Europe/Berlin` | Sets the time zone your scheduled times are read in | | `/intermind recaps here` | Sends the recaps of **your** meetings to this channel | | `/intermind recaps off` | Stops sending recaps to a channel | | `/intermind help` | Lists the commands | Anyone in the channel can open the link. People without an InterMIND account join as guests and the host admits them, exactly as with any meeting link. ## Scheduling from Slack A command that starts with a day and a time schedules the meeting instead of starting it: `today 17:00`, `tomorrow 3pm`, `fri 15:00`, `2026-10-01 at 10:30`, each followed by an optional title. The app posts the join link in the channel right away with the scheduled time, the meeting appears in your upcoming list in InterMIND, and it lasts 60 minutes on the calendar grid. The recap comes back to the same thread when the meeting ends. Times are read in the time zone saved with your connection — your browser's zone at the moment you connected. To change it, or if the app asks for it, run `/intermind timezone Area/City` once with an IANA name such as `Europe/Berlin` or `America/New_York`. A day without a time, or a time that has already passed, schedules nothing; the app tells you so, visibly only to you. Scheduling from Slack does not write to your calendar. To put the meeting into Google or Microsoft Calendar, open the meeting in InterMIND and use **Add to calendar**. ## Where the recap goes - A meeting started with `/intermind` gets its recap **in the thread** under the join message. - Every other meeting you host goes to the channel you chose with `/intermind recaps here` — one channel per workspace, per person. - If you chose no channel, nothing is sent to Slack. The Slack message carries the summary and a link to the full recap. The summary in Slack is in the recap's language; the link opens it in the language each reader uses in InterMIND. In a **private channel** or a direct message the app can post only after it is invited (`/invite @InterMIND`). Until then the join link is still posted, and the recap arrives as a direct message from the app with a note saying why. ## Meeting links become cards Paste an InterMIND meeting link (`intermind.com/xxx-xxx-xxx`) or a recap link anywhere in Slack and the app replaces it with a card: the meeting's title, who hosts it, the scheduled time when there is one, and a **Join the meeting** button. A recap link becomes a card with the title and an **Open the recap** button — the recap's text reaches Slack only through the thread or the channel you chose. The card never shows more than the meeting's join screen shows to anyone who opens the link. Links to InterMIND channels, documents or pages other than a meeting or a recap are left as they are. ## The Home tab Click **InterMIND** under Apps in the Slack sidebar. The Home tab shows whether your account is connected and where your recaps go, lists the commands, and has a **Start a meeting** button: the join link comes to you as a direct message from the app, ready to share, and that meeting's recap comes back to the thread of that message. If your account is not connected yet, the tab offers the **Connect your InterMIND account** link instead. ## Disconnecting **Disconnect** in the Slack card removes the connection between your Slack user and your InterMIND account; recaps stop. To remove the app from the whole workspace, a workspace admin removes it in Slack — InterMIND deletes the workspace's token and every connection when Slack reports the removal. # Integrations InterMIND integrates with external services in one place: your own connections — calendar, Slack, Telegram, API keys, AI assistants — and the team-level ones — directory sync, domain management and SSO. ![Integrations page](https://intermind.com/img/docs/integrations/integrations-page.png) The **Integrations** page is reached from the sidebar. Which cards appear depends on your role and plan: | Block and card | Who sees it | | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | | **Your connections** — [Calendar](https://intermind.com/docs/settings/calendar), [Slack](https://intermind.com/docs/integrations/slack), [Telegram](https://intermind.com/docs/integrations/telegram), [API keys](https://intermind.com/docs/integrations/api-zapier), [AI assistants (MCP)](https://intermind.com/docs/integrations/mcp) | Every signed-in member | | **Team** — Directory Integration | Team owners and admins, on every plan | | **Team** — SSO, Domain Management | Team owners and admins. On a plan without them the cards are shown under **Not in your plan** with the plan they need; clicking one names the plan | Members who do not administer the team do not see the **Team** block. ::callout{type="info"} [Backup & Restore](https://intermind.com/docs/settings/data-export) lives on the **Settings** page. A channel's [email address](https://intermind.com/docs/integrations/email-in) is managed from the channel itself. :: []{#domain-management} ## Domain Management Verify your organization's domains to enable SSO and automatic team membership. ### Adding a Domain 1. Open the **Integrations** page from the sidebar 2. In the **Domain Management** card, type your domain (e.g., `yourcompany.com`) in the input field 3. Press **Enter**, comma, or space to add it 4. The domain appears with a "pending" status ### Verifying a Domain Domains are verified via DNS TXT records: 1. Copy the verification code shown for your domain 2. Add a DNS TXT record in your domain registrar (e.g., GoDaddy, Cloudflare) 3. Use the verification code as the TXT record value 4. Click **Verify All** or wait for the 60-second automatic check 5. Once DNS propagates, the domain status changes to "verified" ✓ ### Domain Statuses | Status | Icon | Meaning | | -------- | ---- | ------------------------------------- | | Verified | ✓ | Domain confirmed — SSO can be enabled | | Pending | ⏳ | Waiting for DNS verification | | Invalid | ✗ | DNS check failed — verify TXT record | ## SSO **Available on:** Business and Enterprise plans :br**Requires:** At least one verified domain Members signing in with an email on one of your verified domains join your team automatically (see [Domain Management](https://intermind.com/#domain-management) above). With an identity provider configured in the **SSO** card, they sign in through it: login page → **Sign in with SSO** → work email → your IdP. ### Identity Provider Configuration Follow the step-by-step [SSO Setup](https://intermind.com/docs/integrations/sso-setup) guide for Okta, Microsoft Entra ID, and Google Workspace. | Provider | Configuration | | ------------------------- | ------------------------------------------------------- | | **OIDC / OpenID Connect** | Issuer URL, Authorization URL, Client ID, Client Secret | | **Google Workspace** | Verified domain only — members use their Google account | ## Directory Integration Sync your organization's user directory to simplify team management. ### Supported Providers | Provider | Permissions | | ---------------------------- | ---------------------------------- | | **Google Workspace** | Read-only access to user directory | | **Microsoft 365 (Entra ID)** | Read-only access to user directory | ### Connecting a Directory 1. Open the **Integrations** page from the sidebar 2. In the **Directory Integration** card, click **Connect** next to your provider 3. Sign in with an **admin account** in the OAuth popup 4. Grant read-only access to the user directory 5. The connection status updates to "Connected" **Important:** An admin account on the provider side is required. Only read access to the user directory is requested — InterMIND never modifies your directory. ### Disconnecting Click **Disconnect** next to a connected provider to remove the directory integration. # Managing Your Subscription This guide covers how to start, change, and cancel your InterMIND subscription. ![Billing page](https://intermind.com/img/docs/billing/billing-page.png) ## Subscribing to a Plan ### From the Pricing Page ::steps ### Go to the Pricing page Visit the [Pricing](https://intermind.com/pricing) page (accessible from the footer or navigation). ### Choose billing interval Toggle between **Monthly** and **Yearly** billing (the yearly discount is shown on the [pricing page](https://intermind.com/pricing)). ### Select a plan Click the plan's CTA: - **Basic** — **Get started free** (no checkout, free forever) - **Pro** — **Try for free** the first time, or **Get Pro** if you've already used your trial - **Business** — **Try for free** the first time, or **Get Business** if you've already used your trial - **Enterprise** — **Contact Sales** to fill out the inquiry form ### Complete checkout The first **Try for free** on Pro opens no checkout at all: the 14-day Pro trial starts at once, with no card (see [Free Trial](https://intermind.com/../billing#free-trial)). In every other case you'll be redirected to the secure checkout page — Stripe, or Paddle in selected countries. Enter your payment details and confirm. ### Plan activated After successful payment, you're redirected back to InterMIND with your new plan active. :: ### For Pro and Business Plans There is nothing to size at checkout. Invite your whole team: every member of a paid organization gets everything the plan includes, and each renewal bills only the members who were **active in the previous 28 days** — joined a meeting, wrote in a chat or asked Mia. Members who go quiet cost nothing and keep their access; the owner is always counted. Meeting guests and channel participants outside your team are always free. The **Users** page shows who is active in the current window and how many members the next renewal counts. ### If You're Not Signed In If you click a plan button while not logged in: ::steps ### Redirect to login You'll be redirected to the login page. ### Sign in After signing in, your selected plan continues automatically: a first Pro trial starts with no card, anything else opens checkout. :: ## Changing Your Plan ### Upgrading To upgrade to a higher plan: ::steps ### Go to Pricing or Billing Visit the [Pricing](https://intermind.com/pricing) page or [Billing](https://intermind.com/billing) page. ### Click Upgrade Select the desired plan. ### Confirm in the billing portal The portal shows a prorated price for the remainder of your billing period. ### Done Confirm the upgrade — your new plan takes effect immediately. :: ### Downgrading To switch to a lower-tier plan: ::steps ### Go to Pricing or Billing Visit the [Pricing](https://intermind.com/pricing) page or [Billing](https://intermind.com/billing) page. ### Select the lower plan Choose the plan you want to switch to. ### Confirm in the billing portal The downgrade typically takes effect at the end of your current billing period. :: ### Switching Billing Interval To switch between monthly and yearly billing: 1. Open the **customer portal** (via Billing page) 2. Change your billing interval 3. Yearly billing applies the current yearly discount automatically ## Cancelling Your Subscription ### How to Cancel ::steps ### Open Billing Go to the **Billing** page from the sidebar. ### Click Cancel You'll be redirected to your payment provider's customer portal. ### Confirm cancellation Confirm the cancellation in the portal. :: ### What Happens After Cancellation - **During trial**: The subscription ends **immediately** — no further access to paid features - **After trial**: Your subscription remains active until the end of the current billing period - The Billing page shows "Subscription Ending" with the end date - After the period ends, your account reverts to the **Basic** (free) plan ### Reactivating If you've cancelled but the billing period hasn't ended yet: 1. Go to the **Billing** page 2. Click **Reactivate** 3. Your subscription continues as normal — no new charge until the next billing period ### Resubscribing If your subscription has fully expired: 1. Go to the [Pricing](https://intermind.com/pricing) page 2. Choose a plan and go through the checkout process 3. Note: the free trial is **not available** if you've used it before ## Payment Methods Payment is handled entirely through our payment providers — Stripe, or Paddle in selected countries: - **Credit/debit card** is the accepted payment method - Manage your payment methods through the customer portal - Update your card before it expires to avoid payment failures ## Payment Issues If a payment fails: - You'll receive a notification about the failed payment - The payment provider will retry the payment automatically - If the issue persists, update your payment method in the Customer Portal - Continued payment failure may result in your subscription being cancelled ## FAQ ### Can I switch plans at any time? Yes, you can upgrade or downgrade at any time. Upgrades take effect immediately with prorated billing. Downgrades take effect at the end of your billing period. ### What happens to my data if I cancel? Your data is preserved after cancellation. If you resubscribe, everything will be as you left it. However, if your storage exceeds the Basic plan limit, you'll need to upgrade to access all files. ### Can I get a refund? Refunds follow the refund policy of the payment provider that processed your purchase. Purchases made through Paddle are governed by [Paddle's Refund Policy](https://www.paddle.com/legal/refund-policy){rel=""nofollow""} and refund requests are handled by Paddle. Except where required by applicable law, subscription fees are non-refundable. ### Is my payment information secure? Yes. All payment processing is handled by our payment providers — Stripe, or Paddle in selected countries. InterMIND never stores your credit card details. # Usage & Invoices The Billing page provides a clear view of your current plan, resource usage, and payment history. ## Accessing the Billing Page 1. Sign in to InterMIND 2. Click **Billing** in the sidebar navigation 3. The page displays your plan status, usage meters, and invoices ## Current Plan Status At the top of the Billing page, you'll see: - **Plan name** — Your current subscription tier (Basic, Pro, Business, or Enterprise) - **Billing status** — Whether you're on a trial, monthly, or annual plan - **Next billing date** — When your next payment is due - **Subscription status** — Active, trialing, or ending (if cancelled) Owners and admins can also set the **organization name** here — it shows up to teammates and on shared invitations. ## Usage Monitoring ### Voice Translation The **Voice Translation** meter shows your meeting translation usage over a **rolling 30-day window**: - **Progress bar** — Visual indicator of used vs. available translation time - **Exact numbers** — Minutes used out of your monthly allowance - **Color coding**: - **Blue/Green** — Normal usage (under 80%) - **Yellow/Warning** — Approaching limit (80%–99%) - **Red/Error** — At or over limit (100%) The 30-day window means usage gradually expires — as sessions from 30+ days ago fall off, your available time increases. Each plan includes a monthly allowance, measured per **meeting host** — minutes spent translating in any meeting you created count against your plan, not the listener's: | Plan | Monthly Translation Time | | -------------- | ------------------------ | | 🆓 Basic | 2 hours | | ⭐ Pro | 25 hours | | 🏢 Business | Unlimited | | 🏛️ Enterprise | Unlimited | #### When You Reach the Limit 1. **Warning** — you see a notification that you're approaching the limit 2. **Language lock** — at the limit, you can no longer change the language you hear and read in 3. **Translation stops** — real-time translation is paused until usage falls below the limit The meeting itself continues — chat, video, and every other feature keep working (chat translation has its own limit, below). If you consistently run out, [upgrade your plan](https://intermind.com/pricing) or wait for older usage to roll off the 30-day window. ### Storage The **Storage** meter shows your team's shared storage pool: - **Progress bar** — Used storage vs. plan limit - **Exact numbers** — GB used out of your storage allowance - **Same color thresholds** — Blue → Yellow (≥80%) → Red (≥100%) Storage is shared across your entire team — all members' files, recordings, and uploads count toward the same limit. ### Text Translation The **Text Translation** meter shows your chat translation usage over the same **rolling 30-day window**: - **Progress bar** — Words translated vs. plan limit. Only the free Basic plan has a word cap (10K/month); on every paid plan text translation is unlimited and the bar is replaced by an **Unlimited** label - **Exact numbers** — Words used out of your monthly allowance, shown in thousands (e.g. `3K / 10K` on Basic) - **Same color thresholds** — Blue → Yellow (≥80%) → Red (≥100%) Text translation is tracked per **meeting host** — only messages translated for participants in meetings you created count toward your limit. When the Basic cap is reached, new messages are still delivered — just not translated. See [Chat Translation](https://intermind.com/../chat/translation). ### Document Translation The **Document Translation** meter shows uploaded-document translations used over the same **rolling 30-day window**: - **Progress bar** — Documents translated vs. plan limit - **Exact numbers** — Documents used out of your allowance (e.g. `4 / 10 documents`) - Metered in **distinct files** — Pro 10, Business 30, Enterprise 100 per 30 days. Re-translating the same file into more languages does not count again - The free Basic plan shows **Not on this plan** — document translation requires a paid plan ## Invoices ### Viewing Invoices The invoices section shows your complete payment history: | Column | Description | | ----------- | ------------------------------------------ | | **Date** | When the invoice was generated | | **Total** | The amount charged | | **Status** | Payment status badge (Paid, Open, or Void) | | **Actions** | Link to view the full invoice on Stripe | ### Invoice Details Click **View** on any invoice to open the full invoice on Stripe's hosted page, where you can: - See itemized charges - Download a PDF copy - View payment method used ### Pagination Invoices are loaded 10 at a time. Click **Load more** at the bottom to see older invoices. ## Understanding Your Usage ### Translation Time Calculation - Translation time is tracked **per meeting host** — usage in any meeting you created counts against your plan, regardless of which participant triggered the translation - Displayed in minutes on the UI - Only active translation time counts — pausing translation stops the meter - Usage rolls off after 30 days, so the available limit gradually refreshes ### Storage Calculation - Storage is calculated as the **total size of all files** across the team - Includes: uploaded files, shared images, screen recordings - Does not include: text messages, user profiles ## Tips - Check the Billing page regularly to avoid hitting usage limits unexpectedly - If translation usage is consistently high, consider upgrading to a plan with more hours - Storage is shared — coordinate with your team if storage is getting full - Download important recordings locally if you're approaching the storage limit - Set up a yearly billing cycle — the discount is shown on the [pricing page](https://intermind.com/pricing) # Billing & Plans InterMIND offers four subscription tiers. The host of the space picks the plan; members, guests and everyone invited by link pay nothing. All plans include core features like real-time translation, video calls, and screen sharing. ## Plans Overview | Feature | 🆓 Basic | ⭐ Pro | 🏢 Business | 🏛️ Enterprise | | ---------------------------- | ------------- | ------------------------ | -------------------------- | ------------------------------------ | | **Best for** | Trying it out | A host with a small team | A host with a growing team | Larger organizations (contact sales) | | **Translation time** | 2 hours/month | 25 hours/month | Unlimited | Unlimited | | **Text translation** | 10K words | Unlimited | Unlimited | Unlimited | | **Document translation** | — | 10 docs/month | 30 docs/month | 100 docs/month | | **Meeting participants** | 50 | 100 | 300 | 1,500 | | **Team members** | 1 | Unlimited | Unlimited | Unlimited | | **Storage** | 1 GB | 30 GB | 1 TB | 5 TB | | **Meeting duration** | 1 hour | Unlimited | Unlimited | Unlimited | | **SSO (OIDC with your IdP)** | — | — | ✓ | ✓ | | **Support** | Live chat | Live chat | Live chat & video | Live chat & video | ::callout{type="tip"} **Most popular**: The **Pro** plan is the best choice for most hosts — it includes 25 hours of translation, unlimited text translation, and unlimited team members. [See pricing →](https://intermind.com/pricing) :: ### Features Included in All Plans ::callout{type="info"} Every plan comes with all core features — no hidden limitations: - ✅ FHD video & audio calls - ✅ Real-time translation with live subtitles - ✅ Automatic transcription & AI meeting recap - ✅ Text translation (10K words/month on Basic, unlimited on all paid plans) - ✅ Screen sharing - ✅ Cloud & local recording - ✅ File sharing in chat - ✅ Full chat history - ✅ Private translation infrastructure \:: ## Pricing ### Billing Intervals Choose between two billing options: - **Monthly** — Pay month-to-month, cancel anytime - **Yearly** — a discount compared to monthly billing; the current rate is shown on the [pricing page](https://intermind.com/pricing) Yearly prices are displayed as monthly equivalents (annual price ÷ 12) for easy comparison. ### Enterprise Pricing Enterprise plans have custom pricing. Click **Contact Sales** on the [pricing page](https://intermind.com/pricing) to fill out an inquiry form with your requirements. ## Free Trial Pro and Business include a **14-day free trial** with full access to the plan's features. **One trial per account** — once used, the trial option is no longer available. **Pro — no card needed.** Click **Try for free** on the [pricing page](https://intermind.com/pricing) and Pro is active at once; no payment form opens. The same trial is offered inside the product when you reach a limit of the free Basic plan — the 24-hour meeting limit, the voice or chat translation allowance, document translation, or storage. - A **Pro trial** card in the sidebar shows the days left, with **Add a card** - Add a card any time before the trial ends to keep Pro — the first charge happens when the trial ends - With no card on file nothing is charged: the account moves to the free Basic plan when the trial ends, and your meetings, chats, recaps and files stay - You get an email three days before the trial ends and on the day it ends **Business — card up front.** The Business trial starts at checkout with a card; nothing is charged until the trial ends, and you can cancel any time before that. In countries where checkout runs through Paddle, plans start without a trial. :::callout{type="info"} If you cancel during the trial period, the subscription ends immediately rather than continuing until the trial expires. ::: ## New Customer Offer New customers — accounts that have never paid an invoice — receive an introductory discount on the first 3 months; the current rate is shown on the [pricing page](https://intermind.com/pricing). A free trial does not use the offer up: it applies to your first payment whether you add a card during the trial or subscribe after it ended: - The discount applies automatically at checkout - Works with both monthly and yearly plans - Applies to all users in your organization - After 3 months, standard pricing resumes - Can be combined with the yearly discount shown on the [pricing page](https://intermind.com/pricing) ## Getting Started - [Managing Your Subscription](https://intermind.com/billing/manage) — Upgrade, downgrade, or cancel your plan - [Usage & Invoices](https://intermind.com/billing/usage) — Monitor usage and view invoices :: # Audio Issues ## Microphone Not Working | Symptom | Likely cause | Fix | | ----------------------------------------------- | ----------------------------------------- | ------------------------------------------------------------------------------------------------------------------- | | "Microphone access denied" prompt | Browser permission blocked | Click the lock icon in the address bar → set **Microphone** to **Allow** → reload | | Mic icon shows a red slash, no audio level | Mic is muted or wrong device selected | Click the arrow next to the microphone button in the control bar → pick the right device | | Audio level indicator stays flat when you speak | OS-level mic permission blocked | macOS: System Settings → Privacy & Security → Microphone → enable browser. Windows: Settings → Privacy → Microphone | | Mic works in other apps but not InterMIND | Another browser tab is holding the device | Close other tabs that may use the mic (Zoom Web, Google Meet, etc.) and reload | | Bluetooth headset connects but no audio | Headset is in low-quality (HFP) mode | Disconnect and reconnect the headset, or switch to wired | ## No One Can Hear You | Symptom | Likely cause | Fix | | --------------------------------------------------- | --------------------------------------------------------------- | ------------------------------------------------------------------------------------ | | Your audio level moves but others hear silence | Wrong mic device routed | Open **Settings** → **Devices** → select the correct microphone | | Others hear muffled/distant audio | Laptop's far-field mic instead of headset | Switch device in the control bar; physically move closer to the laptop if no headset | | You speak but only one participant doesn't hear you | That participant has their speaker muted or wrong output device | Ask them to check their speaker selection — not your issue | ## You Can't Hear Others | Symptom | Likely cause | Fix | | ------------------------------------------------ | ------------------------------------------------------ | ------------------------------------------------------------------------------------ | | Total silence from everyone | Browser tab muted (right-click tab → Unmute) | Unmute the browser tab | | Silence from one participant only | They are muted, or their mic is broken | Check their mic indicator in the participant list | | Translation audio playing, original voices quiet | Under translation the original stays at 20 % by design | This is expected — see [Real-Time Translation](https://intermind.com/../translation) | | Volume too low even at 100% | OS output is low or wrong output device | Check OS sound settings; switch output device | ## Echo or Feedback | Symptom | Likely cause | Fix | | ----------------------------------------- | ----------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- | | Everyone hears their own voice with delay | Someone in the room is using a speaker without a headset | The offender should mute, switch to a headset, or use the **Echo cancellation** toggle in browser audio settings | | Crackling, popping, or robotic voice | Bluetooth bandwidth saturated, or another app using the mic | Switch to wired audio; close other audio apps | ## Related - [Meeting Controls](https://intermind.com/../meetings/controls) — Mic and speaker selection during a call - [Browsers & Devices](https://intermind.com/browsers) — Required permissions and supported browsers # Video & Camera Issues ## Camera Not Detected | Symptom | Likely cause | Fix | | -------------------------------------------- | ------------------------------------------------ | ----------------------------------------------------------------------------------------------------------- | | "Camera not found" or no devices in selector | Camera blocked at OS level | macOS: System Settings → Privacy & Security → Camera → enable browser. Windows: Settings → Privacy → Camera | | Browser asks for permission every join | Permission was denied or set to "Ask every time" | Address bar → lock icon → set **Camera** to **Allow** | | External webcam not listed | Driver issue or USB hub power | Replug directly into the laptop, not through a hub; reinstall driver | | Camera works in other apps but not InterMIND | Another tab is holding the device | Close other tabs using the camera (Google Meet, Zoom Web, etc.) and reload | ## Black or Frozen Video Tile | Symptom | Likely cause | Fix | | ----------------------------------------------------------- | ----------------------------------------------- | ------------------------------------------------------------------- | | Your tile shows your avatar instead of video | Camera is off (click the camera icon to toggle) | Toggle camera back on | | Your tile is black even with camera on | Camera privacy shutter is closed | Open the physical shutter on your webcam | | Video frozen on your end, others see you fine | Local rendering issue | Reload the page (Cmd/Ctrl+R) | | Video frozen on others' end | Network bandwidth too low | See [Network & Connection](https://intermind.com/network) | | Wrong camera being used (e.g. external instead of built-in) | Default device mismatch | Click the arrow next to the camera button → select the right device | ## Video Quality Issues | Symptom | Likely cause | Fix | | ------------------------------------ | ----------------------------------------- | --------------------------------------------------------------------------------------------- | | Pixelated, low-resolution video | Bandwidth-saving auto-adjust | Move closer to your router, switch to wired; InterMIND auto-restores HD when bandwidth allows | | Lighting is too dark | Your face is back-lit (window behind you) | Add a front-facing light or sit facing a window | | Video lag (you move, video stutters) | CPU bottleneck from other apps | Close heavy apps (browser tabs with video, IDEs running builds) | ## Screen Sharing | Symptom | Likely cause | Fix | | ----------------------------------- | ---------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- | | "Screen sharing not supported" | Safari ≤16 doesn't support `getDisplayMedia()` on some platforms | Use Chrome, Edge, or update to Safari 17+ | | Black screen when sharing on macOS | Screen Recording permission not granted | System Settings → Privacy & Security → Screen Recording → enable the browser, then quit and reopen the browser | | Audio not shared when sharing a tab | Tab audio sharing requires Chrome/Edge | Switch browsers, or share window without audio and unmute the source | ## Related - [Screen Sharing & Recording](https://intermind.com/../meetings/screen-sharing) — How sharing works during a call - [Meeting Controls](https://intermind.com/../meetings/controls) — Camera selection and toggle # Translation Quality This page covers issues unique to InterMIND's real-time translation. For general translation behavior, see [Choosing Languages](https://intermind.com/../translation/languages). ## Wrong Language Detected | Symptom | Likely cause | Fix | | --------------------------------------------------- | ------------------------------------------------------------- | ----------------------------------------------------------------------------------------- | | Your speech is being detected as the wrong language | Speaking language not set or auto-detect picked the wrong one | Open the language selector in the control bar → set your **speaking language** explicitly | | Translation comes out in a language you don't want | Listening language is wrong | Click the globe icon → set your **listening language** | | Multilingual speakers cause language flipping | Auto-detect re-evaluates on each utterance | Pin your speaking language to one value; switch manually if you change languages | ![The Translate for me into picker on the join screen](https://intermind.com/img/docs/troubleshooting/join-translation-language.png) ## Translation Lag | Symptom | Likely cause | Fix | | ---------------------------------------------- | ---------------------------------------------------------------- | ----------------------------------------------------------------------------------------- | | 3+ second delay between speech and translation | Normal latency window — translation waits for utterance boundary | This is expected; speak in complete sentences for best results | | Lag growing over time during a long meeting | Network buffer accumulating, packet loss | Check the connection indicator; see [Network & Connection](https://intermind.com/network) | | Translation stops mid-sentence | Speech recognition lost the audio stream | Pause, then speak a complete sentence — the system re-anchors at utterance boundaries | ## Missing Subtitles | Symptom | Likely cause | Fix | | ----------------------------------------------------- | ---------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | | No subtitles appear at all | Subtitles toggle is off | Click the **CC** / subtitles button in the control bar | | Subtitles appear in original language, not translated | Translation is disabled, only transcription on | Enable translation via the globe icon | | Subtitles cut off after one line | Subtitles auto-clear after a few seconds | This is expected — full transcript is preserved, see [Transcription](https://intermind.com/../translation/transcription) | ## Accuracy & Word Errors | Symptom | Likely cause | Fix | | ------------------------------------------------- | ---------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Brand names, acronyms, or jargon mistranslated | The translator does not know your terms yet | Tell Mia how the term must read — «translate Atlas into French as Atlas», «never translate ACME» — and she remembers it for the whole organization (see [Glossary](https://intermind.com/../translation#glossary)); spell out acronyms on first use | | Numbers transcribed wrong (e.g. "fifteen" → "50") | Background noise or accent | Use a headset mic; reduce ambient noise | | Translation says the opposite of what was meant | Negation or context loss across utterance boundaries | Speak in complete sentences with explicit subject + verb + object | | Names of people appear translated/garbled | Names are treated as nouns by some language pairs | Repeat the name or write it in chat | ## Background Noise Breaks Translation | Symptom | Likely cause | Fix | | ------------------------------------------------------------------ | ----------------------------------------- | --------------------------------------------------------------- | | Translation works in quiet rooms but fails in cafes / open offices | Ambient noise confuses speech recognition | Use a directional headset mic; enable browser noise suppression | | Music or TV in background gets transcribed as speech | The recognizer hears it as utterances | Mute the source; use a noise-cancelling headset | | Multiple speakers overlapping → mixed translation | Two voices in the same utterance | Encourage one-speaker-at-a-time; use hand-raise | ## Related - [Choosing Languages](https://intermind.com/../translation/languages) — Supported languages and how detection works - [Live Subtitles](https://intermind.com/../translation/subtitles) — Subtitle behavior and controls - [Usage & Limits](https://intermind.com/../billing/usage) — Per-plan minute limits # Network & Connection InterMIND needs a stable connection in both directions. Most "InterMIND is broken" reports are really network issues. ## Bandwidth Requirements | Activity | Minimum | Recommended | | -------------------------------- | -------------- | -------------- | | Audio-only meeting + translation | 1 Mbps up/down | 2 Mbps up/down | | HD video meeting + translation | 2 Mbps up/down | 5 Mbps up/down | | Screen sharing | +1 Mbps up | +2 Mbps up | Run a [speed test](https://fast.com){rel=""nofollow""} to check your real bandwidth — not the rated speed of your plan. ## "Reconnecting…" Loop | Symptom | Likely cause | Fix | | ------------------------------------------- | ------------------------------------- | -------------------------------------------------------------- | | Banner keeps flickering "Reconnecting…" | Packet loss on the route | Switch from Wi-Fi to wired; move closer to the router | | Reconnects only when video is on | Bandwidth not sufficient for HD video | Turn camera off; InterMIND auto-falls-back to audio-only | | Reconnects when others share their screen | Total downstream bandwidth exceeded | Ask the sharer to lower share quality or close other downloads | | Reconnects in offices with strict firewalls | UDP / WebRTC ports blocked | See **Firewall & VPN** below | ## Choppy Audio or Video | Symptom | Likely cause | Fix | | ------------------------------- | ------------------------------------------------------ | ----------------------------------------------------------------------------------- | | Robotic / chopped voice | Packet loss > 5% | Switch to wired, close bandwidth-heavy apps (cloud sync, video calls in other tabs) | | Video freezes for a few seconds | Bandwidth spike consumed by another app | Pause Dropbox/Google Drive sync, OS updates, BitTorrent | | Audio cuts but video is fine | Audio uses different codec — packet loss on audio path | Toggle camera off and on; if it persists, switch network | | Issues only when on VPN | VPN adds latency and may rate-limit UDP | Disconnect VPN if your IT policy allows | ## Firewall, VPN, and Corporate Networks InterMIND uses WebRTC, which needs specific ports open. | Port / Protocol | Purpose | Required | | --------------- | ---------------------------- | --------------------------------------------- | | TCP 443 | Signaling, fallback media | Yes | | UDP 3478 | STUN (NAT traversal) | Recommended | | UDP 1024–65535 | Media (audio, video, screen) | Recommended; falls back to TCP 443 if blocked | If your network blocks UDP entirely, InterMIND falls back to TCP 443 — it works but quality is reduced. If you're on a managed corporate network, ask IT to allow `*.intermind.com` and these ports. ## Translation Cuts Out Mid-Sentence | Symptom | Likely cause | Fix | | ------------------------------------------------------------------ | ---------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ | | Translation stops, then resumes after a delay | Speech stream interrupted by packet loss | Check connection indicator; see [Translation Quality](https://intermind.com/translation-quality) | | Translation works at the start of the meeting, fails after 30+ min | Bandwidth degraded over time (Wi-Fi roaming, network congestion) | Reconnect on a stable network | ## Diagnostic Steps 1. Run the [WebRTC Browser Test](https://intermind.com/browser-test) — it reports latency, packet loss, and TURN reachability 2. Open browser DevTools → Network tab → check for failing requests to `*.intermind.com` 3. Try a different network (mobile hotspot) — if it works there, the office network is the issue ## Related - [Browsers & Devices](https://intermind.com/browsers) — Browser-level settings that affect connection - [Meeting Controls](https://intermind.com/../meetings/controls) — Connection indicator in the control bar # Browsers & Devices ## Supported Browsers | Browser | Minimum version | Notes | | ---------------------------------- | --------------------- | --------------------------------------------- | | **Chrome** | 90+ | Best support, full feature set | | **Edge** | 90+ | Same engine as Chrome — full feature set | | **Safari** | 15+ | Works; screen-sharing requires Safari 17+ | | **Firefox** | 100+ | Works; some codec fallbacks on older hardware | | **Opera, Brave, Arc** | Chrome 90+ equivalent | Works (built on Chromium) | | **Internet Explorer, legacy Edge** | — | Not supported | Run the [WebRTC Browser Test](https://intermind.com/browser-test) to verify your browser before joining an important meeting. ![Codec support card of the WebRTC Browser Test](https://intermind.com/img/docs/troubleshooting/browser-test-codecs.png) ## Permission Prompts | Symptom | Likely cause | Fix | | ------------------------------------- | ----------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | | Permission prompt loops on every join | Browser is set to "Ask every time" | Click the lock icon in the address bar → set **Microphone** and **Camera** to **Allow** for the InterMIND domain | | "Permission denied" with no prompt | Permission was previously denied | Same as above — change from **Block** to **Allow**, then reload | | Permissions reset every session | Browsing in Incognito / Private mode | Use a regular window, or grant permission again each session | | OS-level prompt never appeared | Browser was previously denied at OS level | macOS: System Settings → Privacy & Security → Camera/Microphone → enable browser. Windows: Settings → Privacy → Camera/Microphone | ## Safari Quirks | Symptom | Likely cause | Fix | | ----------------------------------------- | ---------------------------------------------------------- | -------------------------------------------------------- | | Audio cuts out when tab is in background | Safari throttles inactive tabs aggressively | Keep the InterMIND tab in the foreground during meetings | | Camera switches to wrong device on rejoin | Safari doesn't always honor "default device" memory | Manually select the device after joining | | Screen sharing missing | Safari ≤16 doesn't support `getDisplayMedia()` reliably | Upgrade to Safari 17+ or use Chrome/Edge for sharing | | Echo cancellation weak | Safari's audio processing is less aggressive than Chrome's | Use a headset to avoid echo | ## Mobile Browsers Mobile is supported but has limits versus desktop. | Feature | iOS Safari | Android Chrome | | ---------------------------- | ----------------------------------------------- | ------------------------------------- | | Audio + Video meetings | ✓ | ✓ | | Translation (listen + speak) | ✓ | ✓ | | Screen sharing | ✗ (iOS doesn't expose `getDisplayMedia` to web) | ✗ | | Background mode | Limited — Safari pauses inactive tabs | Limited — Chrome pauses inactive tabs | | Picture-in-picture | ✓ on iOS 15+ | ✓ | For meetings longer than 30 minutes or with screen sharing, desktop is recommended. ## Incognito / Private Mode | Issue | Cause | | ------------------------------------------------ | --------------------------------------------- | | Permissions reset each session | Private mode wipes site data on close | | Sign-in fails with "third-party cookies blocked" | Private mode blocks cookies more aggressively | | Performance worse than normal window | Less caching, more overhead | For meetings, use a regular browser window. ## Browser Extensions Some extensions break WebRTC: | Extension type | What it breaks | | --------------------------------------------------------------- | --------------------------------------------------------------------------------------------- | | Ad blockers (uBlock, AdBlock) | Usually fine; rarely block WebRTC signaling — disable for `*.intermind.com` if issues persist | | Privacy / VPN extensions (NordVPN, Ghostery) | Can block STUN/TURN — disable during meetings | | Tab managers / freezers (The Great Suspender, Auto Tab Discard) | Suspend the InterMIND tab and break the call — disable for InterMIND | | Anti-tracking extensions | Can block analytics endpoints, usually harmless | Test in an incognito window with extensions off — if it works there, an extension is the cause. ## Clearing Cache If something is stuck and nothing else works: 1. Open browser DevTools (Cmd/Ctrl+Shift+I) 2. Right-click the reload button → **Empty Cache and Hard Reload** 3. If still broken: Settings → clear site data for `intermind.com` ## Related - [Audio Issues](https://intermind.com/audio) — Mic and speaker problems - [Video & Camera Issues](https://intermind.com/video) — Camera permissions and screen sharing - [Network & Connection](https://intermind.com/network) — Bandwidth and firewall issues # In-Meeting Notices What the notices you may see during a call mean, and what to do about them. ## "This meeting is open in another tab" You rejoined the same meeting in another tab or window of the same browser, so this one was disconnected — a meeting runs in one tab at a time per device. Click **Return here** to continue in this tab (which disconnects the other one), or just switch to the newer tab. Joining from a **second device** is different and works normally — you appear as a separate participant. ## "Transcript unavailable" Shown once right after joining when the transcription service could not attach to this call. The meeting itself is unaffected — audio, video, live translation, subtitles, chat, and screen sharing all keep working — but the saved transcript and the AI recap won't be produced **for this call**. ## "Translation limit reached" Translation minutes are drawn from the **host's** plan, and the state is the same for everyone in the room. When the host's monthly limit runs out: - a **"Translation limit reached"** badge appears in the control bar; its tooltip explains that translation is paused until the limit resets or the plan is upgraded - the translation toggle and language picker in the **More** menu are disabled - a translation session already running in this meeting keeps going; what's blocked is turning translation on, changing language, and translation in new meetings The notice includes when the next free allowance becomes available, when known. See [Billing & Plans](https://intermind.com/../billing) for the limits per plan. ## "Meeting ending soon" / time limit reached On the Basic plan, meetings are capped at **1 hour**. A warning appears **5 minutes** before the cap; at the cap the meeting ends for all participants automatically. The host then sees a **60-second countdown** before the same link can be rejoined — or can upgrade to remove the cap entirely. Other participants can rejoin as soon as the host restarts the meeting. ## Related - [Meeting Controls](https://intermind.com/../meetings/controls) - [Network Issues](https://intermind.com/network) - [Billing & Plans](https://intermind.com/../billing) # Troubleshooting Most issues fall into one of six categories. Each page lists symptoms, the likely cause, and the fix. ## Where to Start | If you're seeing… | Open | | ----------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- | | No one hears you, or you can't hear others | [Audio Issues](https://intermind.com/troubleshooting/audio) | | Your camera is black, frozen, or not detected | [Video & Camera Issues](https://intermind.com/troubleshooting/video) | | Wrong language, lag, missing subtitles, mistranslation | [Translation Quality](https://intermind.com/troubleshooting/translation-quality) | | "Reconnecting…", choppy stream, dropouts | [Network & Connection](https://intermind.com/troubleshooting/network) | | InterMIND won't start, permission prompt loops, mobile issues | [Browsers & Devices](https://intermind.com/troubleshooting/browsers) | | An in-call banner: "open in another tab", "Transcript unavailable", "Translation limit reached", time limit | [In-Meeting Notices](https://intermind.com/troubleshooting/meeting-states) | ## First Step: Run the Browser Test Before deep-diving, the [WebRTC Browser Test](https://intermind.com/browser-test) checks your microphone, camera, network, and codec support in 30 seconds. If it fails, the issue is local — fix that first. ::callout{type="tip"} The browser test report tells you exactly which subsystem failed (mic permission, camera permission, STUN/TURN reachability, codec support). Most "InterMIND doesn't work" tickets resolve here. :: ## Still Stuck? If none of the pages here match what you're seeing, [contact support](mailto\:support@intermind.com) with: - The exact symptom (one sentence) - Browser name + version - Operating system - A screenshot of the [browser test](https://intermind.com/browser-test) result # Security & Privacy This page describes how InterMIND handles your data in plain terms. For legal language, see the [Privacy Policy](https://intermind.com/privacy) and [Terms of Service](https://intermind.com/terms); for the buyer-facing summary with the GDPR audit and DPA links, see the [Privacy & Security feature page](https://intermind.com/features/security). ## Encryption **In transit.** All connections to InterMIND go over **HTTPS / WSS** (TLS). HTTP requests are redirected to HTTPS automatically — there is no plaintext fallback. This covers the web app, the WebSocket server that carries chat and signaling, and our own calls to the translation engine. Meeting audio and video travel over **WebRTC with DTLS-SRTP** between your browser and the media server of our own engine in France; the media server decrypts each stream to forward it to the other participants and to the speech-recognition and translation pipeline. **At rest.** The database (Neon, Frankfurt) encrypts its storage with AES-256; recordings, attachments and export archives on Tigris object storage are covered by server-side encryption that is always on. OAuth integration tokens and OIDC client secrets are additionally encrypted at the application level (AES-256-GCM) before they are written, and OIDC session tokens are stored encrypted in the session cache. Vendor statements: [Neon security overview](https://neon.com/docs/security/security-overview){rel=""nofollow""}, [Tigris S3 API](https://www.tigrisdata.com/docs/api/s3/){rel=""nofollow""}. **End-to-end encryption: no.** Translation is processing — speech recognition and translation run on our own engine, on our own servers in Germany and France, and that engine has to read the content to translate it. InterMIND is therefore transport-encrypted and encrypted at rest, and the content is readable by our infrastructure at the point of processing; it is not end-to-end encrypted, and no plan or setting changes that. What we offer instead is a verifiable data path: EU at every hop, our own engine for live speech rather than a third-party model, AI features on the gateway your organization selects (our own tenant, no training on your data), and retention you control. Voice notes are transcribed by Azure AI Speech in that same tenant. If end-to-end encryption outranks everything else for you, products built around it — Element, Wire, Threema — are the better fit, and none of them documents translation; we say the same in our [messenger comparison](https://intermind.com/blog/dsgvo-messenger-unternehmen). ## Authentication | Method | Status | | --------------------------------------------------------------------------------------- | ------------------------------------------ | | **Email + verification code** | Available | | **Sign in with Google** (OAuth 2.0) | Available | | **Sign in with Microsoft** (OAuth 2.0) | Available | | **SSO** (Google / Microsoft, automatic team join by verified domain) | Available on Business and Enterprise plans | | **Enterprise SSO via your own IdP** (OIDC — Okta, Microsoft Entra ID, Google Workspace) | Available on Business and Enterprise plans | Passwords are never stored — sign-in is either a one-time verification code or an OAuth flow with Google / Microsoft. Sessions are kept in HTTP-only cookies; you can sign out from the profile menu at any time. Enterprise SSO uses OpenID Connect Authorization Code with **PKCE (S256)**, **state**, and **nonce**. ID tokens are validated against the IdP's published **JWKS** (signature, issuer, audience), and a sign-in is accepted only for email domains the team has **verified via DNS** — your IdP is authoritative only for domains you have proven to own. OIDC client secrets are encrypted at rest, and every SSO sign-in is recorded in the [team audit log](https://intermind.com/docs/users/audit-log). Setup: [SSO Setup](https://intermind.com/docs/integrations/sso-setup). ## Real-Time Translation Real-time voice and subtitle translation runs on **InterMIND's own infrastructure** — speech audio is processed on our private WebSocket service, not sent to a public OpenAI / Google Translate / Azure endpoint. Document translation (PDF, DOCX, DOC, PPTX, XLSX) uses **DeepL** as the translation provider. Files are uploaded to DeepL over a TLS connection for translation and the result is returned to your meeting chat. DeepL's data handling is governed by [DeepL's own privacy terms](https://www.deepl.com/en/privacy/){rel=""nofollow""} — they do not retain content for training. ## AI Features Meeting recaps, document summaries, the writing assistant, Ask AI and Mia (the AI participant you can address by name in a meeting) run on a **language-model gateway of a hyperscaler, in InterMIND's own tenant** — the same gateway your organization most likely already uses for its own AI: :preview-mark{slug="mia-in-meetings"} | Gateway | Region | Status | | ----------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | | **Azure OpenAI** (Microsoft) | EU Data Zone — processing and storage inside EU member states | Default | | **Google Vertex AI** (Google Cloud) | EU multi-region endpoint | Available — organization admins pick it in Settings | | **Amazon Bedrock** (AWS) | EU (Frankfurt) or any region you choose, in **your own AWS account** — you add an IAM access key with Bedrock invoke rights; the models, quotas and Marketplace agreement stay yours | Available — organization admins enter their AWS account in Settings | | **Your own endpoint** | Wherever you run it | Available — any OpenAI-compatible server (for example vLLM in your data centre or a deployment in your own tenant) | An organization admin chooses the gateway on the Integrations page; the choice applies to every AI feature of the organization at once, and **AI features can be switched off for the whole organization** — transcription and translation keep working. What leaves InterMIND for an AI call is the meeting transcript and the chat window at meeting end, the shared documents, the editor text or the question asked; all gateways are configured with zero data retention and no training on your content. Mia's voice is synthesized by the same vendor as the gateway (Azure AI Speech, Google Cloud Text-to-Speech, EU regions); with your own endpoint Mia answers in text. ## Recordings and Transcripts | Data | Storage | Retention | | ------------------ | ------------------------------------------ | --------------------------------------------------------------------------- | | Meeting recordings | S3-compatible object storage | Stored until you delete them | | Transcripts | Linked to the recording / meeting | Same as the recording | | Chat messages | Database, linked to the meeting or channel | Until you delete them, or — for ad-hoc meetings — purged when the call ends | You control retention: your content stays available for as long as your account or team workspace is active, and you can delete any recording, channel, or message at any time. Deleting your account permanently erases all associated content across our database and storage. We do not impose an automatic expiry — you decide how long your content is kept. See our [Privacy Policy](https://intermind.com/privacy) for the full retention statement. ## Where Your Data Lives InterMIND's primary application region is **Paris (CDG, France)** on Fly.io; the database lives in **Frankfurt, Germany**. Recordings and files are kept on S3-compatible storage pinned to **EU regions (Frankfurt / Amsterdam)**. There is currently no per-customer region pinning. ## What Other Parties See | Party | What they see | | ------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **InterMIND** | Meeting metadata, chat content, recordings (until you delete them), transcripts, your account info | | **DeepL** | Only the contents of documents you ask to translate, on a per-file basis | | **Microsoft** (Azure OpenAI, Azure AI Speech — the default AI gateway) | The meeting transcript and chat window at meeting end, shared documents, editor text and Ask AI questions, for the AI features above; Mia's answers for text-to-speech; the audio of a voice note recorded in a channel, for speech-to-text — EU Data Zone, zero data retention, never used for training | | **Google** (Vertex AI, Cloud Text-to-Speech — only for organizations that selected this gateway) | The same content as above, on Google's EU endpoints — zero data retention, never used for training | | **Google / Microsoft** (if you sign in with them) | Your name, email, profile photo — standard OAuth scopes only | | **Stripe** (if you pay) | Billing details (card, address) — InterMIND never sees the raw card number | | **Sentry, PostHog** (error & analytics) | Anonymous usage events and crash traces; meeting content is never sent | ## What InterMIND Does Not Do - **No model training on your data.** Conversations, documents, and recordings are not used to train any AI model. - **No selling or sharing.** Your data is not sold or shared with advertisers. - **No third-party tracking inside meetings.** No tracking pixels, no ad SDKs in the meeting room. ## Deleting Your Data | To delete | How | | ------------------------- | ------------------------------------------------------------------------------------------------------------ | | A single recording | Open the meeting → Recordings → delete | | A standalone chat history | Open the channel → Delete Channel Permanently (removes the channel and all its messages, files, and history) | | Your entire account | Profile → Settings → Delete account, or contact | Account deletion removes your profile, meetings, recordings, transcripts, and chat history. Backups may take up to 30 days to age out. ## Reporting a Security Issue If you believe you have found a security vulnerability in InterMIND, we want to hear about it. **How to reach us.** Email with a short description of the issue and enough detail to reproduce it (steps, affected URL, screenshots or a proof of concept). Encrypted email is fine if you prefer. A machine-readable contact is also published at [`/.well-known/security.txt`](https://intermind.com/.well-known/security.txt) (RFC 9116). **What to expect.** We aim to acknowledge a report within **3 business days** and to keep you updated as we investigate and fix. When a report leads to a fix, we are happy to credit you by name if you would like acknowledgement. **What we ask.** Please practice responsible disclosure: report the issue to us privately first and give us reasonable time to fix it before any public discussion. Do not access, modify, download, or retain data belonging to other users or accounts beyond the minimum needed to demonstrate the issue, do not degrade or disrupt the service, and delete any data or screenshots captured during testing once the report is closed. **Scope.** In scope: `intermind.com` and its APIs, the InterMIND web, mobile, and desktop applications, and our WebSocket service. Out of scope: findings that require physical access to a user's device, social engineering of our staff or users, volumetric denial-of-service, and reports from automated scanners without a demonstrated, exploitable impact. **Rewards.** We do not run a paid bug-bounty program at this time, so we are not able to offer monetary rewards. We do genuinely value good-faith reports and will acknowledge them. **Safe harbor.** We will not pursue or support legal action against researchers who act in good faith, follow this policy, and avoid privacy violations, data destruction, and service disruption. If in doubt about whether an action is authorized, ask us first at . ## Related - [Privacy Policy](https://intermind.com/privacy) — Legal text - [Subprocessors](https://intermind.com/legal/subprocessors) — Providers we use and where they process data - [Terms of Service](https://intermind.com/terms) — Legal text - [Billing & Plans](https://intermind.com/docs/billing) — Plan-level data handling differences # Methodology The InterMIND translation quality benchmark is produced automatically by our own test suite: a weekly synthetic run drives the same translation pipeline that powers the public [/demo](https://intermind.com/demo) over a fixed reference set, the same way for every language pair. It is synthetic and reproducible — nothing here is curated or cherry-picked, and there is no human in the scoring loop. ## How a single test works A test run plays a reference audio file (voice test) or sends a reference text (chat test) from a source language through our live translation pipeline to a target language. The resulting translation is scored 0–100 by an LLM judge against a canonical reference translation. LLM judge: `google/gemini-3.8-flash` primary, `anthropic/claude-sonnet-5` fallback (via Vercel AI Gateway). The same prompt, rubric, and reference texts are used across all pairs. ## How a month is aggregated 1. Every completed full benchmark run is recorded in `demo_test_runs` with per-target-language scores. Single-pair previews are excluded — only full multi-language runs feed the medians. 2. For each (source language, target language, test type, week) we keep the *latest* run, then aggregate by month — so a single source cannot swing medians by repeating a pair within a week. 3. From the deduplicated set we compute median, min, max, p10, p90, average, and sample size. 4. We snapshot individual scores so that once a month closes, the numbers remain stable even after raw runs are deleted by TTL. ## When a pair appears in the public index A (pair × test type × month) row is eligible for the public index and sitemap when it clears a minimum sample size and a median-score floor (a lower floor for voice, which carries unavoidable ASR noise). Because the dataset comes from a single automated source rather than many independent visitors, the unique-source requirement is relaxed for this synthetic data — the sample-size and quality floors still apply. Pairs that fall short remain accessible by direct link — the thresholds gate only what search engines see. We do not hide low scores from anyone who asks for them directly. ## What we deliberately do NOT claim - A single score is not trustworthy. A well-behaved pair can swing 30 points between runs because ASR and LLM judgment are both noisy. That is why every page shows a distribution, not a single number. - The LLM judge itself is imperfect. We may switch or dual-judge in the future; historical rows will carry the judge identifier when that happens. - The benchmark does not measure latency, cost, availability, or user satisfaction. Those live elsewhere. - The dataset is synthetic — produced by our own automated suite, not by independent third-party traffic. We disclose this explicitly rather than imply an external panel. ## Honest calls When a month drops in quality for a specific pair — it stays visible. When a bug is fixed and the next month jumps — the improvement is visible on the same page. We never rewrite historical aggregates. Admins can only hide individual months from the public index; they cannot alter the numbers that were already published. ## Known issues affecting historical data - **Chat test harness, before 2026-04-23:** the automated chat-test pipeline had per-language failures. Chat aggregates from earlier months may show lower scores than the actual translation quality of those periods. Affected months are kept in the database but suppressed from the public index; the trend chart will show a step change at the fix. ## Questions Disagree with something here? Open an issue or write to us. We will update this page and note the change. # Forward Deployed Engineer — make InterMIND work inside the customer's company Dubai, UAE · full-time · on site with customers across the UAE and the Gulf · up to USD 100,000 a year ## About the product InterMIND is a communication space for teams that work across languages: meetings, chat, documents and recaps, each participant seeing and hearing everything in the language they think in. Web, iOS and Android, desktop. Around the room sits everything a company needs to adopt it: single sign-on and directory sync, roles and an audit log, a public API, a connector for AI assistants over MCP, a Slack app, calendar sync, email-in, data export — and the organization's own AI brain: every AI feature of an account runs on the model endpoint that account chooses, ours in the EU or the customer's own cloud tenant or server. ## Why this role exists A product is adopted when it works inside the customer's processes, not when it passes a demo. Between the two there is always engineering nobody planned for: an identity provider configured in a way the documentation never met, a CRM that has to receive every recap, a security team that wants the AI to run in their own tenant, a workflow that needs a feature we do not have yet. We are a small self-funded team, and our first large deployments are ahead of us, not behind. You would be the first engineer in this role: the person a customer's team knows by name, and the person who decides what "deployed" means here. ## What you will do - **Deploy.** Take an account from a signed agreement to daily use: single sign-on and directory, roles, calendars, the Slack app, the account's AI brain on the customer's endpoint — in their environment, with their IT and security people, on site. - **Build what is missing.** Integrations over our API and MCP connector, migration scripts, and — when the gap is in the product itself — the feature, in our codebase, through the same tests and review as any other change. The customer's case is the specification. - **Talk to the customer yourself.** Discovery, scoping, the weekly call, the uncomfortable conversation when something slipped. No account manager stands between you and them. - **Bring the field back.** What you had to work around at one customer becomes product for the next: a setting, a document, a fix, a feature. A workaround that stays a workaround is unfinished work. - **Work before the contract too.** A technical pilot with a prospect's real environment is often what closes the deal. ## Who fits - **An engineer first.** Several years of shipping production software; comfortable across a TypeScript web stack, REST APIs, webhooks, OAuth/OIDC and SAML, a cloud console or three. You read an unfamiliar codebase and change it the same week. - **Fluent with AI tooling.** Most of our code is written with AI agents under engineering discipline — tests, mutation checks, review. You already work this way or want to. - **Good in the room.** You can explain a trade-off to a CIO and debug a proxy with a network admin on the same afternoon, and both trust you afterwards. - **An owner.** You would rather finish one deployment completely than start three. You say "this will not work, here is what will" early. - **Languages.** English good enough for precise writing and hard conversations. Arabic or any other language of the region is a strong plus. - **Here.** Based in Dubai or ready to relocate; most of the work happens at the customer's office, in the UAE and across the Gulf. ## What we offer - Up to USD 100,000 a year, depending on experience. There is no personal income tax in the UAE. - A role with no layers: you work directly with the founders and the customer's decision makers, and what you learn in the field changes the product within days. - The first seat in a function you will shape: its methods, its tooling and, as customers arrive, its team. ## How we hire 1. **A conversation** — held in InterMIND, about deployments you carried and what went wrong in them. 2. **A paid trial task** — a small, real piece of deployment work against a sandbox organization: an integration built over our API, documented the way you would hand it to a customer. 3. **An offer.** ## Apply Send a short note about yourself, one deployment you carried from kickoff to daily use at a customer, and the hardest thing that stood in its way. # Partner sales — 50% of everything your accounts pay Remote · independent-contractor agreement · commission-based · guaranteed minimum for the first three months ## The short version You find companies that should be selling and deploying InterMIND — language service providers, IT/AV integrators, resellers — introduce them to us, and stay their point of contact. We negotiate and sign every partner agreement directly. You earn **50% of everything your partner accounts actually pay us**, for as long as you run the relationship, plus a fixed signing bonus per partner when their first payment arrives. Your first three months carry a guaranteed monthly minimum — an advance against future commission that you never repay in cash if commission comes slower. No cap, no quota, no activity reports. The flip side is symmetrical: everything you earn beyond the first-quarter minimum is tied to money we actually receive, and two consecutive quarters with no signed partner and no partner revenue end the agreement by themselves. ## About the product For teams that work across languages, InterMIND is a communication space that outlives the call: meetings, chat, documents, recaps, and their full history — each in every participant's own language. The host provides it for everyone — not for one meeting, but for good. Guests join by link with no signup; customers choose the jurisdiction their data lives in; translation quality is publicly measured at [intermind.com/benchmark](https://intermind.com/benchmark){rel=""nofollow""}; independent reviews are on [G2](https://www.g2.com/products/intermind/reviews){rel=""nofollow""}. What you would actually be selling is the [partner program](https://intermind.com/partners) — its tracks, margins and mechanics are public, and that page is your pitch surface. ## What you will do - Build your own pipeline of prospective partners from your network and your outreach — we assign no territories and no lists. - Make the introduction, run the early conversations, bring the deal to a term sheet. The company negotiates the final agreement and signs it; you have no authority to sign or accept payments — which is also what keeps the role free of legal ceremony on your side. - Stay the account's point of contact after signature: the partner grows, renews and expands with you, and your commission runs for as long as you support the account. ## How the money works - **50% commission** on every amount we actually receive from your accounts under their partner agreements — for as long as the account is yours. - **Signing bonus** — a fixed amount per partner agreement signed, paid when the partner's first payment arrives. - **First-quarter draw** — a guaranteed monthly minimum for your first three months, offset against your commission and never repayable in cash. - **Quarterly settlement** with a one-page statement per account: invoices issued, amounts received, commission calculated. No reports to write, no calls to attend. - **Money received, not money promised.** Unpaid, disputed or refunded partner invoices carry no commission. ## How it ends Honestly and by itself. Two consecutive calendar quarters with no partner agreement signed and no money received from your accounts, and the agreement terminates automatically. Either side can also end it with 30 days' notice. Whatever the cause, commission keeps accruing on your former accounts' payments for a settlement tail after the end date — nothing already earned is lost. ## Who fits - **A network.** You already know the people who would become partners: translation and language service companies, AV/IT integrators, resellers and MSPs — from working in or selling to that industry. - **B2B sales experience.** You have carried deals from a cold conversation to a signed agreement, and you can explain a product you believe in without a script. - **Languages.** English good enough for term-sheet conversations; more languages are a real advantage — the market is multilingual by definition. - **Independent.** This is a commercial contract with our UAE operating company (we are physically in Dubai), not employment: you invoice us, you own your taxes, you work from wherever you are. ## How we engage 1. **A short note** — see below. We reply with a yes or a no. 2. **Conversations** — we walk you through the partner program mechanics and the agreement text in full before you commit. The terms on this page are the terms; the exact amounts are in the agreement. 3. **Contract** — the introducer agreement, and your first accounts are whoever you bring. ## Apply Send who you are, the industry your network is in, and the two or three companies you would introduce first — names optional, categories enough. Skip the pitch deck. # QA Engineer — exploratory testing beyond automation Remote · part-time · contract · overlapping with 09:00–15:00 Dubai time (UTC+4) ## About the product InterMIND is a communication space for teams that work across languages: meetings, chat, documents and recaps, each participant seeing and hearing everything in the language they think in. Web, iOS and Android, desktop; several participants with roles (host, member, guest); 17 interface languages; live voice translation, translated chat, document translation. Real-time media over WebRTC, a translation engine in the path, and every one of those things running on whatever device and network the participant happens to have. ## What automation already covers — and what it cannot We run unit, integration, end-to-end and multi-actor chaos suites on every push, and an AI reads production errors every morning. Simple, deterministic paths are covered; we do not need a person to click through them. What no script covers, and what this role owns: - **Many devices, real networks.** Laptop plus two phones, Bluetooth headset switching mid-call, Wi-Fi → LTE hand-over, a captive portal, a corporate proxy, the app backgrounded during a call, a tab throttled by the OS. - **Perceived quality.** Is the translated voice intelligible, is its timing usable in a real conversation, does the meaning survive — names, numbers, negations, idioms, two people speaking at once? Is audio clean after a reconnect? Only a person can judge this, and it needs a rubric, not a feeling. - **Exotic paths.** Role changes mid-call, a guest and a member with the same name, screen share plus laser pointer plus chat translation at once, RTL and CJK interface languages, a calendar-created meeting joined from the wrong account, a recap read in a language nobody in the call spoke. - **Reasoning about cause.** Not "it broke" but "it broke on the second device only after the host muted — here is the replay, here is the console, here is what I think is happening". ## What you will do - Explore the product from short charters we give you (an area, a hypothesis, a device set). You decide how to break it and where to look next. - Report what you find through the product's own **Give Feedback** — it captures the screen, the console, the browser and the session replay for you; you add the recording, what you did and what you saw. No forms, no spreadsheets. - Write short quality assessments where a bug report is the wrong shape: translation adequacy on real speech, audio after network events, the usability of the translated voice — scored against a rubric, with examples. - Re-check fixes when asked, and tell us when a fix changed something else. ## Who fits - **Technical.** You read a console and a network tab, you know what ICE, codecs and packet loss are or can learn them in a day, you can drive a phone over `adb`, throttle a connection, switch audio devices and say precisely which build you were on. - **Creative.** You look for the paths nobody wrote down. Filling in the same checklist every day is not this job. - **Experienced.** Several years of testing real-time, media or multi-user products count for a lot here — you already know where such systems break. Experience matters as much as the trial itself. - **Languages.** English good enough for precise reports; at least one more language you speak natively or near-natively, because translation quality is judged by ear. - Reliable availability at agreed hours. ## How we hire 1. **A paid one-week trial** — [the task is public](https://intermind.com/careers/InterMIND-QA-Trial-Week.pdf): three charters on exactly the hard areas above, reported through the product. Evaluated on how much of what you found we can confirm, and on the quality of your judgment where confirmation is not the point. 2. **Contract** if the trial goes well: hourly, remote, an agreed weekly schedule. ## What you need A laptop with a webcam and a headset, at least one smartphone (two — one Android, one iOS — is a plus), a Bluetooth headset, and a network you can deliberately make bad. ## Apply Send a short note about yourself, the real-time or media product you tested most recently, and one bug you found in it that a script could not have. # Trial week — exploratory testing beyond automation Five working days, paid at the agreed rate after the review regardless of outcome. Dates, amount and accounts come in the invitation e-mail; everything else is here. ## Access - The product: [intermind.com](https://intermind.com){rel=""nofollow""}, the iOS and Android apps ("InterMIND"), the desktop app from [intermind.com/downloads](https://intermind.com/downloads){rel=""nofollow""}. - Two test accounts, sent separately: **host** and **second participant**. Everything you report is attributed to the host account, so submit from it. Do not use personal accounts. - Questions: the contact in your invitation. Ask; do not guess. ## How to report Use the product's own **Give Feedback** (in the app sidebar and on the meeting page). It attaches the current page, your browser and OS, the console, a session replay and the screenshots you paste; you can record the screen from it too. That is the report — there is no other form. What you add in the text field is what the capture cannot know: - what you did, step by step, from a fresh start, on which device; - what you expected and what you saw; - how many times you tried and how many times it happened (`3/3`, `1/5`); - for anything involving voice or translation: what was said, in which language, and what came out — and a recording with audio. Mobile and desktop findings are reported the same way from the web app on your laptop, with the device and build named in the first line (`Android 15 / app 2.14.0:`). Voice and translation evidence must carry audio; a silent screenshot of a caption is not evidence. One finding per report. Search your own earlier reports before filing; the same defect under new wording counts against you, not for you. ## Quality assessments Some of what you will judge is not a bug and must not be filed as one. Use Give Feedback with the first line `QUALITY: — ` and score against this rubric, with at least three concrete examples each: | Dimension | 1 | 3 | 5 | | ---------- | ----------------------------------------- | ----------------------------- | ---------------------------------------- | | Adequacy | meaning lost or inverted | meaning kept, details dropped | names, numbers, negations, intent intact | | Fluency | unusable output | understandable, unnatural | reads/sounds native | | Timing | translation arrives after the reply would | usable with pauses | conversational | | Robustness | breaks on overlap, noise, reconnect | degrades, recovers | stable through events | A score without examples is not an assessment. ## Charters Roughly a day and a half each, in this order; the rest of the week is yours to follow whatever you found. ### Charter 1 — Two devices, bad networks, real headsets Host on a laptop, second participant on a phone; then a third seat on the second phone or a second browser. Explore what happens to audio, video, translation and the participant list when: Wi-Fi drops to LTE mid-call; the connection is throttled to 3G-like and back; the phone app goes to background for two minutes and returns; a Bluetooth headset connects and disconnects during speech; the laptop tab is hidden for ten minutes; the host reloads while the guest is speaking. Judge audio after each recovery, not just whether the call survives. ### Charter 2 — Live translation on real speech Host speaks English; the participant speaks a language you know natively (choose it in the picker). Twenty-to-thirty-second turns, natural speech: names, numbers, dates, a negation, an idiom, a sentence changed halfway. Then overlap on purpose, then a noisy room, then a code-switched sentence. Compare voice, chat and — after the call — the recap. Deliverable: a QUALITY assessment for the pair in both directions plus bug reports for anything that is a defect rather than a quality level. ### Charter 3 — Paths nobody scripted Pick at least four: role changes mid-call (member ↔ host, guest approval mid-sentence); two participants with the same display name; screen share with the laser pointer while chat translation runs; the interface in Arabic (RTL) or Japanese while translating a third language; a meeting created from the calendar and joined by an account that was not invited; a document translated during the call and opened by the participant in their language; the desktop app and the web app in the same meeting from the same account. Find the one that breaks and take it apart. ## How the week is evaluated - **Confirmation rate** — the share of your bug reports we can reproduce from your description plus the capture. Reports the capture cannot support (no steps, no recording where audio mattered) do not count. - **Judgment** — whether severity is sensible, whether QUALITY assessments carry examples we can verify against the recording, whether you separated "quality level" from "defect". - **Depth** — how many findings came from the hard areas above rather than from the surface, and whether at least one report reasons about cause. - **Signal** — duplicates and reports written from assumption rather than observation end the trial. Quantity is not a criterion. Six confirmed findings from Charter 1 and a QUALITY assessment we can check beat thirty cosmetic tickets. The evaluation runs automatically from what you submitted, on the day after the trial ends; you receive the outcome and a short written review within a few days. # Company InterMIND (intermind.com and the InterMIND apps) is operated by one company and published by another. This page lists both with the identifiers a bank, payment provider, app store, marketplace or partner needs to verify us, and links straight into the official government registries. It states the same facts as our [Terms of Service](https://intermind.com/terms) and [Privacy Policy](https://intermind.com/privacy); if anything differs, those documents govern. ## Golden Fish LLC — service operator and contracting entity | | | | ------------------------- | ------------------------------------------------------------------------------------------------------------------------ | | Legal name | Golden Fish Computer Systems & Communication Equipment Software Design L.L.C | | Short name | Golden Fish LLC | | Jurisdiction | Dubai, United Arab Emirates (mainland company) | | Licensing authority | Dubai Department of Economy and Tourism (DET) | | Commercial licence | 1414192 (valid until 12 September 2027) | | Commercial register | 2920093 | | Dubai Chamber of Commerce | 561891 | | Licensed activities | Computer Systems & Communication Equipment Software Design · IT Network Services · Cloud Service & Datacenters Providers | | Address | City Avenue Building, Office 405-070, Port Saeed, Dubai, United Arab Emirates | | Role | Operates the Service; your contracting party under the Terms; data controller under the Privacy Policy | **Official record.** The UAE has no public register with a permanent page per company, so verification goes through DET, the licensing authority: - [DET certified licence e-document](https://eservices.dubaided.gov.ae/rt/1097891230.3){rel=""nofollow""} — the DET page the licence's QR code resolves to: licence number, commercial register number, activities, owner and manager. Opens in a normal browser. - [Invest in Dubai licence search](https://app.invest.dubai.ae/search-license){rel=""nofollow""} — the DET public search; enter licence number 1414192. ## MindMeeting OÜ — publisher and intellectual property owner | | | | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Legal name | MindMeeting OÜ | | Jurisdiction | Tallinn, Estonia (European Union) | | Registry code | 16207677 | | VAT number | EE102465446 | | D-U-N-S number | 402477726 | | Address | Juhkentali tn 8, 10132 Tallinn, Estonia | | Role | Owns the InterMIND software and brand; publishes the InterMIND mobile apps on the App Store, Google Play, Huawei AppGallery and Samsung Galaxy Store on behalf of, and under licence from, Golden Fish LLC; EU representative under Article 27 GDPR | **Official record.** [Estonian e-Business Register (ariregister) — company 16207677](https://ariregister.rik.ee/eng/company/16207677){rel=""nofollow""}. The D-U-N-S number can be checked in the [D\&B D-U-N-S lookup](https://dunsnumberlookup.dnb.com/et-ee){rel=""nofollow""}. ## How the two relate Golden Fish LLC operates the Service, signs every customer, partner and enterprise agreement, and bills you. MindMeeting OÜ holds the intellectual property and publishes the apps; it is not your contracting party. The product lives at intermind.com; the corporate site is mind.com. Both domains are operated by the companies above, and e-mail addresses on either domain reach the same team. ## Contact - Legal and data protection: - Support and verification requests: - Postal address: Golden Fish Computer Systems & Communication Equipment Software Design L.L.C, City Avenue Building, Office 405-070, Port Saeed, Dubai, United Arab Emirates # Data Processing Addendum When your organization uses InterMIND under its own agreement with us, your organization is the **data controller** and we process personal data on its behalf as the **data processor**. For that relationship we make a Data Processing Addendum (DPA) available. This page explains what the DPA covers and how to get a signed copy. It is a summary — the DPA itself is the binding document. ## Parties - **Processor (Service Operator and Contracting Entity):** Golden Fish LLC (UAE), operating InterMIND. **Publisher and Intellectual Property Owner of the Service:** MindMeeting OÜ (Estonia). - **Controller:** your organization. - **EU/EEA representative (Article 27 GDPR):** MindMeeting OÜ, Juhkentali 8, Tallinn 10132, Estonia, acts as our representative in the European Union under Article 27 GDPR. Contact: . ## What the DPA covers The DPA governs the personal data we process to provide the Service on your behalf: - **Subject matter and duration:** provision of the InterMIND meeting and translation service for the term of your agreement with us. - **Nature and purpose:** hosting and transmission of meetings (audio and video), realtime speech transcription and translation, chat, document translation, an optional post-meeting AI summary, optional team status pages (facts derived from the recaps, see below), billing, and support. - **Categories of data subjects:** your users and their meeting guests, including external invitees. - **Categories of personal data:** account data (email, name, photo), meeting metadata, speech transcriptions (including speaker names), chat messages and attachments, recordings, facts derived from recaps for team status pages (with a verbatim quote, names as spoken in the meeting, and the mapping of an assignee name to a member account), and billing data. The Service does not require special categories of data; meeting content may incidentally contain anything participants choose to discuss. ### Processing activity: Team status pages Runs for your organization on the plans that include it; choosing such a plan under the [Terms of Service](https://intermind.com/terms) («Team status pages») is your documented instruction to process recaps this way, and moving to a plan without it is the instruction to stop. - **Purpose:** tracking the state of your organization's own work — open tasks, problems, requests, decisions and money at stake — for your members and through the AI assistants they connect. Pages evaluate work, not people: no rating, ranking or scoring of individuals. - **Data:** the content of each meeting recap (read once per recap version), the facts derived from it with a verbatim quote verified against the recap, names of people as spoken in the meeting, the mapping of an assignee name to a member account, and the goals your administrator writes. - **Sub-processors:** only the AI brain your organization has already selected for recaps — Azure OpenAI in the EU Data Zone by default, Vertex AI or Amazon Bedrock by choice, or an endpoint you run yourself. No new sub-processor and no new data category beyond the recap's content. - **Access:** a member reads facts from the sessions they hosted or attended, from their join date onwards unless you open earlier history, plus rows assigned to them; administrators read the organization's pages. The same rule applies to reads through a connected assistant. - **Retention:** facts live as long as the recap they came from — deleting a session's artifacts deletes its facts, deleting the organization deletes all of them. Moving to a plan without the feature pauses extraction and hides the stored facts. ## Our commitments as processor The DPA reflects the Article 28(3) GDPR obligations, including: - We process personal data only on your documented instructions. - Our personnel are bound by confidentiality. - We apply appropriate technical and organizational security measures. - We use subprocessors under a general written authorization and give at least 30 days' prior notice of any addition or replacement, so you can object on reasonable data-protection grounds. The current list is published at [/legal/subprocessors](https://intermind.com/legal/subprocessors). - We assist with data-subject requests. Deletion and export are self-service in the product; we assist with the rest. - We notify you of a personal data breach affecting your data without undue delay and in any event within 72 hours of becoming aware of it. - On termination we delete or return your personal data, subject to backup aging. We do not currently hold SOC 2 or ISO 27001 certification. On request we provide a security questionnaire and our compliance documentation instead. ## International transfers Processing happens in the EU by default (see the [subprocessor list](https://intermind.com/legal/subprocessors) for provider regions). Where a provider's corporate entity is outside the EU/EEA, transfers are covered by Standard Contractual Clauses (SCCs) and, where applicable, the EU–US Data Privacy Framework (DPF), together with supplementary technical measures such as encryption in transit and at rest. Because InterMIND is operated from the UAE, the specific Chapter V mechanism and SCC module are confirmed per customer when the DPA is signed. ## Requesting a signed copy The DPA is signed per customer, so we adapt the international-transfer terms to your situation before signature — it is not a self-serve download. To request a copy for review or signature, email [privacy@intermind.com](mailto\:privacy@intermind.com?subject=DPA%20request) with the subject "DPA request". # Privacy Policy **Effective date: 17 June 2026** ## 1. Who we are InterMIND ("the Service") — the meeting platform with real-time speech translation available at intermind.com and through the InterMIND mobile apps — is operated by: **Golden Fish Computer Systems & Communication Equipment Software Design L.L.C** ("Golden Fish LLC", "we", "us"), City Avenue Building, Office 405-070, Port Saeed, Dubai, United Arab Emirates. For personal data processed through the Service, Golden Fish LLC acts as the data controller, except where your organization uses InterMIND under its own agreement with us — in that case your organization is the controller and we process data on its behalf (see our [Data Processing Addendum](https://intermind.com/legal/dpa)). **Publisher and Intellectual Property Owner:** MindMeeting OÜ (Estonia), Juhkentali 8, Tallinn 10132, Estonia. **Service Operator and Contracting Entity:** Golden Fish Computer Systems & Communication Equipment Software Design L.L.C (United Arab Emirates). The InterMIND mobile apps are published by MindMeeting OÜ on behalf of, and under license from, Golden Fish LLC, which operates the Service and is responsible for personal data processed through it. Registration numbers, licence details and links to the official government registries of both companies are on our [Company](https://intermind.com/legal/company) page. **Privacy contact:** **EU/EEA representative (Article 27 GDPR):** MindMeeting OÜ, Juhkentali 8, Tallinn 10132, Estonia, acts as our representative in the European Union under Article 27 GDPR. EU/EEA users and supervisory authorities may contact our representative on data-protection matters at (subject line "EU representative"). This policy covers intermind.com and the InterMIND apps only. The corporate site mind.com is operated separately and has its own policy. ## 2. What we collect and why | What | Details | Why (purpose) | Legal basis | | -------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Account data | Email, display name, profile photo, language preferences | Creating and operating your account | Contract | | Meeting audio/video | Live streams during a call — **transient, never stored** (see §3) | Running the call: transmission, speech recognition, real-time translation | Contract | | Transcriptions | Recognized and translated speech with speaker names | Live captions/translation; available to participants after the meeting until deleted | Contract | | Recordings & files | Meeting recordings you start, chat attachments, documents | Making your content available to you and participants | Contract | | AI meeting summary | Your meeting transcript is sent **once, at meeting end** to generate a digest | Post-meeting summary in the meeting chat | Legitimate interest (disclosed here) | | Document translation | Contents of documents you submit for translation | Translating the document at your request | Contract | | Team status pages | On the plans that include them (not on Basic): the content of each meeting recap (sent once per recap version to the AI brain your organization selected, §3), the facts derived from it — requests, promises, tasks, decisions, questions, problems, risks, money — each with a verbatim quote from the recap, the names of people as they were spoken in the meeting (who asked, who promised, who is assigned, which client or supplier), the mapping of an assignee name to a member account, and the goals the administrator writes; messages in team channels (not in ad-hoc meetings by link) read once against the open tasks and promises of that channel and the channels sharing a tag with it — a message that says an item is done closes it with a verbatim span of the message, shown on the page with a link to the message; a channel the pages read receives a one-time notice from Mia | Showing the organization the state of its own work — open tasks, problems, requests and money at stake — to its members and through connected AI assistants. Pages evaluate work, not people: nothing rates, ranks or scores an individual. Members see only facts from sessions they hosted or attended and rows assigned to them; administrators see the organization's pages. Facts live as long as the recap they came from (§6) | Legitimate interest of your organization as controller in tracking its own work — we process on its behalf under the [DPA](https://intermind.com/legal/dpa); the organization chooses a plan that includes the pages under the [Terms of Service](https://intermind.com/terms) (§5, «Team status pages») | | Chat messages | Message text and edit history; ad-hoc meeting chats are purged when the call ends | Messaging | Contract | | Billing data | Name, email, billing address, subscription and usage records. **Card numbers never touch our systems** — payments are handled by Stripe or, for buyers in selected countries, by Paddle, which sells the subscription as merchant of record. On plans billed per active member, each renewal counts the members active in the previous 28 days; activity is an action recorded by our servers — joining a meeting, sending a chat message, asking Mia — and a tool call made as you through a connected AI assistant counts as activity for per-active-member billing (see "Assistant activity") | Charging for paid plans; tax/accounting obligations | Contract; legal obligation | | Assistant activity | When you connect an AI assistant (Claude, ChatGPT, Copilot, Gemini or another MCP client) to your account: your account ID, the time of your last successful tool call, the tool's name and the assistant it came from, and the workspace it concerned — never the question you asked or the answer you received | Counting you as an active member of your workspace for billing, and showing your workspace administrator when you were last active | Contract | | Usage analytics | Product events, session replays, error traces. In the browser — **only after you consent via the cookie banner** (analytics is off by default). In the InterMIND apps for iPhone, Android, Windows and macOS — which screens and features you open, on by default, switched off at any time in Settings; **never the content of a meeting or chat** | Improving the product, fixing errors | Consent (browser analytics); legitimate interest (app usage statistics, error monitoring) | | Account records | The fact and time of account events recorded on our servers — registration, subscription and payment changes, API use — keyed to your account ID; no cookies and no browsing data | Counting registrations and paid conversions, measuring product use | Legitimate interest | | Service diagnostics | Technical facts about a failure, recorded on our own servers: that incoming audio stopped arriving during a call, the number of media reconnections, a failed request of a new account — numbers and identifiers only, **never the content of a conversation**; not sent to the analytics provider and not dependent on the cookie choice | Detecting and fixing failures that stop people from hearing each other or from using the Service | Legitimate interest | | Transactional email | Your email address, one-time sign-in codes, notifications | Sign-in and service notifications | Contract | | Product emails | Your email address, account age, whether you have held a meeting, and delivery status (delivered/bounced) | A few short emails after sign-up and a monthly product update; every one carries a one-click unsubscribe, and you can turn them off in Settings | Legitimate interest | | Sales inquiries | Name, email, company, message from contact/partner forms | Responding to your inquiry | Legitimate interest | | Guest exit requests | When a guest who joined a meeting by link asks the host to add them after the call: the name the guest used in the meeting, their language and the meeting it concerns, stored with that meeting for its host; the guest enters nothing, and the address the host invites them to is the host's. A guest who instead keeps the meeting by creating an account is recorded as a reader of that one session's recap | Letting the host add the guest, and giving a guest who created an account that session's recap in their language | Contract | We do not sell personal data, and we do not use your meeting content to train AI models. ### Google user data InterMIND receives data from Google APIs only when you connect a Google feature yourself, and only for that feature: - **Sign in with Google** — your email address, name and profile photo, to create and operate your account. - **Google Calendar** — events you own: InterMIND reads them to show your meetings and creates or cancels only the events it made itself. - **Google Drive** — only the files you pick in the Google file picker, linked in a meeting or chat. InterMIND shares the link, not the file: the content stays in Google Drive and is not summarized by AI. - **Google Workspace directory** — a read-only list of your organization's users, when an administrator imports them. - **InterMIND add-on for Google Workspace Studio** — reads no Google data at all; its only permission is to connect to intermind.com with the API key you paste. The use of raw or derived user data received from Google Workspace APIs adheres to the [Google API Services User Data Policy](https://developers.google.com/terms/api-services-user-data-policy){rel=""nofollow""} and the [Google Workspace API User Data and Developer Policy](https://developers.google.com/workspace/workspace-api-user-data-developer-policy){rel=""nofollow""}, including the Limited Use requirements. We do not use, transfer or sell Google user data — raw, aggregated or derived — to create, train or improve foundational or generalized AI or machine-learning models. We do not transfer Google user data to third parties except as needed to provide the feature you connected, to comply with law, or as part of a merger or acquisition with equivalent protection, and no human reads it except with your permission, for security purposes, or to comply with law. ### YouTube API Services InterMIND uses [YouTube API Services](https://developers.google.com/youtube){rel=""nofollow""} for one purpose: publishing our own product videos to our own YouTube channel and keeping their titles, descriptions, captions and playlists up to date. This runs under our own Google account, from an internal tool that is not distributed to users. It reads no data about you or any other viewer, and no data obtained through YouTube API Services is stored, shared with third parties or used for advertising. Product videos embedded on intermind.com are played by YouTube's own player in privacy-enhanced mode (youtube-nocookie.com); what YouTube collects while you watch is described in the [Google Privacy Policy](https://policies.google.com/privacy){rel=""nofollow""}, and by watching them you also agree to the [YouTube Terms of Service](https://www.youtube.com/t/terms){rel=""nofollow""}. Any Google account that has granted our tool access to a YouTube channel can revoke it at any time on the [Google security settings page](https://security.google.com/settings/security/permissions){rel=""nofollow""}. ## 3. How meetings are processed - **Audio and video streams are not stored.** They pass through our media infrastructure (hosted in Germany and France) for transmission, speech recognition, and translation, and exist only for the duration of the call. Only what is listed above — transcriptions, recordings you explicitly start, chat — is persisted. - **AI features** — meeting recaps, document summaries, the writing assistant and Ask AI — run on the AI gateway your organization selects: Azure OpenAI in the EU Data Zone (Microsoft) by default, Google Vertex AI on its EU multi-region endpoint or Amazon Bedrock in Frankfurt (AWS) by choice, each in our own tenant under the provider's data processing terms, with no training on your content; or an endpoint your organization runs itself. An organization can switch AI features off; transcription and translation keep working. - **Recording is visible to participants.** You are responsible for complying with the laws that apply to you when recording or transcribing a conversation (some jurisdictions require the consent of all participants). ## 4. Who we share data with (subprocessors) We use a small set of infrastructure and service providers. The full, versioned list — including each provider's purpose, processing region, and safeguards — is published at [/legal/subprocessors](https://intermind.com/legal/subprocessors). Headlines, verified against our infrastructure: - Application hosting, database, realtime servers, object storage, analytics, and error monitoring all run in the **EU** (Frankfurt, Paris, EU multi-region storage). - Meeting media, speech recognition, and translation run on infrastructure in **Germany and France**. - AI features (§3) run in EU regions of Microsoft, Google or Amazon Web Services, in our own tenant. - Stripe (payments), Google/Microsoft (optional OAuth sign-in), and the corporate entities of some EU-hosted providers are US-based — covered by Standard Contractual Clauses and/or the EU–US Data Privacy Framework. - Paddle (payments as merchant of record in selected countries) is UK-based — covered by the UK adequacy decision. ## 5. International transfers Processing happens in the EU by default (see §4). Where a provider's corporate entity is outside the EU/EEA, transfers are covered by Standard Contractual Clauses or an adequacy mechanism. The United Arab Emirates, where Golden Fish LLC is established, has comprehensive data-protection legislation but is not the subject of an EU adequacy decision. Where personal data is accessed from, or transferred to, a country outside the EEA — including access by us for the administration of the Service — we rely on appropriate safeguards under Chapter V GDPR (Standard Contractual Clauses and, where applicable, the EU–US Data Privacy Framework) together with supplementary technical measures such as encryption in transit and at rest and EU-pinned storage and processing. A copy of the relevant safeguards is available on request at . ## 6. Data retention We retain your content — meeting recordings, transcripts, translations, and chat messages — for as long as your account or team workspace remains active, so that it stays available to you. You control retention: you can delete individual recordings, channels, or messages at any time, and deleting your account permanently erases all associated content (across our database and storage) together with the cancellation of any active subscription. We do not impose an automatic expiry on your content; you decide how long it is kept. Some data is held only transiently for operational reasons: account-data exports are available for 7 days before deletion, anonymous guest sessions are purged within 24 hours, and one-time email verification codes are swept on expiry. A guest's request to be added to a meeting is deleted with that meeting; a guest's reader record of a session's recap is deleted with that session or meeting, or with the account. Facts derived for team status pages live as long as the recap they came from: deleting a session's artifacts deletes its facts, deleting the workspace or the account deletes all of them. Turning team status pages off pauses extraction and hides the stored facts; it does not delete them. ## 7. Your rights Depending on your jurisdiction (including under the GDPR), you have the right to access, rectify, erase, and export your data, to object to or restrict certain processing, and to withdraw consent at any time. Two of these are self-service, effective immediately: - **Erasure** — delete your account in Settings; this permanently removes your data from our database and storage and cancels any active subscription. - **Portability** — export your full account data as a ZIP archive from Settings (download link valid for 7 days). For anything else, contact . If you are in the EU/EEA, you can also lodge a complaint with your local supervisory authority. If you are in the United Arab Emirates, you have equivalent rights under the UAE Personal Data Protection Law (Federal Decree-Law No. 45 of 2021), which you may exercise through the same contact. ## 8. Cookies and analytics In the browser we use a consent management platform (Usercentrics) to ask for your consent before any non-essential cookies or analytics run. Analytics (PostHog, EU cloud) and session replay are **off by default** and start only if you opt in. You can change your choice at any time via the cookie settings link in the footer. Essential cookies (session, security) do not require consent. In the InterMIND apps for iPhone, Android, Windows and macOS there are no cookies. Usage statistics — which screens and features you open, and in the desktop app a replay of your own screens in the app, never the content of a meeting or chat — are **on by default** and can be switched off at any time in Settings; we rely on our legitimate interest in improving the product for this. Account events recorded on our servers (such as a registration or a payment) are not cookie-based and do not depend on either choice — see "Account records" in the table above. ## 9. Security TLS for all traffic (HTTPS/WSS, no plaintext fallback); encryption at rest for the database and object storage; no passwords stored (one-time email codes or OAuth only); HTTP-only session cookies; server-side role enforcement; speech text scrubbed from client-side logs; isolated per-environment databases. ## 10. Children The Service is not directed at children. You must be at least 16 years old to use the Service. If you are under the age of majority in your country (18 in the United Arab Emirates), you may use the Service only with the consent and under the supervision of a parent or legal guardian. We do not knowingly collect personal data from children below the applicable age; if you believe a child has provided us with personal data, contact and we will delete it. ## 11. Changes to this policy We will post any changes on this page and update the effective date. For material changes we will notify you in the product or by email. ## 12. Contact Golden Fish Computer Systems & Communication Equipment Software Design L.L.C — City Avenue Building, Office 405-070, Port Saeed, Dubai, United Arab Emirates. Email: # Service Level Agreement On every **paid plan** — Pro, Business, and Enterprise — we commit to a **Monthly Uptime Percentage of at least 99.5%**, backed by service credits. This page explains how uptime is measured, the credit tiers, the exclusions, and how to claim. For paid subscriptions this SLA forms part of our [Terms of Service](https://intermind.com/terms); for Enterprise customers it is also incorporated into the Enterprise agreement, and where the two differ, the signed agreement prevails. The free Basic plan is provided as described in the Terms of Service, without a service level commitment. ## The commitment - **Monthly Uptime Percentage: 99.5%**, measured per calendar month. - If we miss it, you are entitled to a service credit (see below). - Current and historical availability of every core service path is published live on [System Status](https://status.intermind.com/){rel=""nofollow""} — you can verify the commitment at any time. ## How uptime is measured **Monthly Uptime Percentage** = the percentage of minutes in the calendar month during which the Service was not Unavailable. **"Unavailable"** means the core functions of the Service — signing in, joining a meeting, meeting audio and video, or real-time translation — do not work for your users due to causes within our control. Availability is measured by our continuous synthetic monitoring, which independently probes each core service path (application and database, realtime channel, translation engine, and authentication) around the clock; the Service counts as available only when all of them are. The results of these probes are public — see [System Status](https://status.intermind.com/){rel=""nofollow""} for the current state and history of each path. Unavailability does not include degraded performance of individual features, or the accuracy of transcriptions and translations — machine translation quality is addressed in our [Terms of Service](https://intermind.com/terms), not this SLA. ## Service credits If the Monthly Uptime Percentage for a calendar month falls below the commitment, you can claim a credit against that month's fee for the affected subscription: | Monthly Uptime Percentage | Service credit | | ------------------------------ | ---------------------- | | Below 99.5%, at or above 99.0% | 10% of the monthly fee | | Below 99.0% | 25% of the monthly fee | Credits are applied to a future invoice, are capped at 30% of the affected month's fee in aggregate, cannot be exchanged for cash, and are your sole and exclusive remedy for our failure to meet the SLA. If you access the Service under a signed agreement with us that states a different credit basis — for example a partner agreement, where credits are calculated against the amounts payable to us for the affected period — that basis applies in place of the monthly fee, with the same tiers, cap, and claim process. ## Exclusions Downtime caused by the following does not count as Unavailability: - Scheduled maintenance that we announce in advance. - Factors outside our reasonable control: force majeure, internet or telecommunications failures beyond our network, or outages of your own equipment, network, or software. - Your violation of the Terms of Service, or suspension of your account under them (for example, non-payment or abuse). - Beta, preview, or trial features identified as such. - Months in which no fee was payable for the affected subscription — the free Basic plan and free trial periods (there is no fee to credit). ## How to claim a credit Email [support@intermind.com](mailto\:support@intermind.com?subject=SLA%20credit%20claim) with the subject "SLA credit claim" within 30 days after the end of the affected calendar month, including the dates and times of the incidents you observed. We verify claims against our monitoring data and confirm the credit within a reasonable time. ## Getting the SLA The SLA applies automatically to every paid subscription — no separate signature needed. Enterprise customers additionally get it incorporated into their Enterprise agreement; to set that up, start from the [pricing page](https://intermind.com/pricing) and contact sales. # Subprocessors To run InterMIND we use a small set of infrastructure and service providers ("subprocessors"). This page lists each one, what it processes, where, and under what safeguards. **Service Operator and Contracting Entity:** Golden Fish LLC (UAE). **Publisher and Intellectual Property Owner:** MindMeeting OÜ (EE). Processing happens in the EU by default. Where a provider's corporate entity is outside the EU/EEA, transfers are covered by Standard Contractual Clauses (SCCs) and/or the EU–US Data Privacy Framework (DPF). DPF participation below was last verified against the [official DPF registry](https://www.dataprivacyframework.gov/list){rel=""nofollow""} on 2026-09-01. We update this list whenever a subprocessor is added or removed. | Subprocessor | Entity domicile | Purpose | Personal data processed | Processing location | Safeguards | | ----------------------------------------------- | --------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | | Vercel Inc. | US | Web app hosting, serverless functions, AI Gateway (proxy) | All app traffic incl. meeting metadata, chat | Functions pinned to Frankfurt (fra1); AI Gateway has a zero-data-retention policy (no prompt retention) | DPA + SCCs; DPF; ZDR | | Fly.io Inc. | US | Realtime WebSocket server hosting | Chat fan-out, conference events, transcription words in transit | Paris (CDG) | DPA + SCCs; DPF | | Neon Inc. | US | Postgres (primary database) | Accounts, meetings, messages, transcripts, billing usage | Frankfurt (AWS eu-central-1) | DPA + SCCs; DPF (covered entity of Databricks, Inc.); encryption at rest | | Tigris Data Inc. | US | Object storage | Meeting recordings, chat attachments, documents, export archives | EU multi-region (Frankfurt + Amsterdam) | DPA + SCCs; TLS | | MindMeeting OÜ (Mind API) | EE | Meeting media (SFU), speech recognition, realtime translation | Audio/video streams, speech, participant names/roles; request logs hold technical fields only (no meeting content since 2026-09-28; earlier logs deleted) and are kept for 3 months | OVH, Germany and France | Intra-group agreement | | DeepL SE | DE | Document translation | Contents of documents users submit for translation | EU (Cologne) | DPA; no retention for training | | Stripe Payments Europe Ltd / Stripe Inc. | IE / US | Billing | Name, email, billing address, payment method (card never touches InterMIND) | EU / US | DPA + SCCs; DPF; PCI-DSS | | PostHog | US (EU Cloud) | Product analytics, session replay | Usage events, console/replay (consent-gated, opt-out by default; meeting speech scrubbed from logs) | EU (eu.posthog.com) | DPA; DPF; EU residency | | Functional Software Inc. (Sentry) | US (EU region) | Error monitoring | Error traces, breadcrumbs (no meeting content) | EU (de.sentry.io) | DPA; DPF; EU residency | | Resend | US | Transactional email (sign-in codes, notifications) and inbound email ingest (in.intermind.com receiving domain) | Recipient email, message content; inbound: full email bodies and attachments | Ireland (eu-west-1) | DPA + SCCs; DPF | | Upstash Inc. | US | OIDC session cache (Redis) | Encrypted session/token cache | Frankfurt (fra1) | DPA + SCCs; DPF; encrypted payloads | | Paddle.com Market Ltd | UK | Billing (Merchant of Record in selected countries) | Name, email, billing address, payment method (card never touches InterMIND), plan/team references, buyer country | UK | DPA; UK adequacy decision; PCI-DSS | | Cloudflare Inc. | US | Bot protection on public forms (Turnstile challenge) | Challenge token, implicit visitor signals (IP, browser characteristics) | Global edge network | DPA + SCCs; DPF | | Usercentrics GmbH | DE | Consent management (cookie/consent banner) | Consent choices, consent ID | EU | DPA; EU processing | | Expo (650 Industries, Inc.) | US | Mobile push notifications and app updates | Push tokens, notification content (message text truncated to 120 characters), device metadata | US | DPA + SCCs; DPF | | Microsoft Corp. (Azure OpenAI, Azure AI Speech) | EU | AI features: meeting recaps, document summaries, writing assistant, support assistant, Ask AI, and Mia's voice in meetings (text to speech); voice-note speech-to-text | Meeting transcript and chat window (at meeting end), shared documents, editor text, help-chat questions; voice-note audio (once, at upload) | EU Data Zone (processing and storage within EU member states); our own tenant | Microsoft Products and Services DPA; EU Data Boundary; no training on customer data | | Google LLC (Vertex AI, Cloud Text-to-Speech) | EU | AI features (only for organizations that select Vertex AI as their AI gateway): meeting recaps, document summaries, writing assistant, support assistant, Ask AI, and Mia's voice in meetings (text to speech) | Meeting transcript and chat window (at meeting end), shared documents, editor text, help-chat questions | EU multi-region endpoint (ML processing within the EU); our own project | Google Cloud Data Processing Addendum; no training on customer data; zero data retention for Gemini on Vertex (abuse-logging off) | | Brave Software Inc. (Brave Search API) | US | Web search for Mia, the organization's AI teammate (organizations can switch it off under Settings → AI features) | The search phrase worded by the AI — never documents, recaps, chats, names of users or account identifiers | US | DPA + SCCs; SOC 2 Type II; queries logged up to 90 days without user identifiers; not used to build profiles | | Google LLC / Microsoft Corp. | US | OAuth sign-in; user-authorized calendar sync, file sharing (Drive / OneDrive), and organization directory sync | Name, email, profile photo; with user-granted scopes: calendar events incl. attendee emails, shared-file permissions, org user directory (names, emails) | US | DPF; SCCs | For questions about this list or to request a copy of the relevant transfer safeguards, contact . # Terms of Service **Effective date: 20 October 2026** ## 1. Agreement These Terms of Service ("Terms") are a contract between you and **Golden Fish Computer Systems & Communication Equipment Software Design L.L.C** ("Golden Fish LLC", "we", "us"), City Avenue Building, Office 405-070, Port Saeed, Dubai, United Arab Emirates — the operator of InterMIND, the meeting platform with real-time speech translation available at intermind.com and through the InterMIND mobile apps (the "Service"). By creating an account or using the Service you accept these Terms. If you use the Service on behalf of an organization, you confirm you have authority to bind it, and "you" includes that organization. **Publisher and Intellectual Property Owner:** MindMeeting OÜ (Estonia), Juhkentali 8, Tallinn 10132, Estonia. **Service Operator and Contracting Entity:** Golden Fish Computer Systems & Communication Equipment Software Design L.L.C (United Arab Emirates). The InterMIND mobile apps are published on the Apple App Store and Google Play by MindMeeting OÜ on behalf of, and under license from, Golden Fish LLC; your contract for the Service is with Golden Fish LLC. Registration numbers, licence details and links to the official government registries of both companies are on our [Company](https://intermind.com/legal/company) page. ## 2. The Service InterMIND provides online meetings with real-time speech transcription and translation, meeting recordings, persistent and in-meeting chat with message translation, document translation, and AI-generated meeting summaries. Feature availability and limits depend on your plan (see §4). **Translation accuracy.** Transcription and translation are produced by automated speech recognition and machine translation. They are provided for communication convenience and may contain errors. Do not rely on them as the sole basis for legal, medical, financial, or other consequential decisions, and verify accuracy before relying on any transcript or translation. ## 3. Accounts You sign in with a one-time email code or a third-party sign-in provider (e.g. Google or Microsoft). Keep access to your email account secure — anyone who controls it can access your InterMIND account. You are responsible for activity under your account. Team workspaces have administrators who can manage members, content, and billing for the workspace; if you join a team workspace, its administrators control that workspace's data. Guests may join meetings without an account; anonymous guest sessions are temporary and are purged automatically (see the Privacy Policy). ## 4. Plans, billing, trials - **Plans.** The Service offers a free plan and paid subscription plans. Current plans, limits (such as monthly translation minutes, participants, and storage), and prices are listed on the pricing page at intermind.com/pricing, which forms part of these Terms. - **Payment.** Paid plans are billed by subscription (monthly or yearly) through our payment provider, Stripe. Your card details are handled by Stripe and never touch our systems. - **Trials.** Paid plans may include a free trial; its length is shown at checkout. Unless you cancel before the trial ends, the subscription begins automatically. - **Renewal and cancellation.** Subscriptions renew automatically until cancelled. You can cancel at any time via the billing portal in Settings; cancellation takes effect at the end of the current billing period. Except as required by applicable law, fees are non-refundable and we do not provide refunds or credits for partial billing periods. Purchases made through our reseller Paddle are governed by [Paddle's Refund Policy](https://www.paddle.com/legal/refund-policy){rel=""nofollow""}; refund requests for such purchases are handled by Paddle. If you are a consumer in the EU/EEA or UK, you have a statutory 14-day right of withdrawal for digital services. Nothing in these Terms limits mandatory consumer rights under the law of your country of residence. - **Plan changes and prices.** We may change plan prices or limits with at least 30 days' prior notice; changes apply from your next billing period. - **Usage limits.** Plan limits (e.g. translation minutes per month) are enforced by the Service; when a limit is reached, the corresponding feature pauses until the next period or an upgrade. ## 5. Your content - **Ownership.** You retain all rights to the content you create or upload — meetings, recordings, transcripts, chat messages, documents ("Content"). We claim no ownership. - **License to operate.** You grant us the license needed to run the Service: to host, store, transmit, transcribe, translate, summarize, and display your Content to you and the people you share it with. This license ends when the Content is deleted. We do not use your Content to train AI models. - **Your responsibilities.** You are responsible for your Content and for your use of recording and transcription features in compliance with applicable law — some jurisdictions require the consent of all participants before a conversation is recorded or transcribed. The Service makes recording visible to participants, but obtaining any legally required consent is your responsibility. - **Deletion and export.** You can delete individual Content, or your entire account in Settings (permanent, immediate, includes storage and subscription cancellation), and export your account data as a ZIP archive. See the Privacy Policy for retention details. ### Team status pages - **What it is.** Team status pages are part of the Service on the plans that include them (not on the free Basic plan; the plans are listed at /pricing). On such a plan, the AI brain your organization has already selected for meeting recaps (§2; Privacy Policy §3) reads each meeting recap once and extracts facts from it — requests, promises, tasks, decisions, questions, problems, risks and amounts of money — each with a verbatim quote from the recap. Facts are weighed for importance and urgency against goals the administrator writes, stored for the workspace, and shown as status pages (tasks, problems, important and urgent items, money at stake, requests by counterparty group) to members and through AI assistants connected to the workspace. A fact whose quote cannot be found in the recap is discarded by the Service. - **How they run.** Team status pages run for every organization on a plan that includes them; there is no separate switch and nothing to accept apart from these Terms — this section is part of these Terms (currently **version 2026-10-20**). Where a workspace administrator accepted the earlier, opt-in version of this section before 20 October 2026, the Service keeps that record. An organization that does not want its meeting recaps processed this way chooses a plan without Team status pages. The administrator informs the organization's members that their meeting recaps are read this way. - **Derived content.** Facts and pages are derived from your Content and are your Content under this §5: you own them, the license above covers producing and displaying them, and we do not use them to train AI models. Facts may name people as they were named in the meeting — who asked, who promised, who is assigned, which client or supplier — and the Service may map an assignee name to a member account so that the row reaches that member. Pages describe the state of work, not the people doing it: the Service does not rate, score, rank or otherwise evaluate individuals, and you agree not to use Team status pages as the sole basis for a decision about an individual (such as hiring, performance or dismissal). Facts are AI-generated and may be wrong or incomplete; the quote is there so that every fact can be checked against the recap. - **Who sees what.** An administrator sees the organization's pages. A member sees facts from the sessions they hosted or attended, from the date they joined the workspace onwards unless the administrator opens earlier history, plus rows assigned to them. The same rights apply when pages are read through a connected AI assistant; on plans billed per active member, such a read is a tool call made as the member and counts as that member's activity (Privacy Policy §2). - **Pausing and deletion.** Moving to a plan without Team status pages pauses extraction; stored facts are kept but shown to no one until the organization is again on a plan that includes them. Facts live as long as the recap they came from: deleting a session's artifacts deletes its facts, and deleting the workspace or the account deletes all of them. There is no separate retention period for facts. ## 6. Acceptable use You agree not to: use the Service for unlawful purposes; infringe others' rights (including recording people without required consent); upload malware or attempt to breach, probe, or overload the Service; resell or white-label the Service without an agreement with us; or interfere with other users. We may suspend or terminate accounts that violate these Terms. Where a violation is capable of being cured, we will give you notice and a reasonable opportunity (normally 14 days) to cure it before suspending or terminating your account. We may suspend access immediately, with notice as soon as reasonably practicable, where the violation is unlawful, poses a security risk, risks harm to others or to the Service, or where required by law. ## 7. Privacy and data protection Our Privacy Policy (/privacy) describes what we process and why; the subprocessor list is published at [/legal/subprocessors](https://intermind.com/legal/subprocessors). For organizations that need one, we offer a [Data Processing Addendum](https://intermind.com/legal/dpa) — request it at . ## 8. Intellectual property The Service, including its software, design, and branding, is protected by intellectual property rights owned by MindMeeting OÜ (Estonia) and/or its licensors and used by Golden Fish LLC. These Terms grant you only the right to use the Service; no other rights are transferred. If you send us feedback or suggestions, we may use them without obligation to you. ## 9. Third-party services Sign-in via Google or Microsoft, and payments via Stripe, are subject to those providers' own terms. We are not responsible for third-party services. ## 10. Disclaimers The Service is provided "as is" and "as available". To the maximum extent permitted by law, we disclaim all warranties, express or implied, including fitness for a particular purpose and non-infringement. We do not warrant uninterrupted or error-free operation, or the accuracy of transcriptions and translations (§2). For paid subscriptions, our uptime commitment and its exclusive service-credit remedy are described in the [Service Level Agreement](https://intermind.com/legal/sla), which forms part of these Terms; otherwise the Service is provided without service level commitments. ## 11. Limitation of liability To the maximum extent permitted by applicable law: (a) neither party is liable for indirect, incidental, special, consequential, or punitive damages, or for lost profits, revenue, data, or goodwill, even if advised of the possibility; (b) our total aggregate liability arising out of or relating to the Service or these Terms is limited to the greater of the fees you paid us for the Service in the 12 months before the event giving rise to the claim, or USD 100; and (c) these limits do not apply to liability that cannot be excluded or limited under applicable law, including for death or personal injury caused by negligence, for fraud or fraudulent misrepresentation, or for willful misconduct or gross negligence. Where mandatory consumer-protection law gives you greater rights, those rights prevail. These limitations reflect a reasonable allocation of risk and are an essential basis of the bargain. ## 12. Termination You may stop using the Service and delete your account at any time. We may suspend or terminate your access for material breach of these Terms (with notice and a reasonable cure period where the breach is curable, as set out in §6), or discontinue the Service with reasonable prior notice — in which case prepaid fees for the unused period will be refunded pro-rata. Sections that by their nature survive termination (e.g. §§8, 10, 11, 13) do so. ## 13. Governing law and disputes These Terms are governed by the laws of the Dubai International Financial Centre (DIFC). The Courts of the DIFC have exclusive jurisdiction over any dispute arising out of or in connection with these Terms or the Service, and the parties submit to the jurisdiction of the DIFC Courts. This choice of governing law and forum does not displace mandatory data-protection law applicable to the processing described in the Privacy Policy. If you use the Service as a consumer, nothing in this section deprives you of the protection of mandatory provisions of the law of your country of residence, and you may bring proceedings in the courts of that country where the applicable law so requires. ## 14. Changes to these Terms We may update these Terms; we will post the new version on this page and update the effective date, and for material changes we will notify you in the product or by email before they take effect. Continued use after the effective date constitutes acceptance. ## 15. Contact Golden Fish Computer Systems & Communication Equipment Software Design L.L.C — City Avenue Building, Office 405-070, Port Saeed, Dubai, United Arab Emirates. Email: # Trust Center InterMIND runs on EU infrastructure across France, Germany and Ireland. This page shows where your data goes at every hop, how long we keep it, and which AI touches what. It states only what we can back up — in code, in configuration, or in a signed contract. **Service Operator and Contracting Entity:** Golden Fish LLC (UAE). **Publisher and Intellectual Property Owner:** MindMeeting OÜ (EE). ## Where a meeting actually runs Every hop a meeting takes, and where that hop happens: | Hop | Provider | Region | | ------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | | Web app and API | Vercel | Frankfurt (fra1) | | Realtime server — chat, presence, transcript words in transit | Fly.io | Paris (CDG) | | Meeting media, speech recognition, live voice translation | Own engine (Mind API, intra-group) | OVH, Germany and France | | Post-meeting AI summaries, document summaries, writing assistant, Ask AI | The AI brain your organization selects — Azure OpenAI by default; Vertex AI or Amazon Bedrock by choice | EU: Azure EU Data Zone (default), Vertex AI EU multi-region endpoint, Bedrock Frankfurt — our own tenant in each; no training on customer data | | Voice-note transcription (speech-to-text) | Azure AI Speech — the speech service of the default AI gateway; on Vertex AI and Amazon Bedrock voice notes are not transcribed yet | Sweden Central (EU) | | Document translation | DeepL | Cologne, Germany | | Database | Neon (Postgres) | Frankfurt (AWS eu-central-1) | | Recordings, attachments, documents | Tigris object storage | EU multi-region (Frankfurt + Amsterdam) | | Transactional email | Resend | Ireland (eu-west-1) | | Product analytics | PostHog | EU Cloud (opt-out by default, consent-gated) | | Error monitoring | Sentry | EU (Germany); no meeting content in error reports | Some of these providers are US companies operating EU regions. That is stated plainly, not hidden: each transfer is covered by a DPA plus Standard Contractual Clauses and/or the EU–US Data Privacy Framework. The full registry — every subprocessor, what it processes, and its safeguards — is on the [subprocessors page](https://intermind.com/legal/subprocessors). ## AI on your meeting content - Live speech recognition and voice translation run on our own engine, hosted at OVH in France — not on a third-party AI cloud. - Every AI call on meeting content — post-meeting summaries, shared-document summaries, editor assistance, support replies, Ask AI — goes to the AI brain your organization selected in its settings, and nowhere else: Azure OpenAI in the EU Data Zone by default, Vertex AI on the EU multi-region endpoint or Amazon Bedrock in Frankfurt by choice, each in our own tenant under the provider's data processing terms with no training on customer data. One resolver in code picks the brain for every call site; there is no second path. - Document translation goes to DeepL (Cologne) and is not retained for training. - Team status pages (on the plans that include them) send each meeting recap once to that same brain and keep only facts that carry a verbatim quote the code verified against the recap — a fact whose quote is not found is dropped. Members see only facts from the sessions they hosted or attended, plus rows assigned to them; administrators see the organization's pages. Pages describe work, not people: nothing rates, ranks or scores an individual. - Meeting audio is never stored. Speech persists as text only — word-level transcripts. Translated voice audio is streamed to participants and never written to disk. ## What we store, and for how long | Data | Retention | | ------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Meeting audio and video | Not stored. If the host records, the recording (mp4) is kept as a private object until the host deletes the session's artifacts or the account is deleted | | Transcripts, chat, documents | Kept until you delete them — there is no automatic expiry. Hosts can irreversibly delete per-session artifacts; account deletion removes everything | | Guest accounts | Expire 24 hours after creation and are hard-deleted by a cleanup job that runs every 6 hours | | Calendar and drive OAuth tokens | Stored encrypted (AES-256-GCM), removable by disconnecting the integration | | Unreferenced chat attachments | Swept by a daily cleanup job after 48 hours | | Team status page facts | Kept as long as the recap they derive from: deleting the session's artifacts deletes them, deleting the organization deletes all of them. Turning pages off pauses extraction and hides the stored facts | Account deletion is email-confirmed and complete: stored files are removed first, then the database records, then the billing customer at our payment provider. It is a hard delete, not a flag. ## Payments Card data never touches InterMIND servers. Checkout and card handling are fully hosted by our payment providers — Stripe, and Paddle as merchant of record in selected countries. We store your plan and billing email; the card stays with the payment provider. ## EU AI Act InterMIND's AI does four things: speech recognition, translation, meeting summaries and — on the plans that include team status pages — extraction of work facts from those summaries. None of these is a prohibited practice or a high-risk use under Annex III of the EU AI Act (Regulation 2024/1689). We do not do biometric identification or categorisation, and we do not do emotion recognition — the engine transcribes and translates what is said; it does not profile who says it. Team status pages evaluate work, not employees: the extraction is instructed not to rate, rank or score people, and the terms forbid using the pages as the sole basis for a decision about an individual. Translation, transcription, AI recaps and team status pages are features of the plan an organization chooses, described here and in the [terms](https://intermind.com/terms), not silent processing. We track the Act's guidance as obligations phase in and will update this page when they apply to us. ## Certifications — the honest version We do not yet hold ISO 27001 or SOC 2. ISO/IEC 27001:2022 certification audit scheduled: Stage 1 in the week of 19 October 2026, Stage 2 in the week of 2 November 2026, certification body Glocert International. We will not write "in progress" until that audit has actually started. What we do have is published: our CSA STAR Level 1 self-assessment (CAIQ-Lite v4.1.0, 138 questions) is listed in the public [CSA STAR Registry](https://cloudsecurityalliance.org/star/registry/golden-fish-csp-llc/services/intermind/){rel=""nofollow""}, answered under the same rule as this page — an honest No wherever a formal control does not exist. Beyond that we offer verifiability: this page and the [subprocessors list](https://intermind.com/legal/subprocessors) state only what is enforced in code or in contract, and the documents below are ready for procurement review. [![CSA STAR Level One — Self-Assessment badge](https://intermind.com/img/badges/csa-star-level-1.png){height="140" width="140"}](https://cloudsecurityalliance.org/star/registry/golden-fish-csp-llc/services/intermind/){rel=""nofollow""} We also hold **Cyber Essentials** (IASME, the NCSC-backed UK scheme; certified September 2026). It is an assessor-verified self-assessment of the five baseline controls — firewalls, secure configuration, user access control, malware protection and security update management — across every device and cloud account that touches organisation data, renewed annually. It certifies the operating entity's baseline, not the service architecture, so we do not present it as a substitute for ISO 27001 or SOC 2. Certified 2026-09-03, recertification due 2027-09-03. Verify it on the [BlockMark Registry](https://registry.blockmarktech.com/certificates/e455115f-0307-4f0f-b960-68bbc244f018/){rel=""nofollow""} or in IASME's public [certificate search](https://iasme.co.uk/cyber-essentials/ncsc-certificate-search/){rel=""nofollow""}. [![Cyber Essentials Certified badge](https://intermind.com/img/badges/cyber-essentials-certified.png){height="140" width="140"}](https://registry.blockmarktech.com/certificates/e455115f-0307-4f0f-b960-68bbc244f018/){rel=""nofollow""} ## Documents - [Security & Data Protection whitepaper (PDF)](https://intermind.com/legal/InterMIND-Security-Whitepaper.pdf) — where meeting data goes, at every hop, and what we do not have yet - [Data Processing Agreement](https://intermind.com/legal/dpa) — [summary PDF](https://intermind.com/legal/InterMIND-DPA-Summary.pdf); the binding DPA is signed per customer - [Service Level Agreement](https://intermind.com/legal/sla) — [PDF](https://intermind.com/legal/InterMIND-SLA.pdf) - [Subprocessors](https://intermind.com/legal/subprocessors) - [Privacy Policy](https://intermind.com/privacy) - [Terms of Service](https://intermind.com/terms) Our completed CAIQ-Lite (CSA Cloud Controls Matrix self-assessment) is published in the [CSA STAR Registry](https://cloudsecurityalliance.org/star/registry/golden-fish-csp-llc/services/intermind/){rel=""nofollow""}; a PDF copy is available on request. Questions, or need a signed copy of the DPA or transfer safeguards: . # Action items: how to write, assign and track them — and how the recap keeps the list (2026) - **One verb, one owner, one date.** A task from a meeting, written so someone who wasn't there knows what happens, who does it and when it is late. - **Lists die after the call.** Teams, Zoom, Google and Slack keep them as a document in one language; whether they got done, a person asks. - **InterMIND keeps the whole meeting in each member's language,** chat, files and the recap's action items, judged next session on the status page (preview). Guests join free by link, no account; you pay only for active members. An action item is one task that came out of a meeting: a verb, one owner, one date. "Anna — send the revised estimate to Aster — by Thursday" is an action item. "Follow up on the estimate" is a topic. The difference is whether a person who wasn't in the room can tell, from the line alone, what will happen, who will make it happen and when it is late. Most meetings produce action items. Few teams keep them. The list gets written at the end of the call, lands in one person's notes, and resurfaces three weeks later as the question "did anyone ever send that estimate?" — asked in the next meeting, which then spends ten minutes reconstructing the last one. This guide is the craft first — what an action item is, the five things each one carries, how to write them during the call and at its close, how to assign them so they get done, how to track them so the list survives — with a template and examples you can copy. Then the mechanics: where action items live in the tools your team already uses, and what happens to them after the meeting. That second part is where lists go to die, and it is the part the recap of a recurring meeting can do on its own. ## What an action item is — and what it isn't Four things come out of a meeting, and the first job of the person writing is to tell them apart: | | What it is | Shape | Where it goes | | ----------------- | ---------------------------------------------- | ---------------------------------- | --------------------------------------------------- | | **Decision** | Something the room agreed | "We agreed …" — one sentence | The recap, under decisions | | **Action item** | One task someone took on because of a decision | Owner — verb — object — date | The action list, reviewed at the next meeting | | **Open question** | Something asked that nobody could answer yet | The question and who will find out | The parking lot, into the next agenda | | **Project task** | Work that already lives in a tracker | A ticket with its own life cycle | The tracker; the meeting links to it, not copies it | A decision is not an action item: "we go with vendor B" changes nothing until "Priya — sign the vendor B order form — by the 14th" exists. An open question is not an action item either, though it often produces one ("Kenji — find out whether the API has a rate limit — by Monday"). And a ticket that was already in the tracker before the meeting is not a new action item; mentioning it in a meeting does not make it one. If the list of action items after a one-hour meeting is longer than ten lines, it contains topics, questions or tickets dressed as tasks. How the decision itself is recorded so it is not reopened at the next meeting is in [the decision log template](https://intermind.com/blog/decision-log-template). ## What every action item carries: the format A usable action item has five parts. The first three are the line; the last two are what makes it trackable. 1. **One verb, one object.** *Send the estimate. Book the QA round. Draft the copy.* A line that starts with "look into", "discuss" or "think about" is not an action — it has no finishing condition. If you cannot say what "done" looks like, the item is a question. 2. **One owner — a name, not a team.** "Marketing" cannot be asked whether something is done; Lena can. If two people are needed, there are two action items, or one owner who delegates. The owner is the person who will be asked about it next time, so it has to be a person who was asked now. 3. **One date — a day, not "soon".** "By the 16th" can be late; "asap" cannot. If the date is unknown, the action item is "Anna — propose a date for X — by Friday", which is a real item with a real day. 4. **Where it came from.** The decision or agenda item that produced it, and — if the record has one — the moment in the meeting where the owner said yes. This is the context a reader needs a month later, when the line "send the estimate" means nothing on its own. 5. **Its state.** *To do*, *done*, *not done — and why*. An action list without states is a wish list; the state is what the next meeting opens with. What stays out: the discussion that led to the item, the reasons, the alternatives. Those belong in the notes. The action item is one line, because it is going to be read by someone looking for their own name. ## How to write them: during the meeting, at the close, after **During the meeting, write the item the moment someone says yes.** Action items are born in a sentence — "I'll send it over Thursday" — and they die in the same sentence if nobody writes it down. The habit that does most of the work: when someone takes something on, read it back aloud, with the date — "so I'm noting: Anna, the revised estimate to Aster, by Thursday" — and let the owner correct it while they still remember agreeing. An item that is read back is an item the owner has agreed to twice. **At the close, run the list.** The last five minutes of a meeting with an [agenda](https://intermind.com/blog/meeting-agenda-template) are reserved for outcomes and owners: every item on the agenda gets one of three states — decided, open, deferred to a date — and every action gets a name and a day. Read the whole list, one line each, in the room. This is where "Marketing to look at the pricing page" becomes "Lena — draft the pricing page copy — by the 16th", because Lena is there to say so. An item that cannot get a name at the close does not go on the list; it goes to the parking lot with the name of the person who raised it. **After the meeting, publish the list the same day — once, in one place.** To everyone invited, including the people who weren't there: an action item whose owner missed the meeting is the one most likely to be missed. Then put the list where the next meeting will open it. A list in the facilitator's notebook is a list the team doesn't have; a list in the channel where the team already talks is one everyone can see ageing. ## How to assign action items so they get done Three rules cover almost every failed assignment: - **The owner is the person who said yes — in the room.** Assigning an item to someone absent produces a line nobody has agreed to. If the right owner wasn't there, the item is "facilitator — ask Dana whether she can take X — by tomorrow", and Dana's real item is born when she answers. - **One owner, however many hands.** "Mateusz and Priya" means each assumes the other. Pick the one who will be asked at the next meeting; the other is help, and help is not on the line. - **The owner repeats it back.** Not the facilitator — the owner. "Thursday, the revised estimate, to Aster, yes." Thirty seconds, and it removes the most common dispute at the next meeting: "that's not what I agreed to." What is not an assignment: an item on a list that the owner first sees in an email the next morning. If that is how items reach their owners, the meeting ended before the close. ## How to track action items Tracking is a routine, not a tool. Four parts: 1. **One list per team or per recurring meeting.** Not one per meeting — one that the meeting adds to and reads from. The list is the memory of the meeting series. 2. **The next meeting opens with the list.** Before the first agenda item: every open action, one line each, the owner says *done* or *not done* and, if not, why. Two minutes for a list of eight. The reason goes next to the item in a few words — "waiting on legal", "not started" — because the reason is what the room decides about. 3. **Three states, and a not-done item is never carried silently.** A not-done item is re-dated, reassigned or dropped, in the room, by the person who owns it. Carrying "send the estimate" across four meetings without a decision about it is how a list stops being read. 4. **The ageing rule.** An item older than the meeting's cadence twice over — two weeks on a weekly — is raised explicitly: either it is bigger than an action item and becomes a project task in the tracker, or it was never going to happen and is dropped. Both are fine. A list where nothing ever leaves is not a list. The question your tracking has to answer is not "what did we decide" — the recap answers that — but "what, of all we decided, has actually happened, and what is stuck." If the list cannot answer it in two minutes at the start of a meeting, the format is wrong, not the people. ## An action items template The line, for the close of the meeting and the recap: > **Action items — \[meeting name], \[date]**:br > – \[Owner] — \[verb + object] — by \[date] — from \[agenda item / decision] :br > – \[Owner] — \[verb + object] — by \[date] — from \[agenda item / decision] :br > – \[Owner] — \[verb + object] — by \[date] — from \[agenda item / decision] > > **Carried over from \[previous date]**:br > – \[Owner] — \[task] — was due \[date] — **done** / **not done:** \[reason, three to six words] — re-dated to \[date] / dropped The tracker, for the list that spans the series: | # | Action | Owner | Due | From | Recorded | State | Note | | - | ---------------------------------- | ----- | ------ | ------------------ | -------- | -------- | ------------------------------------------- | | 1 | Send the revised estimate to Aster | Anna | 16 Oct | Scope call, item 3 | 9 Oct | To do | | | 2 | Book the Japanese QA round | Kenji | 20 Oct | Release, item 2 | 9 Oct | To do | | | 3 | Migrate the deals to the new CRM | Dana | 30 Sep | Weekly, 10 Sep | 10 Sep | Not done | Deals still in the old CRM; re-dated 23 Oct | | 4 | Offer to the second finalist | Priya | 8 Oct | Hiring, item 3 | 6 Oct | Done | Sent 7 Oct | Both paste into a document, a spreadsheet, a chat message or a canvas without reformatting. The columns that are usually missing from templates are *From* and *Recorded*: where the item came from, and how old it is. They are the two the next meeting needs. ## Examples: the same items, before and after | As it was said or first written | As an action item | | -------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | "Marketing to look at the pricing page" | Lena — draft the new pricing page copy — by 16 Oct — from decision 2 | | "Follow up on the estimate" | Anna — send the revised estimate to Aster — by Thursday 16 Oct — from scope call, item 3 | | "We need to check the API limits" | Kenji — find out whether the vendor API has a rate limit and post the answer in the channel — by Monday 13 Oct | | "Someone should talk to legal about the DPA" | Priya — ask legal for a redline of the DPA — by 15 Oct; Priya reports back at the weekly | | "Fix the export job" (already a ticket) | Not an action item — the ticket is linked from the notes; Mateusz is its owner there | | "Decide on the vendor" | A decision for the next agenda, with a date — not an action item until someone owns the comparison: Tomás — vendor A and B against the criteria, one page — by 14 Oct | Notice what the right-hand column has in common: a name first, a verb second, a day, and the item it came from. That is the whole craft. Everything else in this guide is about keeping that line alive after the meeting ends. ## Where action items live in the tools you already use Each major platform has a place for action items, and each stops at a different point. Documented behaviour only, from the vendors' own pages, with the month each page was checked: | Platform | Where action items are written | What happens to them after the meeting | | -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Microsoft Teams** | *Notes* in the meeting controls during the call, a Loop component any attendee or organizer can edit, with tasks assigned by tagging people; the meeting recap lists follow-up tasks | The notes are saved automatically and reachable from the Teams calendar and the meeting recap; external attendees cannot access or edit them (notes page checked October 2026, recap page checked August 2026) | | **Zoom Workplace** | During the meeting, *Meeting questions with AI* answers the preset question "What are the action items?" on paid Zoom Workplace plans; after it, the AI Companion meeting summary carries a "Next steps" section | The summary is sent by email, listed on the Summaries page of the web portal and can be posted to the meeting's group chat; participants receive it when the host chose to share it, only the host can edit it, and unauthenticated users do not receive the email (checked August and September 2026) | | **Google Workspace** | *Take notes for me* adds a "suggested next steps" section to the notes document after the meeting; the reader can review and edit the next steps "and even assign the task to someone" | The notes arrive as a Google Doc, shared per the configured setting; assignment is a person's click in the document; the feature supports one language at a time — multiple languages spoken in the same meeting are not supported (checked September and October 2026) | | **Slack** | A canvas from the meeting-agenda template, shared in the channel, with sections for next steps and action items with due dates | The canvas stays in the channel as a document; what was said in the call is not in it unless someone types it (checked October 2026) | Two things are the same everywhere. The action items are a document next to the meeting, in the one language the room used; and whether last week's items were done is a question the document does not answer — a person opens it at the next meeting and asks. ## How the recap keeps the list InterMIND is a communication space where a meeting lives in a channel, so the list has an obvious home: the channel's chat, where the agenda went in the day before and the outcomes come back after — and where each member types in their own language and reads the others in theirs. During the call, the list posted as a note goes on everyone's screen next to the video tiles with *Share to conference*; the sharer edits it live and every participant reads it in their own language. If the agenda or the tracker is drafted somewhere else, it lands in the channel by email — the channel's owner gives it an address of its own, and a message sent to it appears as a regular message with the sender named and attachments kept. When the call ends, the recap is written from the meeting itself: a summary, the points marked agreed, open or disputed, and the action items — recorded only when someone took responsibility, named or self-assigned, with the owner on the line and the timestamp of the moment they said yes, which opens the transcript at that moment. The deadline, when one was said, stays in the line's words. The recap arrives by email, as a message in the channel and as a link in the calendar event, and every signed-in member reads it **in their own language** — the record is translated per reader, not written once in the language the room happened to use. A wrong owner is fixed with *Edit*; every edit keeps author and revision history, and the channel keeps the recap of every past session, so the item from three weeks ago is one click away. In an organization with team status pages on, the list is also checked. Every task a recap records joins the organization's task chain, and when the next recap is written the open ones are judged against what was said: an item someone reported finished is marked done; an item discussed but not finished is marked not done with the reason in the words of the meeting; an item nobody brought up stays open. The verdicts are not written into the recap — it holds only the tasks born in that meeting — but live on the organization's status page, each with its quote and the recap it rests on; a member's own verdict on a task beats the model's. The recap page sums the channel's action items for the last 30 days or all time — the host sees everyone's row, a member sees their own — and at the start of the next session Mia names the open items and their owners, so the list is spoken about rather than found. Team status pages are a preview feature: an organization's admin switches them on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). Where the list has to end up in a system of record, the host adds a recap copy to any address — a CRM or tracker inbound mailbox — and every recap of the meeting or channel is also sent there after a one-time confirmation of the address; the mechanics are in [a copy of every meeting recap in your CRM, by email](https://intermind.com/blog/how-to-get-a-copy-of-every-meeting-recap-in-your-crm-by-email). The same recap reaches Zapier, a webhook or the API with the summary as Markdown, and the reader's own assistant — Claude, ChatGPT, Copilot or Gemini — can read the recaps through the MCP connector, so "add the action items from my last three meetings to my task list" is a prompt in the tool they already use. A guest joins by link, without an account and at no cost — from a phone, in the browser — and hears the meeting live in their own language. There is no record for a guest afterwards — the account is free, and it is what makes the record reachable. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing); members who go quiet keep their access at no cost. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours, action items included. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. Action items as a craft survive every tool: somebody still has to say yes to a task, out loud, with a date. What doesn't have to survive is the second job — retyping the list after the call, in one language, and opening the next meeting by asking whether anyone did what the last one said. ## FAQ **What is an action item?** An action item is one task that came out of a meeting, written as a verb with an object, one owner and one date: "Anna — send the revised estimate to Aster — by 16 October". It is distinct from a decision (what the room agreed), an open question (what nobody could answer yet) and a project task that already lives in a tracker. Its purpose is that someone who wasn't in the meeting can tell what will happen, who will do it and when it is late. **What is an example of an action item?** "Lena — draft the new pricing page copy — by 16 October — from decision 2." A name, a verb, a day, and the item it came from. The same thing said badly is "Marketing to look at the pricing page": no person, no finishing condition, no date. **How do you write action items in meeting minutes?** One line each, under their own heading: owner, task, deadline, in that order — "Action: M. Bauer — updated price list to sales — by 5 September." Write the item the moment someone takes it on, read it back aloud with the date so the owner confirms it, and list all items together at the close of the meeting. An action item without an owner is recorded as an open question instead; the full format is in [the meeting minutes guide](https://intermind.com/blog/how-to-write-meeting-minutes). **What is the difference between an action item and a task?** An action item is born in a meeting and is reviewed by that meeting: it is one line with an owner and a date, and its life is short — days or weeks. A task lives in a tracker with its own status, estimate and history, and may outlive many meetings. An action item often *becomes* a task ("Mateusz — open the ticket for the export fix — by tomorrow"), but mentioning an existing ticket in a meeting does not make it a new action item. **Who is responsible for action items in a meeting?** Each action item has exactly one owner — the person who said yes to it, in the room — and the facilitator is responsible for the list: reading it back at the close, publishing it the same day, and opening the next meeting with it. An item assigned to someone absent is a line nobody has agreed to; the real item is to ask them. **How do you track action items from meetings?** Keep one list per recurring meeting, not one per meeting; open every meeting with it — each owner says done or not done, and why, in two minutes; give every item one of three states; and never carry a not-done item silently: re-date it, reassign it or drop it, in the room. Any document, spreadsheet or canvas works for the list. In an InterMIND channel the recap writes the list from the meeting and, in an organization with team status pages on (a preview), the open items are judged done or not done with the reason when the next recap is written, on the organization's status page. **Can Zoom, Teams or Google Meet create action items automatically?** Per their documentation: Zoom's AI Companion meeting summary includes a "Next steps" section on paid Zoom Workplace plans, and during the meeting the preset question "What are the action items?" can be asked; Microsoft Teams meeting notes let attendees assign tasks by tagging people, and the Teams recap lists follow-up tasks; Google Meet's *Take notes for me* adds "suggested next steps" to the notes document, where a person can assign them. In each case the record is kept in the one language the meeting was held in; Google states that multiple languages in the same meeting are not supported. --- *Sources: [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Zoom — Meeting questions with AI](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0057748){rel=""nofollow""}; [Google Workspace Updates — "Take notes for me" now captures "next steps"](https://workspaceupdates.googleblog.com/2025/02/google-meet-take-notes-for-me-next-steps.html){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Meeting agenda template (canvas)](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Microsoft's notes page, Google's Meet help page and Slack's template checked October 2026; Microsoft's recap page and Zoom's meeting-summary page checked August 2026; Zoom's meeting-questions page and Google's next-steps announcement checked September 2026. Vendors change plans, features and language lists over time; check their pages for the current state.* # AI meeting assistant that acts during the meeting: what Teams Facilitator, Zoom AI Companion, Google Meet Gemini and InterMIND do in the room (2026) - **A note taker writes afterwards; an assistant works during the call.** It reminds the room what was decided, notes commitments as spoken, schedules the follow-up. - **Each vendor fences it differently.** Facilitator needs a Copilot license and one language; Zoom and Gemini answer when asked; none documents answering each participant in theirs. - **InterMIND keeps the whole meeting in each member's language,** and Mia, in preview, answers each in theirs and acts on the host's word, with undo. Guests join free by link, no account; you pay only for active members. For two years "AI in meetings" meant one thing: a note taker. It listened, and after the call it mailed a summary. That job is done — every platform has it, and we mapped who keeps what afterwards in [the recap guide](https://intermind.com/blog/meeting-recap). The next job is different. An AI meeting assistant works *during* the meeting: it reminds the room what the last session decided, notes a commitment the moment someone makes it, schedules the follow-up when the host asks, and, near the end, says which agenda items were never touched. G2 now lists this as its own feature group for video conferencing — "Agentic AI", with three abilities: proactive assistance, autonomous task execution and decision making. This guide is in two halves. First, how to run a meeting with an AI participant so that it actually helps — what to put in the invite, how to address it, who should be allowed to give it orders, what to check at the end. Second, the documented map: what Microsoft Teams, Zoom and Google Meet ship today under this heading, and what InterMIND's Mia does. Every vendor fact is quoted from that vendor's public documentation, checked September 2026, linked at the end. ## Note taker, assistant, agent — the three words A **note taker** listens and writes afterwards. It never speaks in the meeting. Zoom's Meeting Summary, Teams Recap and Google Meet's "Take notes for me" are note takers; their output is the post-meeting record. An **assistant** answers during the meeting when asked — "what did we agree on the budget?", "catch me up" — from the transcript and the material it can reach. Zoom's in-meeting questions, Ask Gemini in Meet and InterMIND's Mia answering by name are assistants. An **agent** does two more things. It speaks up on its own when something in the conversation warrants it (a commitment, a question nobody answered, the clock), and it acts on a request — schedules, records, sends — instead of describing how you could. Microsoft calls its version Facilitator; Zoom's is ZoomMate; InterMIND's is Mia. The rest of this guide is about that third word, and the two questions it raises in every organization: *when is it allowed to interrupt*, and *who is allowed to give it orders*. ## How to run a meeting with an AI participant The mechanics differ per platform (below), but the practice is the same on all of them. 1. **Give it an agenda before the meeting.** An agent that knows the agenda can tell you what was skipped; one that doesn't can only summarize. In Teams the agenda is read from the invite or the meeting notes; in InterMIND it is the meeting's agenda note; in Zoom and Meet there is no agenda input for the assistant today. 2. **Decide who may command it.** In a customer call, the customer should be able to *ask* the assistant a question and should not be able to *schedule your team's follow-up*. Check which platform lets you separate the two before the call, not during it. 3. **Address it by name, in a full sentence.** "Mia, what did we decide on the vendor last time?" works; a keyword does not. The assistants below trigger on a name, an @-mention or a button — the sentence after that is what the model reads. 4. **Let it record commitments as they happen.** "I'll send the estimate by Friday" is the most valuable sentence of the meeting and the one most often lost. An agent that writes it into the chat the moment it is said produces a recap nobody has to reconstruct. 5. **Use the last five minutes.** Ask it what is still open and which agenda items were not covered. If it can schedule the follow-up, do it in the room, while everyone is there to object to the date. 6. **Keep the undo close.** Every action the agent takes should be reversible from where it was announced. If the platform has no undo, treat its actions as proposals and confirm them yourself. 7. **Know what it heard.** An assistant that joins as a participant is in the recording and the transcript; one that listens through the transcript is not. Both are fine — but tell external participants which one is in the room. --- ## Microsoft Teams: Facilitator Facilitator is Microsoft's agent for Teams meetings. Microsoft's documentation describes it as "an AI-powered agent that helps keep meetings focused, organized, and action-oriented by surfacing agendas, tracking progress, and capturing key highlights in real time". Unlike Copilot in Teams, whose prompts "are private to that individual user", Facilitator "acts like an assistant sitting in your users' meetings": a prompt to it and its reply are shown "within the meeting's conversation for everyone to see". **Speaks up on its own.** It "checks for a meeting agenda from the meeting invite and the meeting notes Loop component and then send\[s] the agenda in the meeting chat", keeps "visual timeline markers to track topics and time, with reminders at midway and wrap-up", "@mentions absent participants in the meeting chat when they've been mentioned multiple times", and "summarizes key decisions and open questions from meeting discussion" into collaborative real-time notes. **Acts on request.** Licensed users "can interact with the agent by mentioning it in the chat, for example '@Facilitator add these topics to the agenda…'"; it offers "Word document creation in meeting or post meeting, for example '@Facilitator, create a BRD based on this meeting for the executive review'", and "AI-powered Q\&A from meeting and web content". "Task tracking integration with Planner" is listed as public preview. **Who may command it.** "A Microsoft Copilot license is required to add Facilitator to a meeting or turn it on during a meeting"; "only meeting participants who are organizers or presenters and are using Teams for web or desktop can turn Facilitator on or off"; "unlicensed users can't prompt Facilitator, but they can see others' prompts to Facilitator and Facilitator's responses". It "isn't supported in 1:1 chats, group chats, or external chats and meetings". **Language.** When turned on, the user "is prompted to select the language participants are speaking during the meeting. The language selected must match the spoken language during the meeting, or notes aren't generated." "AI-generated notes for meetings only support meetings where a single language is spoken." **Where the output lives.** Notes are "stored as a `.loop` file in a OneDrive folder titled Meetings of the user who initiated Facilitator", and "any content generated by Facilitator during the meeting can be accessed both through meeting chat and meeting notes in Recap". ## Zoom: AI Companion in the meeting, ZoomMate after it **In the meeting.** Zoom's *Meeting questions with AI* "allow meeting participants to ask questions about the content of the meeting discussions", with preset questions "Catch me up", "Was my name mentioned?" and "What are the action items?". The host configures who may ask: "All participants and invitees", "All participants only from when they join", internal participants only, or "Only meeting hosts". It works on the live meeting's "speech to text data", on Zoom Workplace Pro, Pro Plus, Business, Business Plus, Enterprise, Enterprise Plus or Enterprise Bundle accounts, in "more than 30 languages", where "quality of supported languages varies by language, audio quality, and other factors". Zoom's documentation does not describe the assistant speaking up unprompted during the meeting. **After it.** ZoomMate, "generally available today" as of 1 June 2026 "for online and direct customers in North America" and "starting at $20 per user per month with included AI credits", "turn\[s] meetings into finished work, automatically creating presentations, documents, spreadsheets, reports, and project plans"; it can "update records, create follow-up tasks, draft customer communications, and trigger onboarding or support workflows" and "schedules events in Google Calendar or Microsoft Outlook". Before a meeting it can "pull key information from Google Docs, open Jira issues, and surface recent Slack discussions". Zoom's launch page does not state whether these actions run autonomously or after a user's confirmation. EMEA and APAC availability is announced for later in 2026. ## Google Meet: Ask Gemini during the call, next steps after it **In the meeting.** *Ask Gemini in Meet* lets a participant "summarize ongoing discussions, or get a recap of what someone said", "identify key takeaways, decisions, and action items" and "catch up on what you missed if you joined late". It answers from meeting captions, the user's accessible Workspace files and public web content, on request: Google's announcement describes prompts the user types, not suggestions the assistant volunteers. At launch (rollout from 29 September 2025) it was available to Business Plus customers, "only meetings in English are currently supported", desktop only, not in breakout rooms, and "no caption data will be stored after the meeting ends". **After it.** "Take notes for me" adds a "suggested next steps" section — "AI-powered identification and organization of next steps and follow-ups discussed during the meeting" — to the notes document; the reader can "review and edit the next steps and follow-ups as needed, and even assign the task to someone". Assignment is a person's click, not the assistant's. Available on Business Standard and Plus, Enterprise Standard and Plus and the listed add-ons; announced 18 February 2025. Google's documentation does not describe the assistant scheduling a meeting or writing to a calendar on a participant's request. ## The axis the three share Lay the three next to each other and the same four lines appear: - **Who speaks first.** Facilitator posts the agenda, the timeline reminders and the notes on its own. Zoom's in-meeting AI Companion and Ask Gemini answer when asked; their documentation describes no unprompted turn. - **Who may give orders.** Facilitator: licensed organizers and presenters, internal meetings only. Zoom: host-configured, down to "only meeting hosts". Meet: whoever has the edition; the assistant does not take actions, so the question does not arise. - **What "do it" does.** Facilitator drafts a Word document and, in preview, tracks tasks in Planner. ZoomMate schedules calendar events and creates tasks after the meeting. Meet identifies next steps and leaves the assignment to a person. - **In which language.** Facilitator takes notes in the one language selected for the meeting. Zoom's in-meeting questions work in more than thirty languages. Ask Gemini launched in English. None of the three documents an assistant that answers each participant in that participant's language. That last line is where InterMIND starts. ## InterMIND: the host's room, with Mia inside it *Status, 19 September 2026: Mia in meetings is in preview — it is being tested inside InterMIND; any account can switch her on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). This section describes how she works in the preview.* Mia is the AI participant of an InterMIND meeting. She listens through the meeting transcript — she is not in the recording and not in the transcript herself — and every participant hears her in their own language: the answer is written natively in each language present in the room and voiced on each participant's device. She answers licensed participants of paid plans — a paid participant has her in every meeting they join, whoever hosts it; guests hear her answers to others. All of it runs on the organization's own cloud gateway (Azure OpenAI in the EU Data Zone by default, Google Vertex AI in the EU on request, or the organization's own model endpoint), with AI switchable off per organization; the details are in [the AI features documentation](https://intermind.com/docs/settings/ai-features). **Answers by name — or in the Help panel.** *"Mia, what did we agree on last time?"* aloud, or a line in the Help panel (⌘/ on a Mac, Ctrl+/ elsewhere) while the meeting is open; every line there is for her, no name needed, and you can hand her a document to read. She answers from this session's transcript, chat and shared documents, and from the recaps of the room's previous sessions. Asked aloud, she answers aloud to the whole room, each participant in their own language; asked in the panel, she answers there only, in your own thread, where nobody else sees it. Her name is needed once: after a spoken answer the conversation stays open for about a minute and as long as the exchange goes on, so anyone can follow up without her name; alone in the room with her, no name at all. Start talking and she stops. **Speaks up on her own — in the chat, never over a voice.** At the start she posts what the previous session decided and left open and what is on today's agenda note; halfway through and five minutes before the scheduled end, what has been decided, what is open and which agenda items were not touched; when someone takes something on, *"Noted: Anna — send the estimate by Friday"*; when a question hangs unanswered and the answer is in a previous recap, a shared document or the chat, she posts it with its source. She does not guess and does not search the web. *"Mia, be quiet"* stops her own notes for the rest of the meeting; she posts at most twenty an hour. **Acts on the host's word.** The host and moderators can tell her to act; other participants can ask questions but cannot give orders. She does it right away and confirms aloud and in the chat, where the host sees an **Undo** button for as long as the meeting lasts (*"Mia, undo that"* works too): - *"Mia, set up a follow-up next Thursday at three"* — a new meeting is created, its link lands in the chat, and the event goes into the commander's connected Google or Microsoft calendar in their own time zone. - *"Mia, note the decision: we go with vendor B"* — the note appears in the chat and is part of the recap. - *"Mia, send the recap to Pipedrive"* — the recap of this meeting also goes to that address from the host's confirmed recap address book. **Proposes the next step.** Before the end she weighs the agenda against what was said and proposes one concrete step — a follow-up for the items not covered, or an owner for a decision that was made but never stated. *"Mia, yes"* from the host executes it. Mia in meetings is a paid-plan feature: she answers licensed participants of paid plans, and her notes and actions run when the host is one. There is no separate switch — the organization's AI features switch turns her off with everything else. On the free plan she does not answer. What she does outside the room today — in the Help panel, in a channel and from the assistant you already use — is in [the AI secretary guide](https://intermind.com/blog/ai-secretary). ## The comparison, in one table | | Teams Facilitator | Zoom (AI Companion in-meeting / ZoomMate) | Google Meet (Ask Gemini / next steps) | InterMIND (Mia) | | --------------------------------------- | ---------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------- | | Speaks up unprompted during the meeting | Agenda, timeline reminders at midway and wrap-up, live notes, @mentions of absent participants | Not described in Zoom's documentation | Not described in Google's documentation | Start / halfway / wrap-up notes, commitments, stalled questions — in the chat | | Answers questions in the meeting | Q\&A from meeting and web content | Preset and free questions on the live transcript | Summaries, takeaways, catch-up, from captions and Workspace files | From transcript, chat, documents and previous recaps; voiced per listener | | Acts on a request | Word document; Planner tasks (preview); agenda edits | ZoomMate after the meeting: calendar events, tasks, documents, records | Next steps identified; assignment is manual | Follow-up meeting + calendar event, decision / action item into the recap, recap to a CRM address | | Proposes the next step itself | Not described | Not described | Not described | Before the end, executed on "Mia, yes" | | Who may give orders | Licensed organizers and presenters; internal meetings only | Host-configurable, down to hosts only (questions) | Anyone with the edition (no actions) | Host and moderators; others ask | | Undo of an action | Not described | Not described | Not applicable | Undo button in the chat; "Mia, undo that" | | Languages in one meeting | One selected language for the notes | "More than 30 languages" for questions | English at launch | Each participant in their own language | | Requirement | Microsoft Copilot license | Zoom Workplace Pro and above; ZoomMate from $20/user/month, North America first | Business Plus at launch (Ask Gemini); Business Standard and above (next steps) | Paid plans; on by default | | Where the output lives | Loop notes in the initiator's OneDrive; meeting chat; Recap | Meeting chat and summaries (Zoom); connected apps (ZoomMate) | Notes document and email | Meeting chat and the recap of the room | ## See it instead of reading about it - **[Read how Mia works](https://intermind.com/docs/settings/ai-features#mia-in-meetings)** — the documentation page, including who she answers and what the host can ask of her. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, monthly translation quality on real traffic, with the methodology public. --- ## FAQ **What is an AI meeting assistant?** An AI participant of the meeting that answers questions during the call from the transcript and the material it can reach, and — in its agentic form — speaks up on its own and takes actions on a participant's request. A note taker, by contrast, only writes after the call. **What does Microsoft Teams Facilitator do during a meeting?** According to Microsoft's documentation it posts the agenda from the invite or meeting notes into the chat, keeps timeline markers "with reminders at midway and wrap-up", writes collaborative real-time notes, summarizes decisions and open questions, answers questions from meeting and web content, and on request creates a Word document or edits the agenda; Planner task tracking is in preview. **Do I need a Copilot license for Facilitator?** Yes: "A Microsoft Copilot license is required to add Facilitator to a meeting or turn it on during a meeting." Unlicensed participants can read its notes and responses but cannot prompt it. **Can Zoom AI Companion answer questions during a meeting?** Yes. *Meeting questions with AI* lets participants ask about the live discussion, with presets such as "Catch me up" and "What are the action items?"; the host decides whether all participants, only internal ones or only hosts may ask. Zoom lists it for Workplace Pro and higher accounts, in more than 30 languages. **What is ZoomMate?** Zoom's AI teammate, generally available in North America since 1 June 2026 from $20 per user per month with AI credits. Zoom describes it creating documents, tasks and records after meetings and scheduling events in Google Calendar or Outlook; its launch page does not say whether these run autonomously or after confirmation. **Does Google Meet have an AI assistant during the meeting?** Ask Gemini in Meet answers a participant's questions during the call — summaries, decisions, action items, catch-up — from captions and Workspace files. It launched in English for Business Plus in September 2025. Suggested next steps appear afterwards in the notes document, where a person assigns them. **Can an AI meeting assistant schedule the follow-up meeting?** Depends on the platform. ZoomMate schedules calendar events after the meeting. Facilitator's documentation describes documents and Planner tasks, not calendar events. Meet leaves assignment to a person. InterMIND's Mia creates the follow-up meeting and the calendar event on the host's word, during the meeting, with an Undo. **Who controls what the AI assistant is allowed to do?** In Teams, only licensed organizers and presenters can turn Facilitator on or prompt it. In Zoom, the host sets who may ask questions. In InterMIND, the host and moderators can give Mia orders, other licensed participants of paid plans can ask her questions, and an owner or admin can switch the organization's AI features off altogether. **Can participants who speak different languages use one AI assistant?** Facilitator takes notes in the one language selected for the meeting. Zoom's in-meeting questions work in more than 30 languages, one per question. Ask Gemini launched in English. Mia answers each participant in that participant's language, in one meeting. **Is the AI assistant in the recording?** Mia is not: she listens through the transcript and her voice never crosses another participant's microphone, so she is neither in the recording nor in the transcript. Check the other platforms' documentation for their own model; Facilitator's notes are stored as a Loop file and treated as meeting transcript data. --- *Sources: [Microsoft Learn — Set up Facilitator in Microsoft Teams](https://learn.microsoft.com/en-us/microsoftteams/facilitator-teams){rel=""nofollow""}, [Microsoft Support — Facilitator in Microsoft Teams meetings](https://support.microsoft.com/en-us/teams/copilot/facilitator-in-microsoft-teams-meetings){rel=""nofollow""}, [Zoom Support — Meeting questions with AI](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0057748){rel=""nofollow""}, [Zoom — Zoom launches ZoomMate](https://news.zoom.com/zoom-launches-zoommate/){rel=""nofollow""}, [Google Workspace Updates — Ask Gemini in Meet](https://workspaceupdates.googleblog.com/2025/09/ask-gemini-in-google-meet.html){rel=""nofollow""}, [Google Workspace Updates — "Take notes for me" now captures "next steps"](https://workspaceupdates.googleblog.com/2025/02/google-meet-take-notes-for-me-next-steps.html){rel=""nofollow""}, [InterMIND documentation — AI features](https://intermind.com/docs/settings/ai-features). Vendors change plans, features, prices and language lists over time; check their pages for the current state. All facts checked September 2026.* # AI secretary for a team: what Mia does today in meetings, in the channel and with the calendar — and where today's tools stop (2026) - **An AI secretary keeps the clerical side of meetings:** the brief before, minutes and promises after, the follow-up in the calendar, the answer to "what did we decide" later. - **Incumbents stop somewhere.** Teams, Zoom and Google document a one-language record for the people the host chose; the next step is a person's click. - **InterMIND keeps the whole meeting in each member's language,** with Mia keeping the record, next to those tools rather than instead of them. Guests join free by link, no account; you pay only for active members. An AI secretary is the part of a secretary's job that is clerical rather than personal: preparing what a meeting needs, writing down what it produced, listing who promised what by when, putting the next meeting in the calendar and answering, a month later, what was decided and where it is written. It does not take the decision and does not sit in the chair; it keeps the paper in order so that the people who decide do not have to. The idea is older than the software. Any organization with more than a handful of meetings a week once had a person whose desk this was. Most teams of ten to two hundred never had that person — the job was spread across whoever typed fastest — and that is who the term "AI secretary" is being searched for by. This guide is the job first: what it consists of, how to hand each part over, a brief you can copy. Then the map: what the tools a team already runs on document under this heading, and what InterMIND's Mia does today. ## What an AI secretary is — and what it isn't Three jobs get called "assistant", and only one of them is the secretary's: | | What it does | When | What it leaves behind | | --------------------------- | --------------------------------------------------------------------- | ----------------------------------------- | ---------------------------------------------- | | **AI note taker** | Listens to the call and writes a summary | After the call | One document, one language, one recipient list | | **AI secretary** | Prepares, records, lists promises, schedules, answers from the record | Before, during and after, and weeks later | A record that is kept, assigned and findable | | **Chatbot over a document** | Answers questions about one file it was handed | When asked | Nothing | A note taker is one task of the secretary's. The difference is continuity: the secretary knows the previous meeting when the next one starts, knows who still owes what, and can be asked on a Tuesday afternoon what was agreed on the 3rd. A summary mailed once and forgotten is not a secretary; it is a transcript with a haircut. ## The six jobs of a secretary, in order Each of these is a task that can be handed over on its own. Hand over the ones that cost you the most time first. 1. **The brief before the meeting.** What the previous session decided, what is still open and who owes it, what today's agenda says. A good secretary posts this before anyone asks. 2. **The minutes.** What was decided, what stays open, what was disputed — each with a timestamp, so a dispute later goes back to the words that were said, not to memory. 3. **The list of promises.** Every "I'll send it by Friday", with the owner and the day, taken from the meeting itself rather than from someone's notes of it. 4. **The follow-up in the calendar.** When the host says "next Thursday at three", a meeting exists at that time with the same people, and the event is in the calendar in each invitee's time zone. 5. **The answer from the record.** "What did we agree with the distributor in March?" answered from the recaps, with a link to the place where it was said. 6. **The carry-over.** When the next recap is written, the organization's open items are judged against what was said — done, or not done with the reason — on the team's status page, and at the start of the next session they are named aloud, so nothing is quietly dropped. The first three are what every meeting tool now sells as "AI". The last three are where most of them stop, and they are the three that make the first three worth having. ## How to hand a job to an AI secretary **Before: give it the room, not a file.** A secretary that only sees what you paste into it has no memory. Hold recurring meetings in one place that keeps their history — a channel, a recurring room — so that "last time" means something to the software. Put the agenda where the meeting is, not in a separate document the assistant cannot read. **During: say outcomes aloud.** Every secretary, human or machine, writes down what was said. "So we go with vendor B" and "Anna, the estimate by Friday" are what make it into the record; a decision everybody understood but nobody said is not a decision the secretary can keep. If the assistant can be addressed in the room, address it by name for actions and let it listen for the rest. **After: read the list back, then assign.** The minutes are a draft until someone with authority has read them. Check three things: that each decision is a decision, that each promise has an owner and a day, that each open item is marked open rather than lost. Then let the follow-up go into the calendar. **Weeks later: ask the record, not the room.** The test of a secretary is whether a question about March is answered from March's record, with a link, rather than by a new meeting. Ask it the first time you would otherwise ask a colleague. ## A brief you can copy Hand this to any assistant that can see your meetings — in the room, in a channel or from the assistant you already use. Replace the brackets. > **Secretary brief — \[team or channel]**:br**Before each session:** post what the previous session decided, what is still open and who owns it, and today's agenda from \[where the agenda lives]. :br**During:** record every decision, every action item with owner and day, and every question that was raised and not answered. Do not infer; record what was said. :br**After:** send the recap to everyone invited, in their own language. List open items at the top. :br**Follow-up:** when \[host] names a date, create the meeting with the same people and put it in the calendar. :br**On request:** answer "what did we decide about X" from the recaps, with a link to where it was said. :br**Never:** take a decision, assign a task nobody accepted, or send anything to a new address without \[host] confirming. The last line matters more than the others. A secretary that acts without confirmation is a liability; one that drafts and waits is a colleague. ## AI executive assistant: the job and the part of it that already runs An *AI executive assistant* is the same role scoped to one person rather than a team: the executive's calendar, the executive's inbox, the executive's meetings. The queries overlap because the job overlaps, and it is worth separating what the software does from what the title implies. The executive assistant's work has four parts. Two of them run in software today, for a team as much as for one person: - **Meetings and their record.** Minutes, action items, carry-over and the calendar follow-up — the six jobs above. This runs. - **Answering from the record.** "What did I promise the board last month?" from the meetings themselves rather than from memory. This runs wherever the assistant can read the meetings. Two of them do not, or run only as drafts: - **Judgement about people.** Who to let into the calendar, who to put off, what the boss would say — this stays with a person, and an assistant that pretends otherwise is dangerous rather than helpful. - **The inbox.** Drafting replies is common; sending them unread is where most organizations draw the line, and rightly. So the part of an AI executive assistant that already runs is the secretary: the record and the calendar. The brief above is the same brief with one name in the brackets instead of a team's. ## Where today's tools stop The three platforms most teams already pay for each have something under this heading. The table lists documented behaviour only, from each vendor's own pages, by the six jobs of the secretary; the month each page was checked is in the *Sources* footer. | Job | Microsoft Teams (Facilitator, Copilot) | Zoom (AI Companion, ZoomMate) | Google Workspace (Gemini in Meet) | InterMIND (Mia) | | ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Brief before the meeting** | Facilitator posts the agenda in the meeting; needs a Copilot license; organizers and presenters only; not in external meetings | ZoomMate can "pull key information from Google Docs, open Jira issues, and surface recent Slack discussions" before a meeting | The Calendar event's description; nothing posted into the call | At the start of a channel's session, the previous decisions, open items and the agenda note; preview, switched on under Settings → Advanced ([Preview features](https://intermind.com/previews)) | | **Minutes** | Notes in a Loop file in the initiator's OneDrive; "only support meetings where a single language is spoken"; AI summary requires Teams Premium or a Copilot license | AI Companion summary on Pro and above; only the host can edit; "unauthenticated users will not receive an email summary" | "Take notes for me" writes a Google Doc to the organizer; "this feature supports one language at a time" | The recap — summary with timestamps, transcript, recording — read by each member in their own language; any member edits, with version history | | **List of promises** | Tasks in Planner, public preview | ZoomMate creates follow-up tasks; the launch page does not state whether autonomously or after confirmation | "Suggested next steps" in the notes; assigning is a person's click | Action items with owners and timestamps in the recap, edited by any member with version history | | **Follow-up in the calendar** | Not described for Facilitator | ZoomMate "schedules events in Google Calendar or Microsoft Outlook"; North America first, from $20 per user per month | Not described for Meet | A meeting at a local time with invitees, written to the connected Google or Microsoft calendar, from the assistant you use | | **Answer from the record** | Facilitator Q\&A in the meeting from meeting and web content; the AI recap afterwards requires Teams Premium or a Copilot license | "Meeting questions with AI" on the live meeting; preset "What are the action items?" | Ask Gemini in Meet answers from captions during the call; English only at launch, Business Plus | From the ⌘/ panel on any screen, with the open channel as its context, or from Claude, ChatGPT, Copilot, Gemini and any MCP client, over the meetings you attend | | **Carry-over** | Not described | Not described | Not described | The organization's open items judged when the next recap is written — done, or not done with the reason — on the team status page; preview, an admin switches team status pages on under Settings → Advanced ([Preview features](https://intermind.com/previews)) | Two things are the same across the three incumbents. The record is written in the language the meeting was held in — Google states it, Microsoft states it, Zoom documents a summary of the spoken transcript — and it reaches the people the host or an admin chose, in one copy. And the step from "next steps identified" to "a meeting exists on Thursday with these people" is, on the pages we checked, either a person's click or a product sold separately and in one region first. ## What Mia does today InterMIND is a communication space that sits next to Teams, Slack or Google Workspace, and Mia is the secretary inside it. This is what she does on a paid plan today, in the order a team meets it. **The record stays in each member's language, and it is kept.** Every meeting in a channel ends with a recap: the summary with timestamps, the transcript and the recording, at one permanent link, read by each signed-in member in their own language — the record is translated per reader, not written once in the language the room happened to use. It arrives by email, as a message in the channel and as a link in the calendar event. Any member edits it, every edit keeps author and revision history, and the channel keeps the recap of every past session. A copy can go to a CRM address from the channel's Recap copy setting. The [recap documentation](https://intermind.com/docs/meetings/recap) has the details. **Ask her from any screen.** The right panel of the app — ⌘/ on a Mac, Ctrl+/ elsewhere, or *Help* in the sidebar — is Mia when you are signed in on a paid plan. She knows the screen you are on and answers from your meetings, chats and files; she can prepare a meeting link or a message for you to confirm, and the conversation is saved. With a channel open, the same panel reads that channel's chat, files and recaps, names the channel in its header, and marks the answer with where it was asked — one thread, whatever screen you are on. On a paid plan she can also search the web and gives the address of what she found; an admin can turn that off. Without a paid plan she answers from the documentation. **Work from the assistant you already use.** Every registered account can connect Claude, ChatGPT, Copilot, Gemini, Cursor or any MCP client to InterMIND, and the assistant acts as you. Reading: the newest recaps, a phrase searched over your recaps with a snippet and the link, the transcript by speaker, your meetings and channels, a channel's messages in your language, your documents. Acting: a meeting link now, a meeting at a local time written to your connected Google or Microsoft calendar with the invitees, a message posted into a channel as you — translated for every reader. So *"What did we agree with Acme last week? Check my InterMIND recaps"* and *"Set up a call with the Lyon team Thursday at three and put it in my calendar"* are one line each, in whichever assistant you keep open. The assistant cannot join a meeting, speak in it or change your settings; a call made through it counts as your activity. Setup per client is in [AI assistants (MCP)](https://intermind.com/docs/integrations/mcp). **In the meeting itself, as a preview.** As of 18 October 2026, Mia in the meeting is a preview feature any account switches on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one): she answers by name aloud, each participant in their own language, posts what the previous session decided at the start, notes a commitment the moment it is spoken, and on the host's word schedules the follow-up into the commander's calendar — with an Undo button in the chat. The open items she names at the start of the next session come from the team status pages, a preview an organization's admin switches on the same way. What she does in the room is described in [the AI meeting assistant guide](https://intermind.com/blog/ai-meeting-assistant-in-the-meeting); neither is switched on for every organization yet. A guest joins by link, without an account and at no cost — from a phone, in the browser — and hears the meeting live in their own language. There is no record for a guest afterwards: the account is free, and it is what makes the record reachable. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing) — joined a meeting, wrote in a chat or asked Mia; members who go quiet keep their access at no cost. All of it runs on the organization's chosen AI gateway — Azure OpenAI in the EU Data Zone by default, Vertex AI in the EU on request, or Bedrock in the organization's own AWS account — with nothing kept after processing, and the AI features switch turns Mia off with everything else. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. A secretary is judged a month later, not the same afternoon: by whether the question about March gets an answer with a link. Hand over the six jobs one at a time, keep the last line of the brief, and read the list back before it goes out. ## FAQ **What is an AI secretary?** An AI assistant that carries the clerical work around a team's meetings: the brief before, the minutes and the list of action items after, the follow-up meeting in the calendar, and answers from the record weeks later — "what did we decide about X, and where is it written". It differs from an AI note taker by continuity: it knows the previous meeting when the next one starts and who still owes what. **What does an AI executive assistant do?** The same job scoped to one person: that person's meetings, record and calendar. The part that runs in software today is the secretary's — minutes, action items, carry-over, the follow-up in the calendar, answers from the record. Judgement about people and sending mail unread stay with a person; most tools draft and wait for a click. **Can an AI secretary schedule meetings?** Depends on the tool. On the vendor pages checked for this post, Zoom's ZoomMate "schedules events in Google Calendar or Microsoft Outlook" and is sold separately, North America first; Microsoft's Facilitator and Google's Meet notes do not describe scheduling. In InterMIND, an assistant connected over MCP creates a meeting at a local time and writes it to your connected Google or Microsoft calendar with the invitees; in the room, Mia does the same on the host's word as a preview feature. **Can an AI assistant take minutes in a meeting?** Yes, on the three platforms most teams already run on: Teams (Facilitator notes, Copilot recap), Zoom (AI Companion summary) and Google Meet ("Take notes for me") each write a summary after a transcribed meeting, in the one language the meeting was held in, for the recipients the host or admin chose. InterMIND writes the recap with timestamps and each member reads it in their own language, with edits kept in version history. **Is an AI secretary safe for confidential meetings?** Look at three things in the documentation: where the model runs, what is kept after processing, and who may give it orders. In InterMIND the organization chooses the AI gateway — Azure OpenAI in the EU Data Zone by default, Vertex AI in the EU on request, or Bedrock in its own AWS account — nothing is kept after processing, Mia reads only the meetings you attend, and an action in the room runs only on the host's or a moderator's word, with undo. **Does Microsoft Copilot work as a secretary in Teams meetings?** Partly, as documented: Facilitator posts the agenda and notes during the meeting and tracks tasks in Planner in public preview; it needs a Copilot license, works for organizers and presenters in internal meetings, and takes notes in one selected language. Scheduling a follow-up from the room and carrying open items into the next session are not described on Microsoft's Facilitator pages. --- *Sources: [Microsoft Learn — Set up Facilitator in Microsoft Teams](https://learn.microsoft.com/en-us/microsoftteams/facilitator-teams){rel=""nofollow""}, [Microsoft Support — Facilitator in Microsoft Teams meetings](https://support.microsoft.com/en-us/teams/copilot/facilitator-in-microsoft-teams-meetings){rel=""nofollow""}, [Zoom Support — Meeting questions with AI](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0057748){rel=""nofollow""}, [Zoom — Zoom launches ZoomMate](https://news.zoom.com/zoom-launches-zoommate/){rel=""nofollow""}, [Google Workspace Updates — Ask Gemini in Meet](https://workspaceupdates.googleblog.com/2025/09/ask-gemini-in-google-meet.html){rel=""nofollow""}, [Google Workspace Updates — "Take notes for me" now captures "next steps"](https://workspaceupdates.googleblog.com/2025/02/google-meet-take-notes-for-me-next-steps.html){rel=""nofollow""}, checked September 2026; [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""} and [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}, checked August 2026; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}, checked October 2026; InterMIND documentation — [AI features](https://intermind.com/docs/settings/ai-features), [Recap](https://intermind.com/docs/meetings/recap), [AI assistants (MCP)](https://intermind.com/docs/integrations/mcp). Vendors change plans, features, prices and language lists over time; check their pages for the current state.* # AirPods Live Translation: what it does well, and where a meeting needs more - **It does the face-to-face job well.** One person in front of you, translated into your ear on your own compatible AirPods and a recent iPhone. - **A meeting is a different shape.** Per device, one conversation partner at a time; the other side needs the same gear, and a group call cannot wear earbuds. - **InterMIND keeps the whole meeting in each member's language,** voice, chat and notes for every participant, on whatever they already join with. Guests join free by link, no account; you pay only for active members. Apple's Live Translation on AirPods is the feature that made "translation in your ear" mainstream. It's genuinely good — for the job it was built for. This explainer covers what it does, what it needs, and the exact line where a real meeting asks for something Apple's feature isn't shaped to give. --- ## What it is You wear compatible AirPods, someone speaks to you in another language, and you hear a translation in your ear — while the feature lowers their original voice underneath. It's built for the traveler-and-local moment: a shop, a taxi, a conversation with one person in front of you. Point-to-point, low-friction, and it feels natural because there's no screen between you. ## What it needs By Apple's own documentation, as of August 2026: - **Hardware:** AirPods Pro 3, AirPods Pro 2, AirPods 4 with Active Noise Cancellation, or AirPods Max 2, on the latest firmware. - **A recent iPhone:** an Apple Intelligence-capable iPhone (iPhone 15 Pro and newer), running iOS 26 or later. - **Languages:** English, French, German, Spanish, Portuguese, Italian, Chinese (Mandarin, Simplified and Traditional), Japanese, and Korean. - **Region:** it launched in the US first; EU availability arrived with iOS 26.2 after extra engineering for the Digital Markets Act. For a phrase with one person, none of that is a problem. The limits only start to bite when the situation changes shape. --- ## Where a meeting is a different job Look at the model, not the polish. AirPods Live Translation is **one-to-one, on your device.** It translates the person in front of you, into your ear, using your phone and your earbuds. That's exactly right for face-to-face — and exactly the wrong shape for a group call: - **It's per-device, not per-room.** For the translation to be mutual, the other person needs their own compatible AirPods and their own recent iPhone. In a call with five people, that assumption breaks for almost everyone. - **It's one conversation partner at a time.** A meeting has several people talking, interrupting, thinking out loud. Earbuds translating "the person in front of you" don't map onto a room. - **No shared hardware in a video call.** You can't hand a Teams or Zoom call a pair of AirPods. Meeting translation has to live in the *call*, not in anyone's ears. None of this is a knock on Apple's feature. It's a category boundary: **AirPods translate a face-to-face exchange; a meeting needs the whole room translated for everyone.** --- ## What "the whole room" means A meeting translator turns the *call itself* multilingual: every participant speaks their own language, and every participant hears everyone else in **their** language, live, for the whole meeting — no matching earbuds, no shared phone, no "you both need the same gear." That's [real-time meeting translation](https://intermind.com/blog/real-time-meeting-translation), and it's an architecture, not a better pair of earbuds. Where Apple translates one person into your ear on your hardware, meeting translation translates the room for everyone, on whatever they're already using to join the call. --- ## Where InterMIND fits InterMIND does the group-call job that earbuds structurally can't. It starts with one person — you open the room and send the link; the others join free, without an account, each in their own language: - **The whole call is multilingual.** Each participant hears the meeting in their own picked language, simultaneously — no shared device, no matching hardware. [23 languages live on voice](https://intermind.com/features/realtime-translation), chat and shared notes. - **Per-listener audio, live.** Each participant hears it as it is said. Five people, five languages, one room. (Under the hood: [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Webinars and conferences** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant on their own listening language: [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation). - **Documents too** — a PDF or DOCX in the meeting, each viewer in their language. - **Quality you can audit** — per-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark). Keep the AirPods for the taxi and the shop; they're great at it. When it's a *meeting* — several people, several languages, no shared hardware — that's the job InterMIND was built for. --- ## Try it - **[Try the live demo](https://intermind.com/demo)** — hear a real meeting translated live, per listener, across a whole room, in any of 23 languages — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month quality on real traffic, methodology included. - The category, in full: [*Real-time meeting translation*](https://intermind.com/blog/real-time-meeting-translation). — The Mind.com Team --- *Sources: [Apple — Use Live Translation with your AirPods](https://support.apple.com/en-us/123185){rel=""nofollow""}, [Apple — Live Translation on AirPods expands to the EU](https://www.apple.com/ie/newsroom/2025/11/live-translation-on-airpods-expands-to-the-eu/){rel=""nofollow""}. Apple expands device and language support over time; check Apple's support pages for the current state. All facts checked August 2026.* # All-hands meeting: agenda, format, examples — and how every office hears it in its own language (2026) - **Everyone in the room, with a floor to ask.** The same three numbers, one decision, one story from the work, and the longest slot for questions. - **The record is written once.** Teams, Zoom, Google and Slack return the summary in the meeting's language; the office that joined late gets it only if shared. - **InterMIND keeps the whole meeting in each member's language,** questions in the channel, the call and the recap. Guests join free by link, no account; you pay only for active members. An all-hands meeting is the one meeting the whole company attends: leadership shares the numbers, the decisions and the stories everyone should know, and everyone gets to ask about them. The name comes from the ship's call "all hands on deck" — every person aboard, whatever their job, on the same deck at the same time. That is the whole test of the format. A meeting that half the company watches as a recording, or follows through a summary email the next morning, is a broadcast, not an all-hands. This guide is the craft first — what belongs in an all-hands and what doesn't, how long and how often, an agenda template you can copy, three filled-in examples — then the mechanics: where the all-hands lives in the tools your company already uses, and what happens to the questions and the answers after the call. Because the all-hands has a second audience: the people who were in another time zone, in a customer meeting, or on leave, and who find out what was said from whatever the meeting left behind. ## What an all-hands meeting is — and what it isn't Three company-wide formats are often called the same thing, and they are built for different jobs: | | Who speaks | What it produces | Cadence | | ------------- | -------------------------------------------------------------- | ------------------------------------------------------------------- | --------------------------------------------------------- | | **All-hands** | Leadership presents; anyone asks; teams present their own work | A shared picture of where the company is, and answers on the record | Weekly to quarterly, by company size | | **Town hall** | One or a few executives; the audience asks | Answers to the audience's questions on one theme | On an occasion: a reorganisation, a results day, a change | | **Broadcast** | One speaker | A recording and a transcript | When there is an announcement | The lines blur, and in many companies "town hall" and "all-hands" are the same calendar event. The useful distinction is who gets to speak: an all-hands has a floor, a town hall has a microphone that goes to the audience, a broadcast has neither. If nobody outside the leadership team said a word, it was a broadcast, whatever the invitation called it. An all-hands is not a status meeting with everyone invited. A team's weekly numbers belong in the team's weekly; the all-hands carries the three numbers that describe the company, the one decision that changes something for everyone, and the one story that shows the work. Everything else is a message in the channel. ## What to include: the standard format An all-hands that people keep attending has five parts, in this order: 1. **The numbers, the same three every time.** Revenue or usage against plan, the one operational number the company is steering by, and headcount or hiring. Three, not thirteen; the same three, so that the room learns to read them and notices when one moves. Ten minutes, with the slide posted in the channel beforehand. 2. **One decision, explained.** The thing that changed since the last all-hands and why. Not a list of changes — the one that affects the most people, told by the person who owns it, with the reasoning and the trade-off that was rejected. A decision explained once to everyone saves twenty one-to-one explanations of it. 3. **One story from the work.** A team shows something it shipped, a customer win, a support case that was handled well. The point is that a person in another team sees what their colleagues actually do. Ten minutes, the team presents, not the executive. 4. **Questions — the ones submitted in writing and the ones asked live.** The longest slot and the one that makes the format. Questions collected in the channel during the week come first, read aloud and answered on the record; then the floor is open. A question the company asked and leadership did not answer is the all-hands everyone remembers. 5. **The close: what was decided, what is open, who follows up.** Two minutes. The decision restated in one sentence, the questions that were parked with a name and a date next to each, and where the recording and the summary will be. What stays out: anything that needs a decision from the room. An all-hands of 200 people does not decide; it informs and it answers. Decisions are made in the leadership weekly and explained in the all-hands. Welcomes of new colleagues go at the start, in one minute per person; birthdays, anniversaries and thank-yous go into the channel. ## How long, how often The cadence follows the size of the company, because the cost of an all-hands is the headcount multiplied by the length: | Company size | Cadence | Length | What fits | | ----------------- | --------------------------------------------- | --------- | -------------------------------------------------------------------------- | | Up to 30 people | Weekly | 20–30 min | Numbers, one update, open questions | | 30–150 people | Every two weeks or monthly | 45 min | The five-part format above | | 150–1,000 people | Monthly | 45–60 min | The five parts, plus one team story per region | | Over 1,000 people | Quarterly, with regional all-hands in between | 60 min | Results, strategy, a long Q\&A; team stories move to the regional meetings | Two rules hold at every size. The all-hands has a fixed slot the company can plan around — the first Thursday, the last Friday — because a meeting that moves is a meeting people miss. And it is scheduled for the offices that find it hardest: a company spread from Lisbon to Singapore alternates the hour between a European morning and a European evening, so the same office is not the one joining at 9 p.m. every month. ## How to run one: before, during, after **The week before, collect questions where the company already talks.** Post one message in the all-hands channel: "All-hands on Thursday — what should leadership answer? Reply here, or send it to me directly if you'd rather not sign it." Questions that come in writing are already half-answered: leadership sees the pattern, prepares the numbers and arrives with an answer instead of a reaction. Post the three numbers and the agenda in the same channel the day before, so the meeting starts with the slide already read. **During the meeting, protect the question slot.** The numbers run over; the story runs over; the Q\&A is what gets cut, and the Q\&A is the all-hands. Run the first three parts to the minute, and open the floor with the written questions — in the order they arrived, with the name of the person who asked unless they asked not to be named. Answer live questions through the raised hands in the order they went up, and when a question cannot be answered yet, say so and give it a date rather than an answer that will be corrected next week. The moderator is not the CEO: a person who is not answering keeps the queue, the clock and the chat. **After the meeting, publish what was said — the same day, to everyone, including the people who weren't there.** The decision in one sentence, the questions with their answers, the parked questions with a name and a date. Put it where the next all-hands will find it, next to the recording. The all-hands that lives only in the memory of the people who attended is an all-hands the company does not have. ## An all-hands meeting agenda template > **\[Company] — All-hands, \[month]**:br**Date:** \[date] · **Time:** \[start]–\[end] · **Link:** \[meeting link] :br**Purpose:** everyone hears the same three things and gets to ask about them. :br**Moderator:** \[name — keeps the queue and the clock] · **Notes:** \[name or "the recap"] :br**Pre-reads:** the three numbers (posted in the channel the day before), \[link] > > **1. Welcome and new colleagues** — \[moderator] — 3 min — *information*:br > One minute each: name, team, what they will work on. > > **2. The quarter in three numbers** — \[CEO or lead] — 10 min — *information*:br > \[Number 1] against plan · \[number 2] · hiring. Same three as last time. > > **3. One decision, explained** — \[decision owner] — 10 min — *information*:br > \[What changed, why, what was rejected.] > > **4. From the work** — \[team] — 10 min — *information*:br > \[What shipped, who it is for, what it took.] > > **5. Questions** — all — 15 min — *discussion*:br > Written questions first, in the order received; then the floor. > > **6. Close** — \[moderator] — 2 min :br > The decision in one sentence · parked questions: \[name] — \[question] — by \[date] · where the recording and the summary will be. ## Three filled-in examples ### Monthly all-hands, 80 people — 45 minutes > **Purpose:** everyone hears the same three things and gets to ask about them. :br**1. Welcome: two new colleagues in support and one in sales** — Ana — 3 min — *information*:br**2. September in three numbers: ARR against plan, active customers, open roles** — Tomasz — 10 min — *information*:br**3. Why we are moving support to a follow-the-sun rota from November** — Priya — 10 min — *information*:br**4. The onboarding redesign: what shipped and what the first customers said** — the product team — 10 min — *information*:br**5. Questions: four submitted in writing, then the floor** — all — 10 min — *discussion*:br**6. Close** — Ana — 2 min ### Weekly company meeting, 20 people — 25 minutes > **Purpose:** the week's numbers, one update, open questions. :br**1. The week in three numbers** — founder — 5 min — *information*:br**2. One update: the new pricing page goes live Monday** — Mateusz — 5 min — *information*:br**3. One demo: what Lena built this week** — Lena — 5 min — *information*:br**4. Questions** — all — 8 min — *discussion*:br**5. Close** — founder — 2 min ### Quarterly all-hands, 600 people in four regions — 60 minutes > **Purpose:** the quarter's results, next quarter's priorities, and the company's questions answered on the record. :br**1. Q3 results in three numbers** — CEO — 10 min — *information*:br**2. Next quarter's three priorities and what we stop doing** — CEO — 10 min — *information*:br**3. One decision, explained: the new sales territories** — head of sales — 10 min — *information*:br**4. From the work: one story from the Bangalore team** — the team — 8 min — *information*:br**5. Questions: submitted in each region's channel during the week, then the floor** — all — 20 min — *discussion*:br**6. Close** — moderator — 2 min :br > Pre-reads: the results deck, posted in the all-hands channel on Monday. Nine more agendas, from the daily stand-up to the board meeting, are in [meeting agenda examples](https://intermind.com/blog/meeting-agenda-examples); the anatomy of the format itself is in the [meeting agenda template](https://intermind.com/blog/meeting-agenda-template) guide. Notice what the three examples have in common: the question slot is the longest or the second longest, the numbers are the same three every time, and every example ends with the close — the one item that produces the record. ## Where the all-hands lives in the tools you already use Each major platform has a format for the company-wide meeting and a place for what it leaves behind, and each stops at a different point. Documented behaviour only, from the vendors' own pages, with the month each page was checked: | Platform | The format and the record | What comes back afterwards, and in whose language | | -------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | Recaps "are available after Teams events, including meetings, town halls, webinars, and calls, that were recorded or transcribed", with "the event recording, transcript, shared files, notes, custom summary, agenda, and follow-up tasks"; the AI parts — generated summary, speaker markers, AI notes — are intelligent recap, which requires Teams Premium or a Microsoft 365 Copilot license (checked August 2026) | The recap lives in the event chat and the calendar event; "guests and external attendees can view the recording only if it's explicitly shared with them". The recap is generated from the transcript in the language the meeting was held in; in a town hall the translated captions are a pool the organizer pre-selects — six languages, ten with Teams Premium — and captions are not saved (checked August 2026) | | **Zoom Workplace** | Meeting summary with AI Companion is generated from the meeting in three sections — quick recap, summary, next steps — on paid Zoom Workplace plans; AI Companion can also draft the agenda when the meeting is scheduled (checked October 2026) | The summary is sent by email, listed on the Summaries page and can be posted to the meeting's group chat; participants receive it when the host chose to share it, "only the host can edit the summary", and "unauthenticated users will not receive an email summary". Zoom lists 32 summary languages; the documentation does not state that a summary can be produced in a different language per participant (checked August 2026) | | **Google Workspace** | For eligible Workspace editions and Google AI plans, *Take notes for me* is switched on in Calendar when the event is created (checked October 2026) | The notes arrive as a Google Doc after the meeting, shared with all guests, organization guests or hosts only, per the setting; the feature supports one language at a time — multiple languages spoken in the same meeting are not supported (checked October 2026) | | **Slack** | Huddles: on paid plans "up to 50 participants, but only 25 can enable video at a time"; "up to two people in a huddle can share their screen at a time". The agenda is a canvas from a template, shared in the channel (checked September 2026) | A huddle has "a dedicated message thread to share notes, links, and files", and the canvas stays in the channel; what was said in the call is not in it unless someone types it (checked October 2026) | Two things are the same everywhere. The record is written once, in the language the meeting was held in; and the person who joined by link without an account, or from another time zone the next morning, gets it only if someone shares it with them. ## How the questions and the answers come back InterMIND is a communication space where a meeting lives in a channel, so the all-hands has an obvious home: a channel the whole company is a member of. The questions of the week arrive there as replies, each office typing in its own language and reading the others in its own; the three numbers and the deck are posted there the day before — and during the call the questions list, posted as a note, goes on every screen next to the video tiles with *Share to conference*, read by each participant in their own language; and if the agenda or the slides are drafted somewhere else, they can land in the channel by email — the channel's owner gives it an address of its own, and a message sent to it appears as a regular message with the sender named and attachments kept. The meeting itself is the channel's own room, 50 to 1,500 participants depending on the host's plan. The host decides what the room may do: in the gear menu of the participants list, the host locks screen sharing for everyone but themselves, and the lock is saved on the meeting, so the setting made for this month's all-hands is still in force next month. When the all-hands runs as a meeting by link instead — with contractors or a partner company in the room — the same menu also locks the microphone, the camera, reactions, and the chat for guests outside the host's team. Raising a hand stays available under every lock, so the queue for the question slot works in a room where microphones are off until called on. When several things are shared at once, **Present to everyone** puts the one that matters on the main stage of everyone in the room at that moment; anyone sharing can press it. The host can start a server recording; every participant sees that it is running. When the call ends, the recap is written from the meeting itself: a summary, the points marked agreed, open or disputed, the action items with owners, each line keeping its timestamp; the transcript and the recording sit next to it. It arrives by email, as a message in the channel and as a link in the calendar event, and every signed-in member reads it **in their own language** — the record is translated per reader, not written once in the language the room happened to use, which is what makes "the office that joined at 7 a.m. and the one that joined at 9 p.m." one audience rather than two. Any member can correct the summary, every edit keeps its author and revision history, and the channel keeps the recap of every past session, so the answer leadership gave in March is one click away in October. The host can add a recap copy to any address — an HR tracker's inbound mailbox, a CRM — so the parked questions reach the system that follows them up without anyone forwarding anything; where a system needs fields rather than an email, the same recap is a Zapier trigger, a webhook and an API. In an organization with team status pages on, the open items of earlier sessions — the parked questions with their owners — are judged when the next recap is written, done or not done from what was said, with the verdicts on the organization's status page rather than in the recap, and at the start of the next session Mia names the open items and their owners, so last month's "we'll come back to you on that" is spoken about rather than lost. Team status pages are a preview feature: an organization's admin switches them on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). A guest joins by link, without an account and at no cost — from a phone, in the browser — and hears the meeting live in their own language. There is no record for a guest afterwards — the account is free, and it is what makes the record reachable. The host provides the room and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing); members who go quiet keep their access at no cost. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. The all-hands as a craft survives every tool: somebody still has to choose the three numbers, explain the one decision and protect the question slot. What doesn't have to survive is the second job — writing up the answers by hand after the call, in one language, for the offices that read others. ## FAQ **What is an all-hands meeting?** An all-hands meeting is a regular meeting that the whole company attends, where leadership shares the numbers, the decisions and the stories everyone should know, and anyone can ask questions. The name comes from the naval call "all hands on deck". It differs from a town hall, which is built around the audience's questions on one occasion, and from a broadcast, where only one side speaks. **What is the purpose of an all-hands meeting?** To give everyone in the company the same picture at the same time — where the company stands, what changed and why — and to answer the company's questions on the record. A secondary purpose is visibility between teams: a person in support sees what engineering shipped, and the other way round. It is not for making decisions; those are made in smaller meetings and explained in the all-hands. **How long should an all-hands meeting be?** Twenty to thirty minutes for a company of up to thirty people, forty-five minutes for most companies, and an hour for a quarterly all-hands of a large company. The length is set by the question slot: if the Q\&A is the part that gets cut, the meeting is too short or the first three parts are too long. **How often should you have an all-hands meeting?** Weekly up to about thirty people, every two weeks or monthly up to a few hundred, monthly up to a thousand, and quarterly above that with regional all-hands in between. Whatever the cadence, the slot is fixed — the same day of the week or month — so the company can plan around it. **What is the difference between a town hall and an all-hands meeting?** In most companies they are the same calendar event, and the words are used interchangeably. Where a distinction is drawn: an all-hands is the recurring company meeting with a fixed agenda — numbers, a decision, a story, questions — while a town hall is held on an occasion, is built around the audience's questions to one or a few executives, and often has a larger, more passive audience. The test is who gets to speak: in an all-hands, teams present their own work. **What should be on an all-hands meeting agenda?** Five things, in order: a welcome for new colleagues; the same three company numbers as last time; one decision, explained by its owner; one story from the work, presented by the team that did it; and the questions — written ones first, then the floor — followed by a two-minute close that restates the decision and lists the parked questions with a name and a date. The template above is the blank version. **How do you make an all-hands meeting engaging?** Collect questions in writing during the week and answer them by name; let teams present their own work instead of having an executive summarise it; keep the numbers to the same three so people learn to read them; and keep the question slot longer than any other. An all-hands people find engaging is one where something they asked was answered. **Who runs an all-hands meeting?** The CEO or the head of the company usually presents the numbers and the strategy, but the meeting is run by a moderator who is not answering questions — often the chief of staff, the head of people or an office manager — who keeps the queue, the clock and the chat, reads the written questions and calls on the raised hands in order. --- *Sources: [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""}; [Microsoft — Start, stop, and find meeting recordings in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/start-stop-and-find-meeting-recordings-in-microsoft-teams){rel=""nofollow""}; [Microsoft — Use live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Zoom — Supported languages for Zoom AI features](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0078144){rel=""nofollow""}; [Zoom — Generating meeting agenda with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0081706){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Use huddles in Slack](https://slack.com/help/articles/4402059015315-Use-huddles-in-Slack){rel=""nofollow""}; [Slack — Meeting agenda template](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Vendors change plans, features and language lists over time; check their pages for the current state. Each table cell names the month its fact was checked — the earliest checked August 2026, the latest checked October 2026.* # Best AI translation tools for conferences, events, and meetings (2026): an honest comparison - **No single winner, because "conference" hides several jobs.** Interpretation for an audience, a working meeting where everyone speaks, or translated captions; name your job first. - **Most tools translate the spoken moment and stop.** Chat, notes, documents and the after-record stay in the speaker's language; ask how much comes back in yours. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes, documents and the recap, for the working-meeting job rather than the stage. Guests join free by link, no account; you pay only for active members. If you typed *"best AI translation tools for conferences,"* *"real-time interpretation software,"* or *"which tools support multilingual simultaneous interpretation,"* you've probably noticed the listicles all blur together. Every tool claims "real-time," "AI-powered," and "multilingual," and most of them mean genuinely different things by it. One subtitles a webinar. One streams a human interpreter's audio to attendees' phones. One is a $300 earbud. These are not the same product, and picking the wrong category is the most expensive mistake here. But there's a deeper split the listicles miss entirely — and it's the one that actually matters once the call is over. **Almost every tool on every list translates one thing: the spoken moment.** Someone talks, you hear it in your language, and that's the whole product. The instant the words stop, the translation stops. The chat is still in the speaker's language. So are the shared notes. So is the contract someone dropped in. So is the follow-up. So is the support thread when something breaks. A meeting is not just the audio. It's the messages, the notes, the documents, the notifications, the help you read mid-call, the conversation with support afterward, and the record you keep. **The honest question isn't "how good is the voice" — it's "how much of the meeting does it actually translate?"** That's the axis this guide is built on, and it's where the field separates hard. So this guide does the part the listicles skip: it names the three *jobs* people mean, gives you the questions that tell them apart — including the surface-coverage one nobody asks — and *then* compares named tools. We make one of them ([InterMIND](https://intermind.com){rel=""nofollow""}), and we'll say where it fits and where it doesn't — but the questions below are vendor-neutral and work on any tool, including ours. > This is the comparison companion to our foundational guide, [*Real-time meeting translation: how it works, and how to evaluate one*](https://intermind.com/blog/real-time-meeting-translation). If you want the deeper "how does this work under the hood" version, start there. New to interpretation as a category? Start with [*interpretation vs translation and the types of interpretation*](https://intermind.com/blog/interpretation-vs-translation) for the definitions, then [*Simultaneous interpretation: booth, RSI, or AI*](https://intermind.com/blog/simultaneous-interpretation-guide) for the modes and the costs. --- ## First: the three jobs hiding under one search Almost every tool in this space does one of three jobs well. Naming them is half the decision. 1. **Simultaneous interpretation delivery** — get *audio* (a human interpreter's, or a machine's) to a room or to attendees' devices, in real time, often one-directional (a stage to an audience). Think large events, parliaments, webinars. Tools: Interprefy, KUDO, Boostlingo, Akouo, Verspeak. 2. **Conversational meeting translation** — a working meeting where *several* people each speak, type, read, and listen in their *own* language, both directions, at once. Think a sales call, a standup, a partner negotiation. This is the hardest job and the smallest category. 3. **Caption / transcript translation** — translate the *text* of what's said: live subtitles, post-call transcripts, AI notes. Think Zoom/Teams/Meet captions, Otter, AI notetakers. A tool can handle job 1 and be useless for job 2. A captioning add-on (job 3) is not interpretation at all — it's reading, not hearing. Decide your job first. --- ## The questions that actually separate tools Run any candidate through these. They cut through the marketing faster than any feature matrix. The last one is the one no listicle asks — and it's usually the deciding one. ### 1. One speaker, or everyone at once? Event tools optimize for **one source → many listeners** (a speaker on stage, an audience listening). Meeting tools have to handle **N people each speaking and listening in different languages, simultaneously, both directions.** If your use case is a four-person call where everyone talks, a one-directional event platform will feel wrong no matter how good its audio is. ### 2. Do listeners *hear* it, or *read* it? Captions (job 3) are a reading experience — subtitles, not audio. They're great for accessibility and webinars where one person presents. They're poor for a discussion, because you can't read four people's subtitles and still react to each other. If you need spoken translation, rule out anything whose "translation" is text-only. ### 3. Machine, or human-in-the-loop? KUDO, Interprefy, and Boostlingo are built around **routing human interpreters** (with AI as an option). That's the right answer for a UN-grade session where a mistranslation is a liability. It's the wrong cost structure for a Tuesday standup. AI-only tools (Wordly, DeepL Voice, InterMIND) trade certified-human accuracy for instant, per-meeting, no-booking availability. Know which trade you're making. ### 4. Whose voice comes out? Most machine tools replace every speaker with **one generic synthetic narrator** — eight people, one robot voice. A few keep the *speaker's own voice* via zero-shot voice synthesis, so a listener hears the translation in a voice recognizably the speaker's. In a real conversation that's the difference between a discussion and a transcript read aloud. (We wrote up why this is hard and how it works in [*Speak in your own voice — in a language you don't speak*](https://intermind.com/blog/own-voice-translation).) ### 5. How much of the meeting does it actually translate? *(the one nobody asks)* This is the question that should be first, not last. Voice is the demo; it's not the meeting. A real working session generates **a whole communication surface** around the audio: - **The chat** — links, decisions, side-questions typed while someone else talks. - **The shared notes** — the agenda, the action items, the doc everyone edits live. - **The documents** — the contract, the deck, the spreadsheet dropped in for review. - **The in-product help** — what you read when you can't find a setting mid-call. - **The support conversation** — what happens, days later, when something breaks. - **The after-record** — the summary, the digest, the transcript you actually keep and forward. Most tools translate *the audio and nothing else*. Everyone hears the call, then opens a chat log, a notes pane, and a follow-up email all still in the speaker's language, not the reader's. The translation evaporated the moment the talking stopped. Ask any candidate plainly: **after the audio, what else comes back in my language?** If the answer is "captions," you have a voice tool with a transcript bolted on — not a translated meeting. This single question reorders most shortlists. ### 6. What happens to the audio — and where does it run? For anything regulated — legal, medical, HR, finance — ask plainly: **is the call recorded or the voice stored, and does any of it leave your jurisdiction?** Some tools retain audio for model training; some store a voiceprint to do voice cloning; some send your meeting content to a US-hosted model the moment they generate a summary. This is a procurement gate, not a nice-to-have. (Our own answer: the live session retains nothing, and everything derived from a meeting goes to one AI gateway in an EU region, chosen by the organization, with zero data retention and no training on customer content — see [*the GDPR audit*](https://intermind.com/blog/gdpr-audit-what-we-closed) and [*where one meeting actually runs*](https://intermind.com/blog/where-one-intermind-meeting-actually-runs).) --- ## The contenders, sorted by job The tools below are the names that come up most for conference and meeting translation in 2026. We've grouped them by the three jobs above so you compare like with like. ### For large events & simultaneous interpretation delivery (job 1) - **Interprefy** — remote-simultaneous-interpretation (RSI) platform. Its documentation states [190+ languages and 6,000+ language combinations](https://www.interprefy.com/){rel=""nofollow""} with human interpreters, and [80 languages for its AI speech translation](https://knowledge.interprefy.com/what-languages-can-interprefy-ai-translate-from-and-to){rel=""nofollow""} (speech and captions). ([InterMIND vs Interprefy, feature by feature.](https://intermind.com/compare/interprefy)) - **KUDO** — RSI platform with an AI option: the [KUDO AI Speech Translator](https://kudo.ai/solutions/kudo-ai-speech-translator/){rel=""nofollow""} page states real-time audio and captions in 60+ languages, alongside its human-interpreter delivery. - **Boostlingo** — interpreter network and delivery platform: [its site](https://boostlingo.com/){rel=""nofollow""} states 10K qualified interpreters, 275+ languages 24/7, on-demand phone/video interpreting (OPI/VRI), plus AI captions ("Boostlingo AI Pro"). - **Akouo / Verspeak** — deliver interpreter audio to attendees' own phones over the web, for in-room and hybrid events without receiver hardware. **Pick one of these if:** you're running a conference, webinar, or formal multilingual session with an audience — especially if you need or already use human interpreters. If your "event" is an internal all-hands or an investor call — an audience, but everyone still needs to follow, and often ask, in their own language — that's a job-2 problem wearing a job-1 badge. See how InterMIND handles [global town halls](https://intermind.com/use-case/town-halls) and [investor-relations calls](https://intermind.com/use-case/ir-calls). And if the event itself is the job — a webinar, a conference session, a training — the InterMIND version of job 1 is at [events & webinars](https://intermind.com/use-case/events); worship services, a format of their own, are at [church translation](https://intermind.com/use-case/church). ### For everyday multilingual meetings (job 2) This is the category where question 5 — *how much of the meeting?* — does the most work, because these tools look alike in a voice demo and diverge sharply once the call has chat, notes, and documents in it. - **Wordly** — AI-only, real-time translation for meetings and events. Its documentation states [60+ languages and 3,000+ language pairs](https://www.wordly.ai/translator-languages){rel=""nofollow""}, with attendees choosing text, audio, or both; [its FAQ](https://www.wordly.ai/faq){rel=""nofollow""} also states translated transcripts and session summaries from the Wordly Portal. Chat, shared-notes, and document translation are not stated in its public documentation (checked August 2026). ([InterMIND vs Wordly, feature by feature.](https://intermind.com/compare/wordly)) - **DeepL Voice** — DeepL's real-time speech translation. [The product page](https://www.deepl.com/en/products/voice){rel=""nofollow""} states live captions in 40+ languages inside Microsoft Teams, Zoom Meetings, and Google Meet — and lists voice-to-voice support as "coming soon" (checked August 2026). Document translation is a separate DeepL product, not part of the meeting flow. - **InterMIND** — what we build. AI-only, **conversational**meeting translation where the whole meeting — not just the audio — comes back in each participant's language, both directions, at once. The point of difference is surface coverage: - **Voice** — 23 languages, per-viewer translated audio, live, in the **speaker's own voice** via a zero-shot ASR → MT → TTS cascade, not a single robot narrator. ([The real-time translation feature](https://intermind.com/features/realtime-translation); [how the pipeline works](https://intermind.com/blog/inside-the-translation-pipelines).) - **Chat & shared notes** — every message and every keystroke in the notes pane translated live, per viewer, in the same 23 languages, with per-language edit diffs. - **Documents** — drop a PDF, DOCX, DOC, PPTX, or XLSX into the chat and each participant gets it back in their language with formatting intact — **30 languages** via the DeepL Document API. (The honest per-surface language breakdown is [here](https://intermind.com/blog/how-many-languages-do-you-support).) - **In-product help & support, in your language** — the help assistant answers in the language you write in, and customer support replies are drafted in the client's language. The conversation around the product is multilingual too, not just the call. - **The after-record** — the post-meeting AI summary/digest is generated for you, and (like everything above) the meeting content stays in the EU — on the AI gateway the organization selects, with zero data retention and no training on customer content. - **Quality is published, not claimed** — the production voice pipeline is scored monthly against FLORES-200 with the full per-language-pair distribution at [/benchmark](https://intermind.com/benchmark), and the [live demo](https://intermind.com/demo) plays a real meeting translated live, per listener — no signup needed. **Pick one of these if:** your "conference" is really a working meeting — a call where multiple people need to talk, type, read, and decide *with* each other across languages, and where the chat, notes, documents, and follow-up need to be readable too, not just the audio. ### For captions, transcripts & notes (job 3) - **Zoom** — translated captions in 36 languages, each participant picking their own ([Business Plus/Enterprise, or a paid add-on](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0060844){rel=""nofollow""}); the newer [Voice translator](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""} renders translated *audio* per participant (AI Companion, US-cluster accounts, desktop app 7.0+); and [audio channels for up to 20 human interpreters](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0064768){rel=""nofollow""} you source yourself. Full breakdown: [Zoom live translation](https://intermind.com/blog/zoom-live-translation). - **Microsoft Teams** — [translated captions in 31 listed languages](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""} (organizer needs Teams Premium or Copilot); the [Interpreter agent](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""} translates spoken audio into spoken audio, optionally simulating the speaker's voice (listener needs a Copilot license); and [pre-configured channels for up to 16 language pairs of human interpreters](https://support.microsoft.com/en-us/office/use-language-interpretation-in-microsoft-teams-meetings-b9fdde0f-1896-48ba-8540-efc99f5f4b2e){rel=""nofollow""}. Full breakdown: [Teams live translation](https://intermind.com/blog/teams-live-translation). - **Google Meet** — [translated captions](https://support.google.com/meet/answer/10964115){rel=""nofollow""} on Business Standard+ Workspace editions, and [Gemini speech translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""} that translates the spoken audio "in a voice like yours" (Google AI Pro/Ultra or qualifying Workspace plans). Full breakdown: [Google Meet live translation](https://intermind.com/blog/google-meet-live-translation). - **Otter, and AI notetakers generally** — transcribe and summarize, sometimes translate the transcript afterwards. This is recording and notes, not live interpretation: nothing changes what participants hear during the call. We compared the category in [Otter alternatives](https://intermind.com/blog/otter-ai-alternatives) and [Fireflies alternatives](https://intermind.com/blog/fireflies-ai-alternatives), with per-tool language counts and sources. **Pick one of these if:** you mainly need a translated transcript or subtitles, and live two-way spoken translation isn't the requirement. ### A note on hardware (Timekettle et al.) Earbud translators show up in these searches, so for completeness: [Timekettle's W4 Pro product page](https://www.timekettle.co/products/timekettle-w4-pro-ai-interpreter-earbuds-new){rel=""nofollow""} states 52 languages and 106 accents online, for in-person conversation plus call/video translation through its companion app. It's a personal device: the translation happens in your ears, not in the meeting — other participants' experience is unchanged. A different category from the meeting platforms above; decide which of the three jobs you're hiring for first. --- ## The surface-coverage table Question 5 — *how much of the meeting comes back in your language?* — as one table. Every cell is what the vendor's own public documentation states, checked August 2026 (links in the sections above and in Sources below). "Not stated" means we found no claim for that surface in the vendor's public docs — check with the vendor before buying if it matters to you. | Tool | Translated audio (live) | Translated captions | Chat messages | Live shared notes | Documents in-meeting | Post-meeting record | | ------------------- | --------------------------------------------------------------------------- | ------------------------------------------------------ | ----------------------------------------------- | --------------------------- | -------------------------------------- | ------------------------------------------ | | **Interprefy** | Yes — human interpreters (190+ languages) or AI (80) | Yes (AI, 80 languages) | Not stated | Not stated | Not stated | Not stated | | **KUDO** | Yes — human interpreters or AI (60+ languages) | Yes (60+ languages) | Not stated | Not stated | Not stated | Not stated | | **Wordly** | Yes (AI; 60+ languages, 3,000+ pairs) | Yes | Not stated | Not stated | Not stated | Translated transcripts + session summaries | | **DeepL Voice** | "Coming soon" (per product page) | Yes (40+ languages, in Teams/Zoom/Meet) | Not stated | Not stated | Separate DeepL product | Not stated | | **Zoom** | Yes — Voice translator (AI Companion; US cluster, desktop 7.0+) | Yes (36 languages; Business Plus/Enterprise or add-on) | Manual per-message (38 languages) | Not stated | Not stated | Not stated | | **Microsoft Teams** | Yes — Interpreter agent, can simulate speaker's voice (Copilot license) | Yes (31 languages; Premium/Copilot) | Per-message, optional auto (inline translation) | Not stated | Not stated | Not stated | | **Google Meet** | Yes — Gemini speech translation, "in a voice like yours" (qualifying plans) | Yes (Business Standard+) | Not stated | Not stated | Not stated | Not stated | | **InterMIND** | Yes — 23 languages, speaker's own voice | Yes (23, per viewer) | Automatic per viewer (23 languages) | Yes — live, per viewer (23) | Yes — PDF/DOCX/PPTX/XLSX, 30 languages | Summary + digest, in your language | Two honest notes on our own row: the per-surface language counts differ (voice/chat/notes 23, documents 30, website 17) — [the full breakdown and why](https://intermind.com/blog/how-many-languages-do-you-support); and voice quality is published monthly against FLORES-200 at [/benchmark](https://intermind.com/benchmark) rather than claimed here. ## AI translation for events: Wordly vs Interprefy vs KUDO vs Boostlingo The four names that come up together for event translation, on the dimensions their own documentation states (checked August 2026; links in Sources): | | Wordly | Interprefy | KUDO | Boostlingo | | ----------------------------------- | -------------------------------------------------- | ------------------------- | ------------------------- | ----------------------------------------------------- | | Interpretation by | AI only | Human interpreters, or AI | Human interpreters, or AI | Human interpreters (network of 10K), plus AI captions | | Languages | 60+ (3,000+ pairs) | 190+ human; 80 AI | 60+ AI | 275+ human | | Output | Audio and/or text, attendee's choice | Audio and captions | Audio and captions | Audio (OPI/VRI); AI captions | | After the session | Translated transcripts + summaries (Wordly Portal) | Not stated | Not stated | Not stated | | Chat / notes / documents translated | Not stated | Not stated | Not stated | Not stated | The split that matters for an event buyer is the first row: with Interprefy, KUDO and Boostlingo you can put certified humans on the session when a mistranslation is a liability; Wordly is AI-only and priced and booked accordingly. None of the four states chat, notes or document translation in its public documentation — for an event that is usually fine; for a working meeting it is question 5 above — how much of the meeting comes back in your language. --- ## A quick decision shortcut - **Conference with an audience + you want human interpreters** → Interprefy / KUDO / Boostlingo. - **Working meeting, several people, everyone talks, both directions, AI-only** → Wordly / DeepL Voice / [InterMIND](https://intermind.com){rel=""nofollow""} — and here the differentiators are *own-voice* output, *whole-surface* coverage (chat, notes, documents, support, the after-record — not just audio), and *published* quality numbers. Test those specifically. - **You just need translated captions or a translated transcript** → your existing Zoom/Teams/Meet, or an AI notetaker. The honest meta-point: "best AI translation tool for conferences" has no single winner because "conference" hides three different jobs — and within the meeting job, most tools translate the spoken moment and stop. Name your job, then ask how much of the meeting actually comes back in your language. The shortlist writes itself. --- ## FAQ **What is the best real-time interpretation software?** Depends on which of the three jobs you're hiring for. Delivering interpretation to an event audience: Interprefy (80 AI languages, 190+ with human interpreters), KUDO (60+), or Wordly (60+) — all three document audio plus captions. A working meeting where everyone speaks, types, and reads in their own language, both directions: that's the conversational job — InterMIND covers voice, chat, notes (23 languages), and documents (30) per participant. Translated subtitles on a call you already run: Zoom (36 caption languages), Teams (31), or Meet handle it natively, with plan gates listed above. **Which tools support multilingual simultaneous interpretation?** With human interpreters: Interprefy (6,000+ language combinations), KUDO, Boostlingo (275+ languages on-demand), plus Zoom (audio channels for up to 20 interpreters you hire) and Teams (16 pre-configured language pairs). AI-only simultaneous: Interprefy AI (80 languages), KUDO AI (60+), Wordly (60+), InterMIND (23, in the speaker's own voice, both directions). **What are the best AI translation tools for conferences and meetings in 2026?** For conferences with an audience: Wordly, Interprefy AI, and KUDO AI all document 60–80 language live translation as audio and captions. For multilingual working meetings: InterMIND translates the whole meeting per participant — audio in the speaker's voice, chat, live notes, and dropped documents. For captions inside your existing platform: Zoom, Teams, and Meet each ship translated captions natively (gates in the table above), and DeepL Voice adds 40+ caption languages inside all three. **Is there an AI meeting assistant that transcribes and translates?** Notetakers (Otter, Fireflies, and the category we compared [here](https://intermind.com/blog/fireflies-ai-alternatives)) transcribe live and can translate the transcript afterwards — nothing changes what participants hear during the call. Wordly documents translated transcripts and summaries after its sessions. InterMIND does both jobs in one: live translated audio/chat/notes during the meeting, then a summary and digest generated in each member's own language. **What is the best AI translation for events?** For an audience listening to a stage: Wordly (AI-only, 60+ languages, audio or text per attendee), Interprefy AI (80 languages, with human interpreters available on the same platform), or KUDO AI (60+, likewise with humans as an option). Boostlingo is a human-interpreter network with AI captions. Which is "best" depends on whether the session needs certified humans on standby — the table above lines up what each documents. **What is an AI meeting translator, and how is it different from event translation?** An AI meeting translator serves a working meeting where several people speak, type and read in different languages, both directions, at once — chat, notes and documents included, not only the audio. Event translation serves one stage and many listeners. Wordly and DeepL Voice document live audio or captions for meetings; InterMIND translates the voice (23 languages, in the speaker's own voice), the chat, the live notes and dropped documents (30 languages) per participant. **Wordly vs Interprefy: how do they compare?** Wordly is AI-only: 60+ languages and 3,000+ pairs, attendees choose audio or text, translated transcripts and summaries afterwards. Interprefy runs human interpreters (190+ languages, 6,000+ combinations) and an AI mode (80 languages) on one platform. Neither states chat, notes or document translation in its public documentation (checked August 2026). **What are the alternatives to Wordly?** On the event side: Interprefy AI and KUDO AI (both 60–80 AI languages, both with human interpreters as an option) and Boostlingo (human network, 275+ languages). For working meetings rather than events: DeepL Voice (40+ caption languages inside Teams, Zoom and Meet) and InterMIND (23 languages on voice, chat and notes, 30 on documents, per participant). Pick by job first — the three jobs at the top of this guide. **Do Zoom, Microsoft Teams, or Google Meet translate meetings by themselves?** Yes, with plan gates. Zoom: translated captions in 36 languages (Business Plus/Enterprise or a paid add-on) and a Voice translator that renders translated audio (AI Companion, US-cluster accounts). Teams: translated captions in 31 languages (Premium/Copilot) and the Interpreter agent for spoken-audio translation (Copilot license). Meet: translated captions (Business Standard+) and Gemini speech translation on qualifying plans. Details and setup for each: [Zoom](https://intermind.com/blog/zoom-live-translation), [Teams](https://intermind.com/blog/teams-live-translation), [Meet](https://intermind.com/blog/google-meet-live-translation). --- ## What stays after the call, and where it lands The live part is the half of the meeting a vendor demos; the other half starts when the call ends. What InterMIND keeps, and where it can go — each item has its own guide: - **The recap, in each member's language.** After every transcribed meeting the signed-in participants get the AI summary, the full transcript and the recording on one permanent, members-only link; each reads the summary in their own language, and a channel keeps the recap of every past session. — [Meeting recap: what you get after the call](https://intermind.com/blog/meeting-recap) - **A copy in your CRM or help desk, by email.** The host adds the tool's inbound address as a recap copy recipient, confirms it once through a test email, and every recap of that room is sent there as a hidden BCC. — [How to get a copy of every meeting recap in your CRM by email](https://intermind.com/blog/how-to-get-a-copy-of-every-meeting-recap-in-your-crm-by-email) - **Structured, into any system.** A Zapier trigger, a signed `recap.ready` webhook, and an API with an OpenAPI 3.1 contract for Make, n8n, Pipedream and AI agents. — [Zapier, a webhook, or the API](https://intermind.com/blog/how-to-send-meeting-recaps-to-your-crm-with-zapier-or-the-api) - **The channel's history.** A meeting that persists as a channel keeps its chat, files, document summaries and recaps, readable by every member in their own language — and a client outside the team can be a member of it by email. — [How to add an external client to a team chat channel](https://intermind.com/blog/how-to-add-an-external-client-to-a-team-chat-channel) - **What the team sends in from elsewhere.** Every channel has its own email address, so a ticketing system or a monitoring tool posts into it without a bot; a file shares in from any app's share sheet on a phone or a Mac. — [Email to channel](https://intermind.com/blog/email-to-channel-no-bot), [Share from any app](https://intermind.com/blog/how-to-share-a-file-into-your-team-chat-from-any-app) A guest of a meeting — a participant without an account — gets the live part in full and none of the record; the account is free, and it is what makes the record reachable. --- ## See it for yourself We'd rather you test than take our word. For the meeting-translation job (job 2), the fastest way to judge any tool — ours included — is to put your own meeting through it: talk, then check whether the chat, the notes, and the doc came back in your language too. - **[Try the live demo](https://intermind.com/demo)** — runs InterMIND's production voice pipeline on your audio, in any of 23 languages. - **[Start your first meeting](https://intermind.com/chats)** — guests join by link, each in their own language. - **[Read the benchmark](https://intermind.com/benchmark)** — monthly FLORES-200 scores, full per-pair distribution, no cherry-picking. - **[How to evaluate any real-time translator](https://intermind.com/blog/real-time-meeting-translation)** — the vendor-neutral foundation behind this guide. --- *Sources: [Interprefy — AI translation languages](https://knowledge.interprefy.com/what-languages-can-interprefy-ai-translate-from-and-to){rel=""nofollow""}, [Interprefy — platform](https://www.interprefy.com/){rel=""nofollow""}, [KUDO — AI Speech Translator](https://kudo.ai/solutions/kudo-ai-speech-translator/){rel=""nofollow""}, [Boostlingo](https://boostlingo.com/){rel=""nofollow""}, [Wordly — translator languages](https://www.wordly.ai/translator-languages){rel=""nofollow""}, [Wordly — FAQ](https://www.wordly.ai/faq){rel=""nofollow""}, [DeepL — Voice](https://www.deepl.com/en/products/voice){rel=""nofollow""}, [Zoom — viewing captions in another language](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0060844){rel=""nofollow""}, [Zoom — Voice translator](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""}, [Zoom — Language Interpretation](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0064768){rel=""nofollow""}, [Zoom — translating messages in Chat](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058113){rel=""nofollow""}, [Microsoft — live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Microsoft — Interpreter in Teams](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft — language interpretation in Teams](https://support.microsoft.com/en-us/office/use-language-interpretation-in-microsoft-teams-meetings-b9fdde0f-1896-48ba-8540-efc99f5f4b2e){rel=""nofollow""}, [Microsoft — inline message translation](https://learn.microsoft.com/en-us/microsoftteams/inline-message-translation-teams){rel=""nofollow""}, [Google Meet — translated captions](https://support.google.com/meet/answer/10964115){rel=""nofollow""}, [Google Meet — Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, [Timekettle — W4 Pro](https://www.timekettle.co/products/timekettle-w4-pro-ai-interpreter-earbuds-new){rel=""nofollow""}, checked August 2026. Vendors expand plans and language lists over time; check their pages for the current state. InterMIND facts: [per-surface language breakdown](https://intermind.com/blog/how-many-languages-do-you-support), [live benchmark](https://intermind.com/benchmark).* # Book a demo: how to set up a demo flow with a calendar and one meeting link (2026) - **A scheduled, person-led walkthrough, not a trial.** A scheduler, a room and a write-up path; nothing is set up in the visitor's name. - **It runs on the calendar you already have.** A booking page, one reusable meeting link in its description, no form or SDR; the visitor keeps only your follow-up email. - **InterMIND holds the whole demo in each side's language,** each side picks its own, and the recap files itself in your CRM. Guests join free by link, no account; you pay only for active members. **"Book a demo"** is the button on a software vendor's site that schedules a guided walkthrough of the product with a person, at a time the visitor picks. It is the opposite of a free trial: instead of the visitor exploring the product alone, someone shows them the parts that matter for their situation and answers questions as they come up. This page is for both sides of that button. For a buyer: what booking a demo gets you, how it differs from a trial, and how to ask for one. For a team that needs the button on its own site: how to run the whole flow — scheduling, the call, the write-up — with the calendar you already use and one meeting link, and without buying a sales-development stack first. Our own **Book a call** page is the worked example, because it runs exactly this way. --- ## What "book a demo" means A demo is a scheduled, live, person-led walkthrough of a product. Three things sit behind the button: 1. **A scheduler** — the visitor picks a slot and it lands on someone's calendar, with a confirmation email. 2. **A meeting room** — where the walkthrough happens, at the booked time. 3. **A write-up path** — what the team keeps afterwards: who the visitor was, what they asked, what was agreed. Vendors differ mostly in how much they put between the visitor and the slot. Some ask for a form and route it to a sales-development rep who then proposes times; some open the calendar directly. The second is shorter for the visitor and has fewer moving parts for the team — which is why the flow below uses it. ### Demo vs free trial vs discovery call | | Book a demo | Free trial | Discovery call | | ------------------ | ---------------------------------------------------------- | ------------------------- | --------------------------- | | Who leads | The vendor shows | You explore alone | The vendor asks, you talk | | What you see | The parts relevant to you, live | Everything, at your pace | Usually no product at all | | What you get after | A write-up and a next step | Your own account and data | A yes/no on fit, and a date | | When it comes | After discovery, or as the first call for simpler products | Any time, self-serve | Before the demo | A demo is not a trial: nothing is set up in your name, and you leave with notes rather than an account. It is also not a [discovery call](https://intermind.com/blog/discovery-call) — discovery finds out what to show; the demo shows it. For simpler products the two collapse into one thirty-minute call. ### How to ask for a demo If the vendor's site has no button, or you want the demo to cover something specific, a short email does it: > **Subject:** Demo request — \[your company], \[the problem] > > Hi, > > We're looking at \[product] for \[one line: the problem]. Before a trial, I'd like a 30-minute demo focused on \[the two or three things that matter]. \[Names/roles] would join from our side. > > Would \[date option 1] or \[date option 2] work? We'd want to see \[specific scenario] rather than a general tour. > > \[Your name] The specific scenario is the part that gets you a useful demo instead of a tour. --- ## The demo flow, in three steps The rest of this guide is for the team. The setup uses the calendar you already have, one meeting link, and no code. ### Step 1 — A booking page in your own calendar Google Calendar's appointment schedules produce a public booking page: the visitor picks a slot and it lands on your calendar. Google documents that a personal Google Account or a Workspace account can create one; that the schedule's description "displays: on your booking page, in confirmation emails, in event descriptions"; and that the conferencing options are "Google Meet video conferencing, in-person meeting, phone call, none / to be specified later" — with the note "to use a third-party conference service, select None / to be specified later" (checked September 2026). Put the booking page behind the **Book a demo** button. Any scheduler with a description field that travels into the confirmation email will do; the recipe does not depend on Google's. ### Step 2 — One reusable InterMIND link in the description Create one ad-hoc meeting in InterMIND and copy its link — it looks like `intermind.com/abc-def-ghi`. Paste it into the booking page description, so it arrives in every confirmation email and calendar invite the scheduler sends. One link serves every demo, permanently. When a session ends, the next visitor who opens the same link starts a fresh session on the same URL. Two properties make it safe to put on a public page: - **Nobody walks in.** An anonymous visitor lands in a waiting room and joins only when you approve them. There is no setting that turns the approval off, and an unanswered request is denied automatically after 5 minutes. - **Nothing carries over.** Ad-hoc rooms delete their chat when a session ends and keep only the latest session's recap — one visitor's demo leaves nothing for the next one to find. ### Step 3 — Each side picks its own language The visitor opens the link in a browser, types a name, picks their language and knocks; you approve and pick yours. From then on each participant hears the others in their own language, and chat messages are translated per participant. Voice and chat cover the same **23 languages**: English, Russian, Spanish, French, German, Italian, Portuguese, Polish, Dutch, Czech, Hungarian, Danish, Finnish, Icelandic, Norwegian, Romanian, Swedish, Ukrainian, Japanese, Korean, Turkish, Chinese (Simplified) and Hindi. For a demo flow this is the step that widens the funnel: a visitor from Warsaw, São Paulo or Seoul books the same slot, from the same page, and asks questions in the language they think in. The visitor installs nothing, creates no account and pays nothing — only the host's side of the room carries a plan. --- ## What the visitor sees From the visitor's side, the whole flow is four screens: 1. **The booking page.** Pick a day and a slot. Enter a name and an email. 2. **The confirmation email.** The time, the calendar invite, and — in the description — the meeting link. 3. **The link, at the booked time.** A browser page: type a name, pick a language, knock. 4. **The room.** Once approved: the walkthrough, in their language. Nothing else. No account creation, no download, no "an SDR will reach out to confirm". ## What your team sees 1. **A calendar event** at the booked time, with the visitor's name and email. 2. **A knock** when they arrive — approve it, pick your language. 3. **The demo.** 4. **A recap by email** when the session ends: a title, an overview, key takeaways, sectioned points with timestamps, action items, open questions and topics. If the conversation produced nothing summarizable, no email is sent. 5. **The same recap on the CRM record**, if the CRM's inbound address is in the meeting's **Recap copy** field. The visitor's address stays in the To field, which is what the CRM matches against; the CRM address is BCC'd. Up to 10 confirmed addresses can live in your address book, and each is confirmed once by a test email opened inside the CRM. Available on every plan. One boundary to state plainly: a visitor who joined without an account receives nothing after the demo — no recap, no history. There is no delivery channel for them. Your follow-up email is what they keep, and a separate guide covers the [sales follow-up email](https://intermind.com/blog/sales-follow-up-email) with templates. --- ## The worked example: our own Book a call page InterMIND's [contacts page](https://intermind.com/contacts) has a **Book a call** card. It opens a Google Calendar booking page; the description of that booking page carries one InterMIND meeting link; a visitor who books gets the link in their confirmation email, joins at the booked time in whatever language they choose, and the team gets the recap afterwards. There is no form in front of the calendar and no SDR between the visitor and the slot. Next to it sits the other half of the answer to "book a demo": a **live demo that needs no booking**. Anyone can open the [demo](https://intermind.com/demo) in a browser, without signing up, and hear the translation working. A visitor who wants to see the product does not have to wait for a slot; a visitor who wants to talk about their situation books one. --- ## Where the flow stops The setup above is deliberately small, and it is worth being precise about what it does not do: - **No routing.** One booking page, one calendar, one link. Assigning demos round-robin across a team, or by territory, is a scheduler feature, not part of this recipe. - **No lead scoring or enrichment.** The team learns who the visitor is from the booking form and from the call. - **No history in the room.** Ad-hoc rooms are designed to leave nothing between sessions. A prospect you will meet repeatedly belongs in a channel, where every session's recap is kept. And the plan limits that decide whether the free tier carries the flow: | Plan | Voice translation | Chat translation | Participants | | ---------- | ------------------- | ---------------------- | ------------ | | Basic | 120 min / 30 days | 10,000 words / 30 days | 50 | | Pro | 1,500 min / 30 days | Unlimited | 100 | | Business | Unlimited | Unlimited | 300 | | Enterprise | Unlimited | Unlimited | 1,500 | The window is a rolling 30 days and the voice-minute pool belongs to the host's account, so Basic covers about four 30-minute demos a month. A team running demos weekly starts on Pro. --- ## FAQ **What does "book a demo" mean?** It is the button on a software vendor's site that schedules a live, person-led walkthrough of the product at a time the visitor picks. Behind it are a scheduler, a meeting room, and a path for the write-up afterwards. It differs from a free trial, where the visitor explores the product alone in their own account. **Is a demo a free trial?** No. A demo is guided and scheduled: a person shows you the parts of the product that matter for your situation and answers questions live, and you leave with notes and a next step. A free trial is self-serve: you get your own account and explore at your own pace. Many vendors offer both, in that order. **How do I ask for a demo?** Email the vendor with the problem you are trying to solve, the two or three things you want the demo to cover, who will join from your side, and two date options. Ask for a specific scenario rather than a general tour — that is what turns a demo into a useful one. **Do we need SDR software to offer "book a demo" on our site?** No. A booking page in the calendar you already use, with one reusable meeting link in its description, covers scheduling, the call and the write-up. Routing across a team, lead scoring and enrichment are separate tools, and a small team can add them later if the volume justifies it. **Does the visitor need an account or an app to join the demo?** No. They open the link from the confirmation email in a browser, type a name, pick a language and knock. Nothing to install, no account to create, nothing to pay — the host's plan covers the room. A visitor who joins without an account does not receive the recap afterwards; the follow-up email is their record. **Is it safe to put a permanent meeting link on a public booking page?** Yes, because the link is not the door. Anyone arriving anonymously waits for the host's approval, no configuration turns that approval off, and an unanswered request expires after 5 minutes. Ad-hoc rooms also delete their chat when a session ends, so nothing from one demo is visible in the next. **Can we run demos for visitors who speak a different language?** Yes, from the same page and the same link. The visitor picks their language when they join and you pick yours; each side hears the other in their own language across 23 languages, and chat is translated per participant. Nothing about the booking flow changes. --- ## Try it - **[How to schedule a meeting from Google Calendar or Outlook](https://intermind.com/blog/how-to-schedule-a-meeting-from-google-calendar-or-outlook)** — the calendar half of New meeting, the permanent link, the recurrence. - **[Book a call with us](https://intermind.com/contacts)** — see the flow from the visitor's side, end to end. - **[Try the live demo](https://intermind.com/demo)** — the no-booking half: hear the translation now, without signing up. - **[Start a meeting and copy its link](https://intermind.com/chats)** — the link you would paste into your own booking page. --- *Sources: Google Calendar Help, [Create an appointment schedule](https://support.google.com/calendar/answer/10729749){rel=""nofollow""} — account eligibility, where the description displays, and the conferencing options including "None / to be specified later" for third-party services. checked September 2026.* # The other bundle: languages around your communication, not apps around English - **The office bundle assumes one language.** Mail, docs and meetings in one box, a communication layer that defaults to English, translation sold back per seat. - **Nothing translated survives their meetings.** Meet translates one pair per meeting, always with English; Teams gates captions and Interpreter behind licenses; captions are not saved. - **InterMIND keeps the whole space in each member's language,** meetings, chat, documents and the recap, next to Workspace or 365 rather than instead of them. Guests join free by link, no account; you pay only for active members. Walk into any growing company from Jakarta to Bogotá and the software decision has usually already been made — not tool by tool, but as a bundle. Google Workspace or Microsoft 365: mail, calendar, documents, spreadsheets, storage, and a meeting app, one subscription, one admin console. The bundle *is* the pitch. Nobody buys Meet or Teams on its merits; they arrive in the box. It's a genuinely good deal on its own terms. But look at what sits at the center of the box. Every app in the bundle exists to serve communication — mail is communication, documents get written to be discussed, meetings are where the rest converges. And that communication layer, in both bundles, quietly assumes something about your team: **that it operates in one language.** In practice, in English. ## What the bundle assumes This isn't a rhetorical jab — it's documented product design, and we track it closely because it's our market: - **Google Meet's speech translation runs between English and five European languages, one pair per meeting** — every documented pair includes English. A meeting between a Portuguese speaker and an Indonesian speaker isn't in the design space (checked August 2026). - **Microsoft Teams gates translated captions behind the organizer's Premium or Copilot license, and its AI Interpreter behind a per-listener Copilot license, metered at 20 hours per user per month** — ten languages, scheduled meetings only. Translation is an enterprise add-on, priced per seat, on top of the bundle you already bought (checked August 2026). - **Nothing translated survives either platform's meetings.** Teams documents that captions aren't saved and recordings keep original audio only; Google documents that speech translation is unavailable in recordings and no audio is saved. The record of your meeting — the thing your team rereads, cites and onboards from — speaks whatever language the meeting was held in. Read the three facts together and the shape of the bundle is visible: the apps are many, and the communication layer underneath them defaults to one language — with translation documented as a paid, per-seat layer on top of the subscription you already bought. The bundle is apps around English-default communication. If your team happens to think in English, you'll never notice. If it thinks in Spanish, Portuguese, Turkish, Indonesian, Vietnamese — the bundle works, but *you* do the translating, in your head, every day, at whatever it costs you in precision and standing. We've written about what that costs: [the false fluency trap](https://intermind.com/blog/false-fluency-trap). ## Invert it Now run the bundling logic in the other direction. Keep communication at the center — meetings, chat, notes, documents, the history they leave — and instead of bundling *more apps* around it, bundle *languages* around it: - The meeting, live, in [every participant's own language](https://intermind.com/features/realtime-translation) — 23 languages for voice, chat and shared notes, each participant choosing theirs independently. - The [chat and its history](https://intermind.com/features/multilingual-chat), readable in each member's language — not just the messages arriving now, but the record. - [Documents](https://intermind.com/features/document-translation), translated in the same space — 30 languages. - The [recap after every meeting](https://intermind.com/features/recap), delivered to each signed-in participant in their own language. - And the whole thing persisting: the meeting becomes a channel, and [a week later it still exists in your language](https://intermind.com/blog/the-meeting-a-week-later) — which is the part no caption feature can give you, because captions die with the call. That's the entire product idea. Not an office suite with translation sprinkled on top; a communication space with languages as the load-bearing layer. One subscription on the host's side — [participants pay nothing](https://intermind.com/blog/free-for-participants). ## Where it lives, in one line One more thing the bundle decides without asking: where your meetings, transcripts and files live, and whose AI processes them. We treat that as a property of the product, not a theme: an [EU data path at every hop, zero data retention on the AI features, and user-controlled recording](https://intermind.com/features/security) — verifiable, not asserted, like the [monthly per-pair translation quality](https://intermind.com/benchmark) we publish instead of adjectives. ## What we're not Honesty clause, because bundle comparisons invite overreach: **InterMIND does not replace your office suite.** We don't do mail, spreadsheets or slide decks, and we don't plan to. Keep Workspace or 365 for those — most of our customers do. The claim is narrower and sharper: the *communication* inside that stack — the meetings, the chat, the record they leave — deserves a layer built for the languages your team actually thinks in, rather than an English-default layer with translation sold back per seat. Two bundles, two philosophies. Theirs: more apps around one language. Ours: [every language around the communication](https://intermind.com) — next to the suite you already run. ## See the difference in one meeting - **[Try the live demo](https://intermind.com/demo)** — no signup; hear a meeting where every listener gets their own language, simultaneously. - **[See the benchmark](https://intermind.com/benchmark)** — translation quality per language pair, published monthly on real traffic. - **[Compare with your current bundle](https://intermind.com/compare/google-workspace)** — feature-by-feature against [Google Workspace](https://intermind.com/compare/google-workspace) and [Microsoft Teams](https://intermind.com/compare/microsoft-teams), every competitor cell sourced. --- ## FAQ **Can InterMIND replace Google Workspace or Microsoft 365?** No, and it doesn't try to — there's no mail, spreadsheets or slides. InterMIND sits next to it as the *communication layer*: multilingual meetings, chat, shared notes, document translation, and the persistent translated history they produce — alongside the office suite, not instead of it. **What does "languages around communication" mean concretely?** That translation is the room's default behavior, not an add-on: voice in 23 languages per participant live, chat and notes translated per viewer including history, documents in 30 languages, and a recap after every meeting in each member's own language — with no per-listener licenses. The per-pipeline numbers differ on purpose; [here's why](https://intermind.com/blog/how-many-languages-do-you-support). **Isn't translation in Meet and Teams good enough for an international team?** Check the documented fences against your actual meetings: Meet translates speech between English and five languages, one pair per meeting; Teams interprets in ten languages for listeners holding Copilot licenses, 20 hours a month, scheduled meetings only — and neither keeps anything translated after the call (checked August 2026). If your meetings fit inside those fences, the bundled features may serve you well. If they don't, that's the gap this post is about. --- *Sources: [Google Meet — Learn about Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, [Google Workspace — plans and pricing](https://workspace.google.com/pricing){rel=""nofollow""}, [Microsoft — Interpreter in Teams meetings and calls](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft Learn — Teams Premium licensing](https://learn.microsoft.com/en-us/microsoftteams/teams-add-on-licensing/licensing-enhance-teams){rel=""nofollow""}, [Microsoft 365 — business plans](https://www.microsoft.com/en-us/microsoft-365/business){rel=""nofollow""}, [Microsoft — Use live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}. Vendors change bundles, licensing and language lists over time; check their pages for the current state. All facts checked August 2026.* # Your meetings, from the assistant you already use: connect InterMIND to Claude, ChatGPT, Copilot or Gemini (MCP connector) - **Your assistant can act as you in InterMIND.** Connect the MCP server once and Claude, ChatGPT, Copilot or Gemini creates meetings, reads recaps and transcripts, and posts in channels. - **It reads only what your account sees.** Meetings you host or attend, nothing else; it does not join the call, translate on demand or change settings. - **InterMIND keeps the whole space in each member's language,** so the assistant reads the recap your account already sees in yours. Guests join free by link, no account; you pay only for active members. Most of a working day now runs through one assistant: Claude, ChatGPT, Microsoft 365 Copilot or Gemini, whichever the company pays for. The assistant reads your mail, your calendar and your documents. Until now, your meetings lived outside it: to know what was agreed on last week's call you opened another app. InterMIND ships a remote [MCP](https://modelcontextprotocol.io){rel=""nofollow""} server — the open protocol every major assistant speaks. Connect it once, and the assistant acts as you inside your InterMIND account: creates and schedules meetings, reads recaps and transcripts, searches what was decided, reads and posts in your channels. Every participant still takes part in their own language; the assistant does not need to know which language the call was in. This post lists what you can ask, how the ten tools map to those requests, how to connect each assistant, and where the connector stops. ## What you can ask The assistant picks the tool from your wording. These are the requests the tools were built for, with what happens behind each. | You say | Tool | What happens | | ------------------------------------------------------------------------------------------------ | --------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | | "Create a meeting link for tomorrow's kickoff with Acme" | `create_meeting_link` | A meeting you own; anyone who opens the link knocks and you admit them | | "Schedule a 30-minute call with Acme on Thursday at 15:00 Berlin time and invite " | `schedule_meeting` | A meeting at that time, written to your connected Google or Microsoft calendar with the invitees | | "What do I have coming up?" | `list_meetings` | Your scheduled meetings, soonest first; or the recent ones by activity | | "Show me my latest recaps" | `list_recaps` | The newest recaps with the summary in Markdown and links to the recap and transcript pages | | "What did we decide about the Acme discount?" | `search_recaps` | Recaps whose summary contains the phrase, with a snippet around the match | | "Give me the transcript of yesterday's sales call" | `get_transcript` | The transcript by speaker, in the language it was spoken or in your cached translation | | "Summarise the last 50 messages in the Sales EU channel" | `list_channels`, `get_channel_messages` | The channel's chat, each message as written plus its translation into your language when the room already made one | | "Post in Sales EU that the deck is ready" | `post_channel_message` | A message from you; every member reads it in their own language, and it lands in the channel's recap | | "Which files were shared in the Acme channel?" | `list_documents` | Uploads and linked Google Drive / OneDrive files, newest first | Two things the table implies. Reading is limited to meetings you host or attend: a meeting you are not in answers "not found", never a summary. And posting is as you, under your name; the assistant should show you the text before it goes out, and the prompts in our published Copilot agent tell it to. ## How to connect The server URL is `https://intermind.com/api/mcp`. Sign-in is OAuth: the assistant opens an InterMIND page that lists what it will be able to do, you allow it, and the connection appears in **Integrations → API keys** under the assistant's name, where you can revoke it at any time. Clients that take a static header instead (Claude Code, Cursor, Gemini CLI, Copilot Studio) use an API key from the same page. - **Claude** (claude.ai, Desktop): InterMIND is listed in the [Claude Connectors Directory](https://claude.ai/directory/connectors/intermind){rel=""nofollow""} — open it, click **Connect**, allow the connection. Or add it by URL under **Customize → Connectors → Add custom connector**. - **ChatGPT:** turn on **Settings → Apps & Connectors → Advanced → Developer mode**, create a connector with the server URL and OAuth. Available on Plus, Pro, Business, Enterprise and Edu; in a workspace an admin allows custom connectors. - **Microsoft 365 Copilot:** in Copilot Studio, **Tools → Add a tool → New tool → Model Context Protocol**, the server URL, **OAuth 2.0 → Dynamic discovery**. The InterMIND agent for the Microsoft 365 store is in review. - **Gemini:** in the Gemini web app, **Settings & help → Connected apps → Custom apps for Spark → Add a custom app** with the server URL (personal Google accounts; Google offers this in the US, in English). A team on Gemini Enterprise adds the server once for everyone through the administrator's **Connected apps**; the [connection guide](https://intermind.com/docs/integrations/mcp) has the client registration and the form values. - **Cursor, Windsurf, VS Code, Claude Code:** a remote MCP server with the URL above; OAuth where the editor supports it, otherwise an API key in the `Authorization` header. The server is also in the [official MCP Registry](https://registry.modelcontextprotocol.io/v0.1/servers/com.intermind%2Fintermind/versions/latest){rel=""nofollow""} as `com.intermind/intermind`, so any client that browses the registry finds it by name. ## Who can connect Every registered InterMIND account, including the free Basic plan; guests cannot connect apps. The assistant sees exactly what the connected account sees — its own meetings, channels and recaps — and nothing from a meeting the account is not in. If you connected InterMIND before September 2026, the connection carries the two rights that existed then: meeting links and recaps. It does not gain the new rights on its own. Reconnect InterMIND in your assistant, or create a new key in **Integrations → API keys**; a tool the connection lacks answers with that exact instruction. ## What the connector does not do - It does not join the meeting or speak in it. Mia, the assistant inside the room, is a [separate feature](https://intermind.com/blog/ai-meeting-assistant-in-the-meeting) with its own rules about who may give her orders. - It does not search transcripts. `search_recaps` matches a phrase against the current summary of each session; for the words themselves, ask for the transcript. - It does not translate on demand. A transcript comes back in the language it was spoken unless the room already translated it for your account; chat messages carry the translation the room made for you, when there is one. - It does not change your settings, invite members, or delete anything. - It does not see the meetings of other people in your team, even when you are the team owner. ## In which language does the assistant get the meeting In the language the connected account uses in that meeting. Recaps are written once and translated for every participant; the assistant reads the recap the account sees. Chat messages come back as written, with the cached translation into the account's chat language next to them. The assistant can translate further itself, but the source it reads is already in your language wherever the room made one. ## FAQ **What are Claude connectors, and is InterMIND one of them?** Connectors are the remote MCP servers Claude can use from a conversation. InterMIND is listed in the Claude Connectors Directory; connecting it takes a click on the listing and an allow on the InterMIND consent page. Any other MCP client connects by the server URL. **How do I add a custom connector to ChatGPT?** Turn on Developer mode under Settings → Apps & Connectors → Advanced, then create a connector with `https://intermind.com/api/mcp` and OAuth authentication. ChatGPT opens the InterMIND consent page; after you allow, the tools appear in the conversation. **Can a Copilot agent read my meeting notes?** Through Copilot Studio, yes: add InterMIND as an MCP tool to an agent, and it can list your recaps, search them and read transcripts of meetings you attend. The agent InterMIND submitted to the Microsoft 365 store bundles the same tools with ready conversation starters. **Does Gemini support MCP servers?** Personal Google accounts add custom MCP servers in the Gemini web app under Connected apps (US, English, on Google's terms). Gemini Enterprise lets a team administrator add a custom MCP server for the whole team with an OAuth client; Gemini inside Gmail, Docs and Meet takes only the integrations Google ships itself, as of September 2026. **What can the assistant do with my InterMIND account?** Create and schedule meetings, list your meetings, read recaps and transcripts, search recaps by phrase, read and post in your channels, and list the documents shared in your meetings. Ten tools; the table above maps them to requests. **Can the assistant schedule a meeting in my calendar?** Yes. `schedule_meeting` takes a local time, an IANA time zone, a duration and invitee emails, creates the meeting and writes the event to the Google or Microsoft calendar connected to your InterMIND account. Without a connected calendar the link still works and the assistant tells you to send the invite yourself. **Is it safe to connect my meetings to an AI assistant?** The connection is a credential you grant on a consent page that lists every right, revocable in Integrations → API keys. The assistant acts as your account and only within it; it cannot read a meeting you are not in. Which assistant vendor stores what from the conversation is that vendor's policy, not InterMIND's. **Do I need a paid plan?** No. Every registered account can connect an assistant, including Basic. Guests cannot. **Why does a tool answer that I need to reconnect?** The connection was made before that right existed. Reconnect InterMIND in your assistant or create a new API key; the new connection carries all ten tools. **Which language will the assistant get the recap in?** The one your account sees in that meeting. Recaps are written once and translated for every participant, so the assistant reads yours. ## Try it - **[Connect your assistant](https://intermind.com/docs/integrations/mcp)** — the server URL, the steps per client, the Gemini Enterprise form values, and the API key alternative. - **[Try the live demo](https://intermind.com/demo)** — a meeting in your language, no signup, to have a recap to ask about. - **[Best MCP servers for meetings](https://intermind.com/blog/mcp-servers-for-meeting-tools)** — what Zoom, Teams, Fireflies, Otter and Granola expose to an assistant, from their documentation. *Sources: Model Context Protocol ([specification](https://modelcontextprotocol.io){rel=""nofollow""}); Anthropic ([Claude Connectors Directory](https://claude.ai/directory){rel=""nofollow""}); Google ([custom apps for Gemini Spark](https://support.google.com/gemini/answer/17209137){rel=""nofollow""}, [custom MCP server in Gemini Enterprise – Business edition](https://support.google.com/g/answer/17106276){rel=""nofollow""}, [custom MCP server data store](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/custom-mcp-server/set-up-custom-mcp-server){rel=""nofollow""}); official [MCP Registry entry](https://registry.modelcontextprotocol.io/v0.1/servers/com.intermind%2Fintermind/versions/latest){rel=""nofollow""}; InterMIND ([AI assistants (MCP)](https://intermind.com/docs/integrations/mcp), [API](https://intermind.com/docs/integrations/api-zapier)) — checked September 2026.* # Decision log template: how to record decisions so nobody re-litigates them — and where the log lives (2026) - **A decision log is one entry per decision:** the sentence, who decided, the options rejected and why, and the condition that reopens it. - **Decisions get re-litigated when the reasons are missing;** in Teams, Zoom, Google Workspace and Slack the log is a typed document in one language. - **InterMIND keeps the whole meeting in each member's language,** its recap marking each point agreed, open or disputed, next to those tools rather than instead of them. Guests join free by link, no account; you pay only for active members. A decision log is the running record of what a team has decided: one entry per decision, dated, with the decision stated in one sentence, the person or body that made it, the options that were on the table and the reason the chosen one won, what the decision rules out, and the condition under which it would be looked at again. It is not the minutes, and it is not the task list. It is the document someone opens three months later, when a new colleague asks "why do we do it this way?", and finds an answer instead of a meeting. This guide is the craft first — what a decision log is, what every entry carries, how to write one before, during and after the meeting where the decision is made, a template and a register you can copy, three filled-in entries — then the mechanics: where the log lives in the tools your team already uses, and what of the decision actually gets into it. Because the log's real test is not the week it is written. It is the day someone says "I don't remember agreeing to that." ## What a decision log is — and what it isn't Four kinds of record come out of a meeting, and the decision log is the one most often confused with the other three: | | What it holds | One entry looks like | Who reads it, and when | | ---------------------------------------------------------------------- | ------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------ | | **Decision log** | What was decided, by whom, why, and what was rejected | "D-14 · 9 Oct · We quote in EUR only; USD requests get the EUR price with the day's rate. Decided by Lena. Rejected: dual price lists." | Anyone, months later — the person who asks "why" | | **[Action items](https://intermind.com/blog/action-items)** | What someone will do because of a decision | "Anna — update the quote template to EUR — by 16 Oct" | The owner this week, the next meeting | | **[Minutes](https://intermind.com/blog/how-to-write-meeting-minutes)** | The official account of one meeting: attendance, items, decisions, votes | Two pages for one meeting | Members and whoever missed it, once | | **Open questions** | What nobody could answer yet | "Does the Swiss client accept EUR invoices? Priya finds out." | The next agenda | The difference that matters: minutes are organized by meeting, the decision log is organized by decision. A decision made across three meetings has three minutes entries and one log entry. And the log keeps what minutes usually drop — the options that lost and the reason they lost — because that is the part the next argument is about. A decision log is also not a policy manual. A policy is the current rule; the log is the history of how the rule got there, including the entries marked *superseded*. Keep both, link them, and never edit an old entry to match a new decision — add a new entry and point the old one at it. Nor is it a procedure: the step-by-step way a job is done belongs in an [SOP with its own owner, version and review date](https://intermind.com/blog/sop-template), and the log records the decision that changed it. ## What every entry carries: the format Seven elements. Most templates online carry the first three and stop, which is why most logs get re-litigated: 1. **An ID and a date.** "D-14, 9 October". The ID is what people cite in chat ("that's D-14") instead of re-describing the decision and reopening it by accident. 2. **The decision, in one sentence, in the present tense.** "We quote in EUR only." Not "we discussed pricing"; not "it was felt that". If the sentence needs a paragraph, it is two decisions or none. 3. **Who decided, who was consulted, who was told.** One name or one body for the decision; the people whose input was taken; the channel or list that was informed. The first answers "who can change this"; the other two answer "was I asked" — the most common reason a decision is contested. 4. **The options considered, including the one chosen.** One line each. A log entry with a single option is a record of an outcome, not of a decision; the rejected options are what stop the same proposal coming back next quarter under a new name. 5. **The reason the chosen option won.** One line — the constraint, the number, the risk that settled it. This is the sentence that the new colleague is actually looking for. 6. **Consequences: what changes, what it costs, what it rules out.** The decision to quote in EUR only rules out a USD price list; say so, so that nobody builds one. 7. **The revisit condition, and the source.** The date, number or event that would legitimately reopen it ("if more than 10% of quotes are refused on currency"), and a link to where it was made — the meeting recap, the thread, the moment in the transcript. A decision with a stated revisit condition is reopened on evidence; a decision without one is reopened on mood. What stays out: the discussion. Three paragraphs of who said what belong in the minutes or the transcript, and the log links to them. An entry is read by someone looking for one answer; it should fit on one screen. ## How to write one: before, during, after **Before the meeting, put the decision on the agenda as a decision.** The [agenda item](https://intermind.com/blog/meeting-agenda-template) that will produce the entry is marked *decision*, with the question and the options already written: "Decide: EUR only, dual price lists, or USD on request — Lena, 15 min, decision." Half the entry exists before anyone speaks, and the room spends its minutes on the reason, not on reconstructing the options. **During the meeting, read the decision back before moving on.** The facilitator says the sentence aloud, with the loser named: "so we're recording — EUR only, dual price lists rejected because of the maintenance cost, Lena decides, revisit if refusals pass 10%." The read-back is the moment the entry is actually made; the people who could object are in the room, and an objection now is cheaper than the same objection in six weeks. An item that cannot be read back as one sentence is not decided yet — it is marked *open* with the question that remains, and goes to the next agenda. **After the meeting, write the entry the same day and publish it where the team already reads.** Copy the read-back sentence, add the options and the reason from the notes, give it an ID, link the recap. Then post it — in the channel where the meeting lives, not in one person's document. A log in a private folder is a log the team doesn't have, and a decision the team can't find is a decision it will take again. The whole discipline is the read-back. The log is the read-back, written down. ## A decision log template One entry, for a document or a channel post: > **D-\[number]** · \[date] · **\[Decision in one sentence, present tense]**:br**Status:** proposed / decided / superseded by D-\[number] :br**Decided by:** \[name or body] · **Consulted:** \[names] · **Informed:** \[channel or list] :br**Context:** \[two lines — the question, and why it had to be decided now] :br**Options:** A — \[one line]; B — \[one line]; C — \[one line]. **Chosen:** \[letter] :br**Why:** \[the one constraint, number or risk that settled it] :br**Consequences:** \[what changes, what it costs, what it rules out] :br**Revisit if:** \[a date, a number or an event] :br**Source:** \[recap or thread link, and the moment] The register, for the list that spans the year: | ID | Date | Decision | Decided by | Why (one line) | Rejected | Revisit if | Source | | ------ | ------- | --------------- | ---------- | -------------- | ---------- | ------------ | ------- | | D-\[n] | \[date] | \[one sentence] | \[name] | \[one line] | \[options] | \[condition] | \[link] | Both paste into a document, a spreadsheet, a canvas or a chat message without reformatting. The columns that are usually missing from templates are *Rejected* and *Revisit if* — the two that decide whether the entry is ever read again. ## Three filled-in entries ### A pricing decision — from the weekly > **D-14** · 9 Oct 2026 · **We quote in EUR only; a USD request gets the EUR price converted at the day's rate.**:br**Status:** decided :br**Decided by:** Lena · **Consulted:** Anna, Mateusz · **Informed:** #sales :br**Context:** Two distributors asked for USD quotes in September; maintaining a second price list was proposed. :br**Options:** A — EUR only; B — dual EUR/USD price lists; C — USD on request, hand-converted. **Chosen:** A :br**Why:** B doubles the maintenance of every price change; C has produced three inconsistent quotes already. :br**Consequences:** No USD price list is built; the quote template says "EUR" in its header; refusals on currency are counted. :br**Revisit if:** more than 10% of quotes in a quarter are refused on currency. :br**Source:** Weekly, 9 Oct, recap item 2, 14:05. ### A hiring decision — from a one-off meeting > **D-15** · 10 Oct 2026 · **The second support hire is in Lisbon, Portuguese- and Spanish-speaking, not a second person in the Milan office.**:br**Status:** decided :br**Decided by:** Tomás · **Consulted:** Priya, Dana · **Informed:** #team :br**Context:** Support tickets from Spain and Brazil passed 40% of the queue in Q3. :br**Options:** A — second hire in Milan; B — hire in Lisbon; C — outsource Spanish support. **Chosen:** B :br**Why:** C was rejected on handover quality in the pilot; A leaves the Spanish queue where it is. :br**Consequences:** The job post is in Portuguese and Spanish; onboarding happens remotely; the team's working language in the support channel stays mixed. :br**Revisit if:** the Spanish and Portuguese share of tickets falls below 20% for two quarters. :br**Source:** Hiring call, 10 Oct, recap item 3. ### A decision superseded > **D-9** · 14 Aug 2026 · **Client calls are recorded by default.**:br**Status:** superseded by D-16 :br**D-16** · 13 Oct 2026 · **Client calls are recorded only when the client has agreed in the invitation; the recap is written either way.**:br**Decided by:** Lena · **Consulted:** Kenji (legal), Anna · **Informed:** #sales, #team :br**Options:** A — keep recording by default; B — ask in the invitation; C — stop recording clients. **Chosen:** B :br**Why:** two clients objected in September; the recap, not the recording, is what the team actually reads afterwards. :br**Consequences:** The invitation template gains one sentence; D-9 is closed, not deleted. :br**Revisit if:** a client contract requires recordings. :br**Source:** Weekly, 13 Oct, recap item 1, 03:40. Notice what the three have in common: a sentence a stranger can act on, the loser named with its reason, and a condition that says when the question is legitimately open again. That is the whole craft. Everything else in this guide is about keeping that entry findable after the meeting ends. ## Why decisions get re-litigated Teams rarely reopen a decision because they disagree with it. They reopen it because the record cannot answer one of four questions: - **"Did we actually decide that?"** The outcome was discussed but never read back, so each person left with their own version. The fix is the read-back, not a better document. - **"Why did we decide that?"** The sentence survived, the reason didn't. Six weeks later the reason is unknown, the decision looks arbitrary, and the proposal that lost comes back as if it were new. The fix is the *Why* and *Rejected* lines. - **"Was I asked?"** Someone affected was not consulted or not told, and contests the decision to be heard rather than to change it. The fix is the *Consulted* and *Informed* lines — and publishing the entry where that person reads. - **"Has anything changed?"** A decision with no revisit condition is reopened whenever someone feels like it; one with a condition is reopened when the condition is met, and otherwise cited by ID. The fix is the *Revisit if* line. A log that carries all seven elements closes all four questions. One that carries only the sentence closes the first and opens the other three. ## Where the decision log lives in the tools you already use Each major platform has a place where a decision can be written down, and each stops at a different point. Documented behaviour only, from the vendors' own pages, with the month each page was checked: | Platform | Where a decision is written | What of the decision comes back after the meeting | | -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | *Notes* in the meeting controls during the call — collaborative notes any attendee or organizer can edit, with tasks assigned by tagging people; or *Add an agenda* in the meeting's Details when scheduling | The notes are saved automatically and reachable from the Teams calendar and the meeting recap; what is in them is what a person typed; external attendees cannot access or edit them (checked October 2026) | | **Zoom Workplace** | The AI Companion meeting summary after the call, with a "Next steps" section, on paid Zoom Workplace plans | The summary is sent by email, listed on the Summaries page of the web portal and can be posted to the meeting's group chat; only the host can edit it, and unauthenticated users do not receive the email (checked August 2026) | | **Google Workspace** | The Calendar event's description, or *Take notes for me* in Meet on eligible Workspace editions and Google AI plans, which writes a summary and "suggested next steps" | The notes arrive as a Google Doc shared per the configured setting; the feature supports one language at a time — multiple languages spoken in the same meeting are not supported; Google's page does not describe a decisions section (checked September and October 2026) | | **Slack** | A canvas from the meeting-agenda template, shared in the channel, with sections for objectives, time allocations, next steps and action items with due dates | The canvas stays in the channel as a document; what was said in the call is not in it unless someone types it (checked October 2026) | Two things are the same everywhere. The decision is a line a person types into a document next to the meeting, in the one language the room used; and the reason, the rejected options and the moment it was said are in the document only if that person wrote them down. ## How a decision comes back as the recap InterMIND is a communication space where a meeting lives in a channel, so the log has an obvious home: the channel's chat, where the agenda went in the day before and the entries are posted after — and where each member types in their own language and reads the others in theirs. If the register is kept somewhere else, a spreadsheet or a document, its updates can land in the channel by email: the channel's host gives it an address of its own, and a message sent there appears as a regular message with the sender named and attachments kept. During the call, the entry under discussion goes on everyone's screen next to the video tiles with *Share to conference*: the sharer edits the note live while the room watches the read-back take shape, and every participant reads it in their own language, with the original a toggle away. When the call ends, the recap is written from the meeting itself. It carries an overview and key takeaways, then the points — each marked **agreed**, **open** or **disputed**, with the speakers attached and a timestamp that opens the transcript at the moment it was said — then the action items with owners and the open questions. That is the raw material of a log entry: the sentence, who said yes, who disagreed and where, and the moment to link as *Source*. The recap arrives by email, as a message in the channel and as a link in the calendar event, and every signed-in member reads it **in their own language** — the record is translated per reader, not written once in the language the room happened to use. Any member can edit it, every edit keeps author and revision history, and the channel keeps the recap of every past session, so the meeting where D-14 was made is one click away from the entry that cites it. Where the entry has to end up in a system of record, the host adds a recap copy to any address — a CRM or tracker inbound mailbox — and every recap of the meeting or channel is also sent there after a one-time confirmation of the address; the mechanics are in [a copy of every meeting recap in your CRM, by email](https://intermind.com/blog/how-to-get-a-copy-of-every-meeting-recap-in-your-crm-by-email). The same recap reaches Zapier, a webhook or the API with the summary as Markdown, and a member's own assistant — Claude, ChatGPT, Copilot or Gemini — can search the recaps through the MCP connector, so "what did we decide about USD quotes?" is a question asked in the tool they already use, answered with the recap and its moment. A guest joins by link, without an account and at no cost — from a phone, in the browser — and hears the meeting live in their own language. There is no record for a guest afterwards — the account is free, and it is what makes the record reachable. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing); members who go quiet keep their access at no cost. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours, points and timestamps included. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. Decision logs as a craft survive every tool: somebody still has to say the sentence aloud, name the option that lost, and write down when the question may be asked again. What doesn't have to survive is the second job — reconstructing who agreed to what from memory, in one language, for people who read others. ## FAQ **What is a decision log?** A decision log is the running record of a team's decisions, one entry per decision: the decision in one sentence, the date, who made it, who was consulted and informed, the options considered and the reason the chosen one won, what it rules out, the condition that would reopen it, and a link to where it was made. It is organized by decision, not by meeting, which is what makes it different from minutes. **What should be included in a decision log?** Seven things per entry: an ID and a date; the decision in one present-tense sentence; who decided, who was consulted and who was informed; the options considered, including the rejected ones; the reason the chosen option won; the consequences — what changes and what is ruled out; and the revisit condition plus a link to the source. The two most often left out are the rejected options and the revisit condition, and they are the two that stop a decision from being re-opened. **How do you write a decision log?** Put the decision on the agenda as a decision, with the options written in advance. In the meeting, read the decision back aloud before moving on — the sentence, the loser and its reason, who decides, when it is revisited. The same day, write the entry from the read-back, give it an ID, link the recap, and post it where the team already reads. A log that is written from read-backs is accurate; one reconstructed a week later from memory is the start of the next argument. **What is the difference between a decision log and an action log?** A decision log records what was decided and why; an action log — or an [action items](https://intermind.com/blog/action-items) list — records what someone will do because of it, with an owner and a date. "We quote in EUR only" is a decision; "Anna — update the quote template to EUR — by 16 October" is the action it produced. Decisions are cited for months; action items are closed in days. Keeping both in one list is how the reasons get lost under the tasks. **What is a decision register?** The same thing as a decision log, in the vocabulary of project and governance work: a table with one row per decision — ID, date, decision, who decided, why, status. "Register" tends to mean the tabular view and "log" the running one; the table in this guide is both, with *Rejected* and *Revisit if* added to the usual columns. **Is there a decision log template in Excel or Word?** The register in this guide is a plain table and the entry is plain text; both paste into Excel, Google Sheets, Word, a Slack canvas, a Loop page or a chat message without reformatting. The format matters more than the file: whatever holds the log needs a row per decision with the reason and the rejected options, and it needs to live where the team already reads. **Who should keep the decision log?** The facilitator of the meeting where the decision is made writes the entry, the same day, from the read-back; the person named under *Decided by* owns the decision itself. In a small organization that is usually the same person for most entries. What matters more than the role is the place: one log for the team, in the channel the team already uses, not one per person. **What is an architecture decision record?** An architecture decision record, or ADR, is the software-engineering form of a decision log entry: one short document per decision, kept in the project's repository, with the context, the decision, and its consequences, and a status that moves from proposed to accepted to superseded. The template in this guide is the same idea for a team's operating decisions, with the people — who decided, who was consulted, who was told — added, because outside engineering that is what gets contested. --- *Sources: [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Google Workspace Updates — "Take notes for me" now captures "next steps"](https://workspaceupdates.googleblog.com/2025/02/google-meet-take-notes-for-me-next-steps.html){rel=""nofollow""}; [Slack — Meeting agenda template (canvas)](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Microsoft's notes page, Google's Meet help page and Slack's template checked October 2026; Zoom's meeting-summary page checked August 2026; Google's next-steps announcement checked September 2026. Vendors change plans, features and language lists over time; check their pages for the current state.* # Discovery call: what it is, how to run one, and how to hold it in the lead's own language (2026) - **The first conversation, held to decide fit.** The seller learns the problem, its cost, who decides and when; the prospect decides whether to meet again. - **Ask before you tell, end with a date.** Half an hour is enough; answers come out shorter in a second language than in the lead's own. - **InterMIND holds the whole call in each side's language,** one reusable link in your booking page, and the recap files itself in your CRM. Guests join free by link, no account; you pay only for active members. A **discovery call** is the first scheduled conversation between a seller and a prospective customer, held to establish whether the prospect's problem is one the seller actually solves — before anyone demos anything. It is a listening exercise with a decision at the end: is there a fit, and if so, what is the next step? This guide covers the call itself — what it is and isn't, a 30-minute agenda, the questions that do the work, a short script, and what should happen afterwards. The last section covers a case most guides skip: the lead who would rather answer in Portuguese, Japanese or Polish than in your language. The setup for that is three steps, uses the calendar you already have, and produces the call write-up on its own. --- ## What a discovery call is — and what it isn't A discovery call sits between the first contact (an inbound form, a reply to an outreach email, a referral) and the demo. Its output is a **decision about fit**, in both directions: - **For the seller:** does this prospect have a problem we solve, the means to buy, and a reason to act now? - **For the prospect:** does this vendor understand our situation well enough to be worth a second meeting? Three things a discovery call is *not*: - **Not a demo.** A demo shows the product; discovery finds out what to show. Running them together is the most common way to spend forty minutes presenting features the prospect never needed. - **Not an interview.** The prospect is not being examined. The questions are about their situation, and a good call has the prospect talking for most of it — a seller who talks for the first several minutes has already lost the structure. - **Not a pitch.** If the prospect leaves knowing everything about your product and you leave knowing nothing about their problem, the call ran backwards. Other names for the same meeting: *qualification call*, *intro call*, *exploratory call*, *fit call*, *first call*. In most sales processes they refer to the same thing — the first structured conversation before a demo or proposal. --- ## How to run a discovery call: a 30-minute agenda Thirty minutes is enough for discovery when the time is planned. A structure that works: | Minutes | Block | What happens | | ------- | --------------------- | ------------------------------------------------------------------------------------------------------------------- | | 0–3 | Agenda and permission | State what you want to learn and what they get at the end (a clear yes/no on fit). Ask whether that works for them. | | 3–12 | Situation | How things run today: the process, the tools, the people involved. No pitching. | | 12–20 | Problem and impact | What breaks, how often, what it costs — in time, money, missed deals, or people. Get a number where there is one. | | 20–26 | Decision | Who else is involved, how a decision like this gets made, what the timeline is, what would stop it. | | 26–30 | Next step | Summarize what you heard, say plainly whether it sounds like a fit, and agree on the next meeting — with a date. | Two rules keep the agenda honest. **Ask before you tell:** the product does not come up until you can describe their problem back to them in their words. **End with a date:** "I'll send some information" is not a next step; "demo on Thursday with your ops lead present" is. --- ## Discovery call questions The questions below are grouped by the agenda block they belong to. Fifteen is more than one call needs — pick the ones that fit and let the answers lead. **Situation** 1. Walk me through how this works today, start to finish. 2. Who is involved when this happens — which teams, which roles? 3. What tools are you using for it now? 4. What made you take this call? **Problem and impact** 5. Where does the current process break down? 6. How often does that happen? 7. What does it cost you when it does — time, money, customers, people? 8. What have you already tried to fix it? 9. What happens if nothing changes for another year? **Decision** 10. Who else would need to be involved in a decision like this? 11. How did you last buy something in this category — what did that process look like? 12. Is there a budget attached to solving this, or would one need to be found? 13. What is the timeline you're working with — and what's driving it? 14. What would make this a "no" for you? **Next step** 15. If what I've described sounds right, what would be a useful next conversation, and who should be in it? --- ## A short discovery call script A script is not a text to read out; it is the set of sentences that carry the call from one block to the next. **Opening (agenda and permission):** > "Thanks for making the time. I'd like to spend most of this call understanding how things work on your side and where they break — and at the end I'll tell you honestly whether I think we can help. If we can, we'll pick a next step; if not, I'll say so. Does that work?" **Transition into the problem:** > "You mentioned that \[situation]. Where does that go wrong most often?" **Getting to impact:** > "When that happens, what does it actually cost you — is it hours, is it a missed deal, is it someone's weekend?" **Transition into the decision:** > "If you decided this was worth fixing, who else would need to be in the room?" **Close:** > "Here's what I heard: \[two sentences in their words]. Based on that, I think this is / isn't something we solve well. The useful next step would be \[demo / proposal / a call with X]. Can we put that on the calendar now?" --- ## What happens after a discovery call Three things, in this order: 1. **The write-up.** What the prospect said about their situation, the problem and its cost, who decides, the timeline, and the agreed next step — in their words where possible. This is the document every later conversation refers back to. 2. **The follow-up email**, the same day. It restates the write-up in a few lines and confirms the next step with its date. (A separate guide covers the [sales follow-up email](https://intermind.com/blog/sales-follow-up-email), with templates.) 3. **The CRM record.** The write-up lands on the prospect's record, so the colleague running the demo next week reads it there instead of asking you. In most teams the first and third steps are manual, which is why they are often skipped. The setup in the next section makes both of them a by-product of the call. --- ## Discovery calls with international leads: each side in its own language The agenda above assumes both sides share a working language. With an international pipeline that is often not the case — or it is the case on paper, while the prospect's answers to "what does this cost you?" come out shorter and vaguer than they would in the language they think in. Discovery runs on the quality of those answers. The following setup lets the prospect answer in their own language and you ask in yours, without changing anything else about the call. It has three steps and uses the calendar you already run on. ### Step 1 — A booking page in your own calendar Google Calendar's appointment schedules produce a public booking page; a prospect picks a slot and it lands on your calendar. Google documents that a personal Google Account or a Workspace account can create one, that the schedule has a description which "displays: on your booking page, in confirmation emails, in event descriptions", and that the conferencing options are "Google Meet video conferencing, in-person meeting, phone call, none / to be specified later" — with the note that "to use a third-party conference service, select None / to be specified later" (checked September 2026). Any scheduler with a description field that travels into the confirmation email works the same way. ### Step 2 — One reusable InterMIND link in the description Create one ad-hoc meeting in InterMIND and copy its link (it looks like `intermind.com/abc-def-ghi`). Paste it into the booking page description. From then on it is in every confirmation and calendar invite the scheduler sends. One link serves every discovery call, permanently: when a call ends, the next prospect who opens the same link starts a fresh session on it. Two properties make the link safe to publish: - **Nobody walks in.** An anonymous visitor lands in a waiting room and joins only when you approve them; there is no setting that turns that approval off, and an unanswered request is denied automatically after 5 minutes. - **Nothing carries over.** Ad-hoc rooms delete their chat when a session ends, and keep only the latest session's recap — one prospect's call leaves nothing for the next one to find. ### Step 3 — Each side picks a language The prospect opens the link in a browser, types a name and picks their language; you pick yours. From then on each participant hears the other in their own language, and chat messages are translated per participant too. Voice and chat cover the same **23 languages**: English, Russian, Spanish, French, German, Italian, Portuguese, Polish, Dutch, Czech, Hungarian, Danish, Finnish, Icelandic, Norwegian, Romanian, Swedish, Ukrainian, Japanese, Korean, Turkish, Chinese (Simplified) and Hindi. The prospect installs nothing, creates no account, and pays nothing — only the host's side of the room carries a plan. ### What you get afterwards When the session ends, InterMIND generates a recap — a title, an overview, key takeaways, sectioned points with timestamps, action items, open questions and topics — and emails it to the registered participants. That is the write-up from the section above, produced without anyone writing it. Add your CRM's inbound address to the meeting's **Recap copy** field and the same email is BCC'd there, landing on the prospect's record because the participants stay in the To field — the address the CRM matches against. One honest boundary: a prospect who joined without an account receives nothing after the call — no recap, no history. There is no delivery channel for them. Your follow-up email is the record they get, which is one more reason to send it the same day. --- ## Where the limits are The constraints that decide whether the free plan is enough for a discovery pipeline: | Plan | Voice translation | Chat translation | Participants | | ---------- | ------------------- | ---------------------- | ------------ | | Basic | 120 min / 30 days | 10,000 words / 30 days | 50 | | Pro | 1,500 min / 30 days | Unlimited | 100 | | Business | Unlimited | Unlimited | 300 | | Enterprise | Unlimited | Unlimited | 1,500 | The window is a rolling 30 days, and the voice-minute pool belongs to the host's account — four 30-minute discovery calls use up Basic's 120 minutes. A team running discovery weekly is on Pro from the start. --- ## FAQ **What does a discovery call mean?** A discovery call is the first scheduled conversation between a seller and a prospective customer, held to find out whether the prospect's problem is one the seller solves — their situation, what breaks, what it costs, who decides and when. It ends with a decision about fit and, if there is one, a dated next step, usually a demo. **Is a discovery call an interview?** No. An interview examines the person; a discovery call examines the situation, and the prospect does most of the talking. The seller's job is to ask, listen, and at the end say plainly whether there is a fit. If the prospect leaves feeling tested, or the seller leaves having presented rather than listened, the call was something other than discovery. **What is another way to say "discovery call"?** Qualification call, intro call, exploratory call, fit call or first call. Teams use them interchangeably for the same meeting: the first structured conversation before a demo or a proposal. **How long should a discovery call be?** Thirty minutes is enough when it is planned — roughly three minutes for agenda and permission, nine for the current situation, eight for the problem and its cost, six for the decision process, and four to summarize and agree the next step. Calls run long when the demo creeps in; keep the product out of it until you can describe the problem back in the prospect's own words. **What happens after a discovery call?** Three things: a write-up of what the prospect said, a same-day follow-up email restating it and confirming the next step with a date, and the write-up landing on the prospect's CRM record so the next person in the process reads it there. With a room that generates the recap and BCCs it to the CRM, the first and third steps happen without anyone writing them. **Can I run a discovery call when the lead prefers a different language?** Yes, without an interpreter and without changing the call. Put one InterMIND meeting link in your booking page description; the prospect joins from the confirmation email, picks their language, and you pick yours. Each side hears the other in their own language across 23 languages, and the recap arrives in your inbox afterwards. **Does the prospect need an account or an app to join?** No. They open the link in a browser, type a name, pick a language and wait for you to approve them. Nothing to install, no account to create, nothing to pay — the host's plan covers the room. A prospect who joins without an account does not receive the recap, so the follow-up email is the record they keep. --- ## Try it - **[Start a meeting and copy its link](https://intermind.com/chats)** — the link you would paste into a booking page description. - **[Try the live demo](https://intermind.com/demo)** — hear the translation before you set anything up. - **[See the multilingual support setup](https://intermind.com/blog/multilingual-customer-support)** — the same three steps, applied to customer calls. - **[See the book-a-demo flow](https://intermind.com/blog/book-a-demo)** — the same setup behind a "Book a demo" button, with our own page as the example. --- *Sources: Google Calendar Help, [Create an appointment schedule](https://support.google.com/calendar/answer/10729749){rel=""nofollow""} — account eligibility, where the description displays, and the conferencing options including "None / to be specified later" for third-party services. checked September 2026.* # GDPR-compliant messenger for companies (2026): what the vendors actually document - **No messenger is GDPR-compliant by itself.** The obligations sit with you, the controller; a vendor can make them fulfillable, nothing more. - **The checks a DPO asks anyway, plus language.** DPA, location, encryption, metadata, deletion, sub-processors; WhatsApp, Signal and Telegram document no DPA, the Swiss and German ones no translation. - **InterMIND keeps the whole space in each member's language,** with a DPA per customer, EU runtime at every hop, published sub-processors and, stated plainly, no end-to-end encryption. Guests join free by link, no account; you pay only for active members. "Which messenger is GDPR-compliant?" is a question no vendor can honestly answer with "we are". The GDPR puts the obligations on you, the controller: you need a data processing agreement (Art. 28), you need to know where the data sits and whether it crosses into a third country, you need to be able to delete and to answer access requests. A messenger can make those obligations *fulfillable* — or not. A badge on a homepage says nothing more than that. So this guide does something different from the usual lists. It takes six checks a data protection officer asks anyway and applies them to twelve services: the consumer messengers that companies actually run on (WhatsApp, Signal, Telegram), the business messengers from Switzerland and Germany (Threema Work, Teamwire, Wire, Stackfield), the self-hosted platforms (Element, Mattermost, Rocket.Chat) and the two bundles (Microsoft Teams, Slack). Then InterMIND, which we build — on the same criteria and with the same sourcing rule. Every statement comes from the vendor's public documentation, checked August 2026, linked at the end. A seventh check joins them, one that never appears on GDPR lists and matters every day in an international team: **in which language does each member read the channel?** A messenger that stores messages only in the original pushes translation onto the individual — and onto services that then process data again. --- ## The six checks Germany's Federal Commissioner for Data Protection (BfDI) publishes selection criteria for messenger services, the most usable public yardstick. They define end-to-end encryption as messages "encrypted on the sender's device and only decrypted again on the recipient's device", list privacy settings such as address-book access, profile visibility, read receipts, usage analytics and error reporting, and require account deletion where data is "deleted immediately". For company use, the Art. 28 obligations come on top. Together: 1. **Data processing agreement (DPA).** Does the vendor offer one — and is it in their documentation? 2. **Entity and server location.** Which company is your contracting party, where does the data sit, is there a third-country transfer? 3. **Encryption.** End-to-end, or transport and server-side? Both are legitimate — they just have to be named. 4. **Metadata and address book.** Is the address book uploaded? Which usage and device data is collected, and who is it shared with? 5. **Deletion and retention.** Where does the history live, who deletes it, what happens when an employee leaves? 6. **Sub-processors.** Are they published — including the services used for AI features and translation? Plus the seventh: **language per member.** --- ## The consumer messengers at work ### WhatsApp (and the WhatsApp Business app) - **Contracting party:** for the EEA, "WhatsApp Ireland Limited". - **Encryption and storage:** messages are end-to-end encrypted; "we do not retain your messages in the ordinary course of providing our Services to you. Once your messages are delivered, they are deleted from our servers." The history therefore lives on employees' devices and in their backups. - **Metadata:** collected are "information about your usage of our Services", device data ("hardware model, operating system information, battery level, signal strength") and, optionally, the address book ("contact upload … from your device address book on a regular basis"). Data is shared with "Meta Companies in the United States and Ireland" and transferred "globally". - **DPA:** the app's privacy policy names no data processing agreement for companies (checked August 2026). The Business app "is built with the small business owner in mind". - **Language:** since September 2025 a message can be translated by long-press — on the device ("translations occur on your device where WhatsApp cannot see them"); Android can auto-translate whole chats (six languages at launch), iPhone uses Apple's translation in 19+ languages. Voice notes and calls aren't part of the announcement. ### Signal - **Contracting party:** Signal Messenger LLC, Mountain View, California — a nonprofit. - **Encryption:** "Signal cannot decrypt or otherwise access the content of your messages or calls." - **Metadata:** registration by phone number; technical data is limited "to the minimum required to operate the Services". - **DPA:** none documented in Signal's legal documents (checked August 2026). - **Language:** no translation feature documented. ### Telegram - **Contracting party and location:** "Telegram Messenger Inc.", with "Telegram FZ-LLC, a group member located in Dubai"; for EU/EEA users, "your data is stored in data centers in the Netherlands". The GDPR representative is the European Data Protection Office (EDPO) in Brussels. - **Encryption:** cloud chats are server-side encrypted — "all data is stored heavily encrypted and the encryption keys in each case are stored in several other data centers in different jurisdictions" — and only secret chats are end-to-end: "Secret chats use end-to-end encryption." - **DPA:** not documented in the privacy policy (checked August 2026). - **Language:** "All users can translate individual messages"; Premium users "can translate entire chats, groups and channels in real time by tapping the Translate bar at the top". All three are tools teams genuinely work in. What they share: the history belongs to the device or to the vendor's cloud, not to the company — and the DPA that Art. 28 requires appears in none of the three documentations. ## Business messengers from Switzerland and Germany ### Threema Work - **Location:** Switzerland. The vendor notes that a data transfer from the EU to Switzerland is legally permissible without further review. - **Metadata:** Threema Work "requires no personal data (such as a phone number or e-mail address)" and "can be used without access to the address book". - **DPA:** according to the vendor, Threema Work "meets the requirements for data-protection-compliant processing on behalf of a controller under the GDPR and the Swiss DSG". - **Trial:** "30 days, 30 users. No automatic renewal." Per-user prices aren't on the page. - **Language:** no translation feature documented. ### Teamwire - **Location:** "German public cloud (IONOS, C5-certified)", "dedicated private cloud" or "full on-premise hosting"; "hosting in Germany instead of the USA", "no storage outside the EU". - **Certifications:** "ISO 27001, BSI C5, TÜV certified"; EU GDPR, BDSG, BSI IT-Grundschutz, NIS-2, DORA and CER are named. - **Metadata:** "no address book access" and "no analysis of communication". - **GDPR:** the vendor describes itself as "100 % GDPR-compliant" — a self-description the DPA has to make good on case by case. No prices on the page. - **Language:** no translation feature documented. ### Wire - **Location:** "cloud, on-premises or hybrid". - **Encryption:** MLS protocol; "messages, files and calls are fully E2EE by default"; video calls "with up to 200 participants", every session end-to-end encrypted. - **Certifications:** ISO 27001, ISO 27701, FedRAMP, FIPS 140-2. - **GDPR:** "fully compliant with strict data protection regulations, including GDPR" (self-description). No per-user prices on the page. - **Language:** no translation feature documented. ### Stackfield - **Location:** "all data processing is limited to the EU, and the data itself resides exclusively in German data centers"; the company is subject "exclusively to the jurisdiction of Germany and the EU". - **Encryption:** "true end-to-end encryption" for messages, files and tasks. - **Certifications:** ISO 27001, BSI C5. - **Meetings:** audio and video conferencing included. - **Language:** no translation feature documented. The four answer the location and encryption questions as clearly as a vendor can. What none of them documents: a translation that lets a Polish, a Portuguese and a German colleague read the same channel in their own language. ## Self-hosted platforms ### Element (Matrix) - **Encryption:** "the entire platform is end-to-end encrypted by default" — including Element Call for voice and video. - **Operation:** **Community** free, self-hosted; **Enterprise** per seat per month, self-hosted; **Sovereign** per deployment, air-gapped. - **Language:** no translation feature documented — with end-to-end encryption there is no server-side place for one. ### Mattermost - **Operation:** Professional and Enterprise as self-hosted annual licenses, prices on request; Mattermost Cloud Enterprise as a single-tenant offer. - **Language:** **automatic channel translation** (beta, since v11.5) on **Enterprise Advanced**: back-end is "LibreTranslate: a self-hosted, open-source machine translation engine" or "Agents: uses the Mattermost Agents plugin with a configured LLM backend"; a user's target language "is determined by their Mattermost display language". Translation runs on your server. ### Rocket.Chat - **Operation:** the **Starter** plan is free, "self-managed, self-hosted", "for technical evaluation or small teams of up to 50 users"; paid plans are Commercial, Government and Defense — on-premises, private cloud or air-gapped, prices on request. - **Language:** Auto-Translate per room — "each user receives translations based on their own selected language" — via **DeepL, Google Translate, Microsoft Translator or LibreTranslate**, with an API key the administrator supplies. Message text therefore goes to the provider you chose — unless it's LibreTranslate on your own host. Nextcloud Talk belongs in the same group: "a fully self hosted, on-premises audio/video and chat communication service", with live transcription and translation on your own hardware (details in the [team communication tools comparison](https://intermind.com/blog/team-communication-tools)). ## The bundles: Microsoft Teams and Slack ### Microsoft Teams - **DPA:** "When you subscribe to a Product under the terms of the Product Terms site, the data processing and security terms are defined in Microsoft Online Services Data Protection Addendum (DPA)." - **Location:** Teams data resides "in the geographic region associated with your Microsoft 365 or Office 365 organization"; country residency (Germany, France, Italy, Norway, Poland, Sweden, Switzerland and others) is "for new tenants only", existing EU tenants stay in the EMEA region. The **EU Data Boundary** commits Microsoft to store and process Customer Data for Microsoft 365 within the EU/EFTA — "subject to limited circumstances" with documented exceptions; customers with Multi-Geo are out of scope. - **Language:** chat and channel messages translate on request or automatically ("Teams can automatically translate received messages"), 100+ languages, no license named; in meetings, translated captions need the organizer's Teams Premium or Copilot license, and the Interpreter agent (10 languages) needs a Copilot license **per listener**, 20 hours a month. Details: [Teams live translation](https://intermind.com/blog/teams-live-translation). ### Slack - **DPA:** "Slack offers a Data Processing Addendum that supplements the Customer Terms of Service" — executed via a form, not incorporated automatically. - **Location:** data residency from **Business+**: Frankfurt, Paris, Stockholm, Zurich, London. Covered: messages, canvases, files and the search index; not covered: member profiles and usage analytics. The Free plan keeps 90 days of message history. - **Language:** "Translate message" on **Business+ and Enterprise+**, on request per message; "translations are only visible to you, so other people will always see the original message." ## InterMIND We build a communication space in which every member reads meetings, chat, documents and their history in their own language — and hold it to the same seven checks: 1. **DPA:** signed per customer — Art. 28 processor terms with a 30-day notice of new sub-processors and a 72-hour breach window; a signed copy is available for procurement ([/legal/dpa](https://intermind.com/legal/dpa)). 2. **Entity and location:** operated by an Estonian OÜ; the runtime is **in the EU at every hop** — voice and chat translation on our own engine on dedicated servers in France, meeting orchestration in Paris, database in Frankfurt, EU-resident storage and analytics. The map, vendor by vendor: [where one InterMIND meeting actually runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs). 3. **Encryption:** transport encryption — audio and video over DTLS/SRTP, chat and files over HTTPS/WSS and encrypted at rest on our servers. **No end-to-end encryption**: translation is processing, and it happens on our engine, not at a third party. If E2EE outranks everything else for you, Element, Wire or Threema are the better fit — we say so. 4. **Metadata and address book:** no address-book upload; participants join by link, without an account and without a phone number. 5. **Deletion and retention:** the retention criterion is written into the privacy policy — data stays until you or your team owner delete it; deleting an account deletes its data. We audited our own code against the GDPR obligations and documented what we closed: [GDPR audit](https://intermind.com/blog/gdpr-audit-what-we-closed). 6. **Sub-processors:** [published](https://intermind.com/legal/subprocessors), with function and domicile per vendor. The language-model steps (recap, document summaries, writing assistant, Ask AI) run on the AI gateway the organization selects — Azure OpenAI in the EU Data Zone by default, Vertex AI EU or Amazon Bedrock Frankfurt by choice — in InterMIND's own tenant with zero data retention and no training on customer content; the vendors are US companies operating EU regions, stated on the trust page. Document translation runs through DeepL as a named EU sub-processor. 7. **Language per member:** chat and notes in 23 languages, documents in 30, live speech for every participant in their own language — as the room's default behavior, without add-ons or per-listener licenses. Quality is published monthly per language pair: [/benchmark](https://intermind.com/benchmark). What we don't claim: an ISO certificate we don't yet hold. Our answer to the checklist is architectural and verifiable in the code; certifications are on the roadmap. --- ## The overview | Service | Contracting party / location | Encryption | DPA documented | Address book / metadata | Language per member | | ------------------- | ---------------------------------------------------------------------------------- | -------------------------------------------------------------------- | ----------------------------------------- | --------------------------------------------------- | ------------------------------------------------------------------------------ | | **WhatsApp** | WhatsApp Ireland; users' devices; shared with Meta Companies in the US and Ireland | End-to-end | Not documented | Optional address-book upload; usage and device data | On-device translation on request; Android auto per chat | | **Signal** | Signal Messenger LLC, California | End-to-end | Not documented | Phone number; metadata "minimum required" | Not documented | | **Telegram** | Telegram Messenger Inc. / FZ-LLC Dubai; EU data in the Netherlands | Cloud chats server-side; secret chats end-to-end | Not documented | — | Individual messages; whole chats on Premium | | **Threema Work** | Switzerland | End-to-end | Vendor: GDPR/DSG-compliant processing | No phone number, no address-book access required | Not documented | | **Teamwire** | Germany (IONOS C5) / private cloud / on-premise | "fully encrypted" | Self-description "100 % GDPR-compliant" | No address-book access | Not documented | | **Wire** | Cloud / on-premises / hybrid | End-to-end (MLS), calls included | Self-description GDPR-compliant | — | Not documented | | **Stackfield** | German data centers, DE/EU jurisdiction | End-to-end | — | — | Not documented | | **Element** | Self-hosted / air-gapped | End-to-end, calls included | Your own operation | — | Not documented | | **Mattermost** | Self-hosted; single-tenant cloud | Server-side, your operation | Your own operation | — | Auto per channel (beta), Enterprise Advanced, your LibreTranslate/LLM | | **Rocket.Chat** | Self-hosted; Starter free to 50 users | Server-side, your operation | Your own operation | — | Auto per room via DeepL/Google/Microsoft/LibreTranslate with your key | | **Microsoft Teams** | Tenant region; EU Data Boundary for EU/EFTA tenants | Transport + server-side | Yes — Microsoft DPA via the Product Terms | Tenant data | Messages on request/auto, 100+ languages; meeting language per Copilot license | | **Slack** | Residency from Business+ (Frankfurt, Paris, Stockholm, Zurich) | Transport + server-side | Yes — DPA via form | Profiles and usage analytics not residency-bound | On request, visible only to you, from Business+ | | **InterMIND** | Estonian OÜ; runtime EU at every hop (France, Paris, Frankfurt) | Transport (DTLS/SRTP, HTTPS/WSS) + encrypted on our servers; no E2EE | Yes — per customer, Art. 28 | No address-book upload; join without an account | Yes — every member reads and hears the space in their language, 23 languages | --- ## Which messenger for which case - **End-to-end encryption is your first criterion and translation doesn't matter:** Threema Work (Switzerland, no phone number), Wire (MLS, calls included), Stackfield (German data centers) or Element (self-hosted, free in the Community edition). - **Everything must run on your own servers, and you have the staff:** Rocket.Chat (free to 50 users, translation via your provider key), Mattermost Enterprise Advanced (beta channel translation on your LibreTranslate or LLM), Nextcloud Talk. - **You're a Microsoft or Slack customer anyway:** both document a DPA and EU residency — Teams via tenant region and the EU Data Boundary, Slack from Business+. Translation is per reader, on request; the meeting language in Teams hangs on Copilot licenses. - **The team works in WhatsApp, Signal or Telegram:** services documented for private communication, partly end-to-end encrypted — but with no documented DPA, the history on devices or in the vendor's cloud, and at WhatsApp usage and device data going to Meta companies in the US. A DPO will ask questions the documentation doesn't answer. - **The channel itself is multilingual** — colleagues and customers replying to each other in three languages, guests without your licenses, and a compliance team that wants to name the location: that's what we build [InterMIND](https://intermind.com/chats) for — every member reading the space in their own language, guests in by link without your licenses; EU at every hop, DPA per customer and published sub-processors are the one line for the DPO. ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener in any of 23 languages. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, monthly translation quality on real traffic, with the methodology public. - **[Read the sub-processors](https://intermind.com/legal/subprocessors)** — function and domicile per vendor, no request needed. --- ## FAQ **Which messengers are GDPR-compliant?** None is by itself — the obligations sit with the company. What can be checked is whether the vendor makes them fulfillable: a DPA is documented by Microsoft Teams (via the Product Terms), Slack (via a form), Threema Work (vendor: GDPR/DSG-compliant processing) and InterMIND (per customer, Art. 28); Teamwire and Wire describe themselves as GDPR-compliant. For WhatsApp, Signal and Telegram the documentation names no DPA (checked August 2026). Self-hosted services — Element, Mattermost, Rocket.Chat, Nextcloud — move the question into your own operation. **Is Signal GDPR-compliant?** Signal documents end-to-end encryption ("Signal cannot decrypt or otherwise access the content of your messages or calls") and technical data limited to the minimum; the contracting party is Signal Messenger LLC in California, registration is by phone number. The legal documents name no data processing agreement for companies. Private use is a different picture from company use, which has to satisfy Art. 28. **Is WhatsApp GDPR-compliant for business use?** WhatsApp Ireland documents end-to-end encryption and that delivered messages are deleted from its servers — and, at the same time, usage and device data, optional address-book upload and sharing with "Meta Companies in the United States and Ireland". The privacy policy names no DPA for the app; the Business app is, per the vendor, built for small business owners. Whoever uses WhatsApp in a company has to justify these points to the DPO themselves. **Is Telegram GDPR-compliant?** Telegram states that EU data is stored in the Netherlands and names an EU representative (EDPO, Brussels); cloud chats are server-side encrypted with keys "in several other data centers in different jurisdictions", only secret chats end-to-end. No DPA is documented. That's a documented data situation, not GDPR compliance in the Art. 28 sense. **Is Microsoft Teams GDPR-compliant?** Microsoft documents the DPA as part of the Product Terms, storage of Teams data in the tenant's region — country residency only for new tenants — and the EU Data Boundary for Microsoft 365 customers based in the EU/EFTA, with documented exceptions. For companies already on Teams that's a solid basis; the translation features in meetings depend on Copilot licenses per organizer and listener. **What must a GDPR-compliant messenger for companies offer?** Six documented answers instead of a badge: a DPA under Art. 28, a named entity and server location with no unexplained third-country transfer, a named encryption model, control over address book and metadata, a deletion concept that covers an employee leaving, and a published sub-processor list — including the AI and translation services. For international teams a seventh point joins: a messenger that stores the channel only in the original pushes translation onto every individual. **Is there a free GDPR-compliant messenger for companies?** Free and self-hosted: Rocket.Chat Starter (up to 50 users) and Element Community — the GDPR obligations then sit entirely in your own operation. Threema Work offers 30 days for 30 users without payment details. With InterMIND, participation is free for every participant — join by link without an account — and the [live demo](https://intermind.com/demo) needs no signup; the host pays for the room. --- *Sources: [BfDI — Selection criteria for messenger services (German)](https://www.bfdi.bund.de/DE/Buerger/Inhalte/Telemedien/Auswahlkriterien_Messengerdienst.html){rel=""nofollow""}, [WhatsApp — Privacy policy (EEA)](https://www.whatsapp.com/legal/privacy-policy-eea){rel=""nofollow""}, [WhatsApp — Privacy policy](https://www.whatsapp.com/legal/privacy-policy){rel=""nofollow""}, [WhatsApp blog — Introducing message translations](https://blog.whatsapp.com/introducing-message-translations){rel=""nofollow""}, [WhatsApp Business app](https://whatsappbusiness.com/products/business-app/){rel=""nofollow""}, [Signal — Terms & Privacy Policy](https://signal.org/legal/){rel=""nofollow""}, [Telegram — Privacy Policy](https://telegram.org/privacy){rel=""nofollow""}, [Telegram blog — Real-time translation](https://telegram.org/blog/profile-pics-emoji-translations){rel=""nofollow""}, [Threema — GDPR-compliant messenger (German)](https://threema.com/de/use-cases/gdpr-compliant-messenger){rel=""nofollow""}, [Teamwire — GDPR-compliant messenger (German)](https://teamwire.eu/loesungen/anwendungsfaelle/dsgvo-konformer-messenger/){rel=""nofollow""}, [Wire — Wire vs. MS Teams (German)](https://wire.com/de/wire-vs-ms-teams){rel=""nofollow""}, [Stackfield — Microsoft Teams alternative (German)](https://www.stackfield.com/de/microsoft-teams-alternative){rel=""nofollow""}, [Element — Pricing](https://element.io/pricing){rel=""nofollow""}, [Mattermost — Pricing](https://mattermost.com/pricing/){rel=""nofollow""}, [Mattermost — Set up Auto-translation (Beta)](https://docs.mattermost.com/administration-guide/manage/admin/autotranslation.html){rel=""nofollow""}, [Rocket.Chat — Our plans](https://docs.rocket.chat/docs/our-plans){rel=""nofollow""}, [Rocket.Chat — Auto-Translate messages](https://docs.rocket.chat/docs/auto-translate-messages){rel=""nofollow""}, [Nextcloud Talk](https://nextcloud.com/talk/){rel=""nofollow""}, [Microsoft — Products and Services Data Protection Addendum](https://www.microsoft.com/licensing/docs/view/Microsoft-Products-and-Services-Data-Protection-Addendum-DPA){rel=""nofollow""}, [Microsoft Learn — Location of data in Microsoft Teams](https://learn.microsoft.com/en-us/microsoftteams/location-of-data-in-teams){rel=""nofollow""}, [Microsoft Learn — What is the EU Data Boundary?](https://learn.microsoft.com/en-us/privacy/eudb/eu-data-boundary-learn){rel=""nofollow""}, [Microsoft — Translate a message in Microsoft Teams](https://support.microsoft.com/en-us/teams/chat/translate-a-message-in-microsoft-teams){rel=""nofollow""}, [Microsoft — Interpreter in Teams meetings and calls](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Slack — Data Processing Addendum](https://slack.com/terms-of-service/data-processing){rel=""nofollow""}, [Slack — Data residency for Slack](https://slack.com/help/articles/360035633934-Data-residency-for-Slack){rel=""nofollow""}, [Slack — Pricing](https://slack.com/pricing){rel=""nofollow""}, [Slack — Guide to AI features in Slack](https://slack.com/help/articles/25076892548883-Guide-to-AI-features-in-Slack){rel=""nofollow""}. Vendors change plans, locations, features and self-descriptions over time; check their pages for the current state. All facts checked August 2026.* # Email to channel: how any service posts into your team chat without a bot — and why an address beats a bot token - **Every channel has its own email address.** Anything that can send email posts into it: alerts, tickets, receipts, attachments kept, no bot, no token. - **An address beats a token when it matters.** Mail is queued and retried by the sender's server, no single platform can switch it off, no secret on your side. - **InterMIND keeps the whole space in each member's language,** so mail is read by each member in theirs and stays in the history. Guests join free by link, no account; you pay only for active members. Most of what a team needs to see during the day is not typed by a colleague. It is produced by a machine: the uptime monitor that noticed a slow endpoint, the payment processor that received an invoice, the helpdesk that opened a ticket, the CI pipeline that failed. Getting those messages into the place where the team actually talks is called "an integration", and in most chat tools it means a bot: create it, get a token, store the token, write or configure a sender, keep the token alive. InterMIND takes a shorter route. **Every channel has its own email address.** Anything that can send email can post into the channel, and nearly everything can send email. There is nothing to create on the InterMIND side beyond the address itself, nothing to install, and no token to keep. This post is the full mechanics of that route, plus an honest comparison with bot-based delivery on the four things that matter in practice: setup, secrets, delivery guarantees, and who can switch it off. The setup itself is on the [Email to Channel feature page](https://intermind.com/features/email-in); the reference is in the [docs](https://intermind.com/docs/integrations/email-in). ## How it works ### 1. The address The channel **host** opens the channel's display settings (the gear icon in the chat header), chooses **Email to channel** and clicks **Create address**. The result is a private address of the form `@in.intermind.com`. Only the host can see it, rotate it (**New address**) or remove it; both take effect immediately, and the old address stops working the moment a new one exists. Your personal **Inbox** has the same kind of address, visible to you alone. A channel address is for what the team should see; the Inbox address is for what only you should. ### 2. The sender Paste the address wherever a tool asks for a notification email. That field is the integration. An uptime monitor's alert channel, an error tracker's alert rule, a helpdesk's "notify on new ticket", a billing system's receipts, a CI server's build notifications, a form builder's submissions, a newsletter subscription — all of them have that field, and none of them need to know what InterMIND is. ### 3. What lands in the channel The email arrives as a regular channel message: - **Attributed to the sender.** The message carries the sender's name and address, not the host's, and is translated for each reader the way any external message is. - **Subject first.** The subject line becomes the first line of the message. - **Text, not boilerplate.** The plain-text part is used; an HTML-only email is converted to text. Signatures and quoted reply tails are stripped, so a forwarded thread shows the new content rather than the whole history. Bodies are capped at 100,000 characters. - **Attachments kept.** Each attachment becomes a file message, up to 25 MB per file. ### 4. Where it is read Members with the channel open see the message arrive live on web and desktop. Members who are not looking get a push on mobile. Each reads it in their own language, and it stays in the channel history like everything else. The flow is one-way: replying in the channel does not send email back to the sender. ### Limits, stated plainly - Attachments count toward the team's storage pool. When storage is full, the text still arrives and the attachment is skipped, with a note in the message saying so. - Up to 30 emails per hour per address; anything beyond that in the same hour is dropped. - Mail to an address that does not exist is dropped silently: no bounce, no reply. A guessed address gets no signal back. - Available on every plan. ## The same job with a bot A bot-based integration is not hard. It is just longer, and every step is a thing that can later break. Here is the Telegram version, because we ran one ourselves for our monitoring alerts until this week, and the Slack version, because it is the reference most teams know. **Telegram.** A bot is created through BotFather, which issues a token; every message is an HTTP call to the Bot API with that token and the numeric id of the target chat, and the token can be revoked and reissued through BotFather ([Telegram Bot API documentation](https://core.telegram.org/bots/api){rel=""nofollow""}, [Bots: From Beginner to Advanced](https://core.telegram.org/bots){rel=""nofollow""}, checked September 2026). So the sender needs the token and the chat id, and every place that sends needs both. **Slack.** Incoming Webhooks give an app a unique URL per channel; the URL is the secret, and Slack's own documentation tells you to treat it as one and to keep it out of public repositories ([Slack — Sending messages using incoming webhooks](https://api.slack.com/messaging/webhooks){rel=""nofollow""}, checked September 2026). One URL per channel per app, stored on every sender. Our own alert setup, before the switch, needed five things to exist and stay correct: a bot token in the monitoring vendor's variables, two secrets on the hosting platform, a webhook signing secret, a sender inside the error tracker's webhook handler, and a sending step inside the post-deploy watcher script. The email version of the same setup is one address, entered into each vendor's "notification email" field. On the InterMIND side the change is zero. ## Address vs token: four properties | | Channel email address | Bot token / webhook URL | | -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------- | | **What you create** | One address, from the channel itself | A bot or app, then a token or URL, then a sender that uses it | | **Where the secret lives** | Only in the tools that send; the host sees it in the channel | On every sender, plus wherever the bot is administered | | **Delivery when the receiver is down** | Store-and-forward: SMTP requires a sender to queue mail it cannot deliver and retry it later ([RFC 5321 §4.5.4.1](https://www.rfc-editor.org/rfc/rfc5321#section-4.5.4.1){rel=""nofollow""}) | One HTTP call; retry only if the sender implements it | | **Who can switch it off** | No single party: email is a federated protocol between independent servers | The platform that issued the token or URL | The last two rows are the ones that decide incidents. A bot API is a single vendor's endpoint on a single vendor's network: if the call fails, the message is gone unless the sender wrote retry logic, and if the platform is unreachable from where you are, so is the integration. Email was designed in the opposite direction. The sending server keeps the message and tries again; no one operator sits between sender and receiver. Rotation follows the same logic. Revoking a bot token means updating every sender that holds it. Rotating a channel address means updating the same senders, but with the difference that the address was never stored in your own code or infrastructure to begin with: it exists in the vendor's notification field and nowhere else. ## What this is for The obvious use is machine messages: alerts, receipts, tickets, build results. The less obvious one is people. A client who will never install anything can be told "send it to this address" and the whole team reads the thread in the channel, in their own language, with the attachments. A supplier's weekly report, a regulator's notice, a partner's contract draft: all of it lands where the work is already happening, without asking anyone to join anything. That is the point of a persistent space rather than a meeting: what arrives stays, in the language each member reads. Email-in is one more door into the same room. Telegram is another; that route is described in [How to bring your Telegram chats into InterMIND](https://intermind.com/blog/telegram-ingest-how-it-works). ## Try it - **[How to forward, select and bulk-delete messages in a team chat](https://intermind.com/blog/how-to-forward-select-and-delete-messages-in-a-team-chat)** — housekeeping for what the address brings in. - **[Read the Email to Channel feature page](https://intermind.com/features/email-in)** — the mechanics in one screen, with a demo. - **[Open the docs](https://intermind.com/docs/integrations/email-in)** — creating and rotating the address, the Inbox address, limits. - **[Try the live demo](https://intermind.com/demo)** — a meeting with an AI participant, no signup. ## FAQ **Which services can post into a channel by email?** Any service that can send email to an address you specify: uptime and error monitoring, ticketing and helpdesk systems, CRMs, billing and invoicing, CI pipelines, form builders, newsletters. If the tool has a field for a notification email, that field is the whole integration. **Who can see the channel's email address?** Only the channel host. The host creates it, rotates it and removes it from the channel's display settings. Members see the messages, not the address. **What happens if the address leaks?** Anyone who has it can post into the channel, so treat it like a password. Issue a new address from the same dialog; the old one stops working immediately. Mail to an unknown address is dropped without a bounce, so a guessed address learns nothing. **Do attachments come through?** Yes, as file messages, up to 25 MB per file. They count toward the team's storage pool; when storage is full, the text still arrives and the attachment is skipped with a note. **Are inbound emails translated?** Yes. The message is attributed to the external sender and translated for each reader like any other external message in the channel. **Can members reply to the sender from the channel?** No. The flow is one-way, email into the channel. Replies in the channel stay in the channel. **Is email-in available on the free plan?** Yes. Email to channel is available on every plan; the only plan-dependent part is the storage pool that attachments count against. **Why not just add a bot to Telegram or Slack?** You can, where the tool you want to connect supports it. The difference is what you maintain afterwards: a bot needs a token or a webhook URL stored on every sender and administered on the platform, delivers with one HTTP call, and depends on that platform being reachable. An address needs nothing stored on your side, is retried by the sender's mail server when delivery fails, and has no single operator who can switch it off. *Sources: [Telegram Bot API](https://core.telegram.org/bots/api){rel=""nofollow""} and [Bots: From Beginner to Advanced](https://core.telegram.org/bots){rel=""nofollow""} (token issued by BotFather; sendMessage takes a chat id; token revocation); [Slack — Sending messages using incoming webhooks](https://api.slack.com/messaging/webhooks){rel=""nofollow""} (one webhook URL per channel per app; the URL is a secret); [RFC 5321 §4.5.4.1 — Sending Strategy](https://www.rfc-editor.org/rfc/rfc5321#section-4.5.4.1){rel=""nofollow""} (queued mail retried until delivered or given up). Checked September 2026.* # English gets the first contact. The deal runs in the partner's language - **The first email is in English; the deal is not.** Quote, negotiation and claim run in the partner's language, paid per word, per day and per hire. - **The spend does not accumulate.** The interpreter leaves, the PDF goes stale, the hire moves on; call tools cover only the call. - **InterMIND keeps the whole deal in each side's language,** calls, chat, files and the recap in a channel the next buyer reads on day one. Guests join free by link, no account; you pay only for active members. An export desk rarely loses a deal at the first email. The first email is in English, on both sides, and English is enough for it: a product, a price range, a date. The deal moves to the partner's language later, when the distributor's buyer and your sales lead sit down over a price list, a spec and a claim, each of them with a second language that goes as far as a first contact. That is the moment the export desk has paid for since long before translation software existed, and the money goes to things that do not stay with the deal. This guide walks an export deal stage by stage and asks two questions at each one: which language does this stage run in, and what does the desk pay for that language today. ## The study that named it The European Commission's ELAN study (2006) surveyed 1,989 exporting SMEs in 29 European countries. Eleven percent, 195 companies, said they had lost a contract because of a lack of language skills. The qualitative part put the pattern into one sentence: *"English might be used for initial market entry, but longer-term business partnerships depended upon relationship-building and relationship-management and, to achieve this, cultural and linguistic knowledge of the target country were essential."* Twenty years on, the shelf of translation tools is longer, and the shape of the deal is the same. The latest Eurobarometer on languages (fieldwork autumn 2023, published 2024) finds that 47 % of EU respondents can hold a conversation in English. On a call between an Italian supplier and a Moroccan distributor, or a Spanish exporter and a Polish buyer, the share on each side is whatever it is. The first contact survives it. The negotiation and the spec do not. ## Where English stops: a deal in five stages | Stage | Who talks | The language it runs in | What the export desk pays for it today | What stays with the deal afterwards | | ---------------------------------------------- | --------------------------------- | --------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------- | | Enquiry, first call | Your sales lead, their buyer | English on both sides | Nothing extra | An email thread | | Quote, spec, price list | Sales lead, their technical buyer | The partner's language, or two half-languages | Agency per word (one source lists 0.089 € per word for Spanish to Italian, so a 1,000-word spec is 89 €, retrieved October 2026) | A translated PDF, one version per language, re-sent after every change | | Negotiation, supplier visit | Owner, buyer, factory | The partner's language | A liaison interpreter by the day (one Spanish agency lists 400 € per half-day and 550 € per day excl. VAT; the French SFT × AIIC 2023 survey puts the median liaison day at 644 € excl. VAT) | The interpreter's memory, and whoever took notes | | Claims, delays, the next order | Back office, their logistics | The partner's language, by email and in chat | A hire picked for the language (an "impiegata commerciale estero" is advertised at 28,188 € a year in Italy, an "assistant export" at 31,651 € in France, both retrieved 2026) | Whatever that person remembers and files | | Twelve months later, a new buyer on their side | Everyone again | Starts from English again | The same list from the top | Almost nothing readable by the new person | Three things in that table are structural, not a matter of tool choice. **The spend is per event.** Each quote, each visit, each claim is paid for separately, and the price list given above is per word, per day and per hire. None of these prices is per deal. **The spend does not accumulate.** The interpreter leaves, the PDF goes stale at the next price change, the hire changes job. ELAN's 2006 numbers show how much of this was already outsourced then: 39 % of Italian, 52 % of Spanish and 23 % of French SMEs had used external translators, and 28 %, 56 % and 61 % respectively had hired staff specifically for their language skills. **The next person starts from zero.** A distributor changes its buyer, your desk changes its export assistant, and the last two years of negotiation exist in a language one of the two sides cannot read. ## What the call tools cover, and what they leave The three suites most export desks already pay for translate the call while it runs. Facts from their documentation, checked October 2026: - **Microsoft Teams** offers live translated captions in meetings; the feature requires a Teams Premium or Microsoft 365 Copilot licence ([documentation](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}). - **Zoom** offers translated captions, "automatically translated in real-time to captions in another language", on eligible paid accounts ([documentation](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0059081){rel=""nofollow""}). - **Google Meet** offers speech translation between English and French, German, Hindi, Italian, Portuguese and Spanish on eligible Workspace editions ([documentation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}). Each of these covers row three of the table, the call, for the duration of the call. The spec in row two and the claim in row four are not calls, and a new buyer in row five was not in the meeting. ## What InterMIND changes in the table InterMIND is built so that the deal, not the moment, runs in each side's language. The facts, as the product works today: - **Your partner joins by link, without an account, free.** The distributor's buyer opens the link from their phone or laptop and speaks their own language. Nobody on their side installs or signs up for anything. - **23 languages live for voice, chat, notes and the recap**, in any pair, with no English in the middle. Italian to Arabic, Spanish to Polish, French to Turkish, each person hears and reads the other in their own language. Per-pair quality is published on real traffic at [/benchmark](https://intermind.com/benchmark). - **The spec, the price list and the claim are read in each language.** PDF, Word, PowerPoint and Excel files opened in the call or dropped into the channel are readable in 30 languages. One file, not one file per language. - **The deal becomes a channel.** A call started from your calendar or from Slack ends with a recap in each member's language, and the channel keeps every meeting's recaps, chat and files readable to your team, in each member's language. The new buyer on their side, or the new assistant on yours, reads two years of history on day one. (An ad-hoc call by link, outside a channel, leaves its recap and nothing else.) - **Billing counts the people who use it.** Pro and Business bill per active member over the previous 28 days; quiet members keep their access at no cost, and guests never pay. Live prices are on [/pricing](https://intermind.com/pricing). How this looks for a distributor network, step by step, is on the [export and import use case](https://intermind.com/use-case/export-import). The mechanics of per-listener translation are in [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines), and the mechanism that makes "good-enough" English on both sides riskier than no English is in [*The false-fluency trap*](https://intermind.com/blog/false-fluency-trap). ## FAQ **What does a business interpreter cost?** By the day or half-day, and the rate depends on country and pair. Public price lists checked in October 2026 give 400 € per half-day and 550 € per day, excluding VAT, for liaison interpreting in Spain, and a median of 644 € excluding VAT per day in France according to the SFT × AIIC 2023 survey. Pairs outside the main European languages are usually quoted case by case. The rate buys the meeting; it does not buy the record of it. **Do I need a trade show interpreter?** For the stand, a day interpreter does the job: short exchanges, a lot of first contacts, English on both sides for most of them. The deals that follow the fair are a different stage. The follow-up call with the three distributors who stopped at the stand runs in their language, and that call is what [a translated meeting room with guests by link](https://intermind.com/use-case/export-import) is for. **Is a telephone interpreter for business enough?** For one call, yes. A telephone interpreter is paid per minute or per call and leaves nothing behind. If the same partner calls every week and sends a spec in between, the per-call model pays for the same conversation again each time. A channel that keeps the recaps and files in each language pays once for the deal. **My partner only speaks Chinese. Does the call work from their side?** Chinese is one of the 23 live languages. Your partner opens the link, picks Chinese, and hears you in Chinese while you hear them in your language. They need no account and pay nothing. The spec you share in the call is readable in Chinese too. ## Try it - **[Try the live demo](https://intermind.com/demo)**: hear a real call translated per listener, in your language and your partner's, with no signup. - **[See the benchmark](https://intermind.com/benchmark)**: per-pair quality on real traffic, methodology included. - The full walk-through for distributors, suppliers and agents: [export and import](https://intermind.com/use-case/export-import). — The Mind.com Team --- *Sources: [ELAN: Effects on the European Economy of Shortages of Foreign Language Skills in Enterprise](https://ec.europa.eu/assets/eac/languages/policy/strategic-framework/documents/elan_en.pdf){rel=""nofollow""}, European Commission / CILT, December 2006 (1,989 SMEs, 11 % lost a contract; Figures 5.5 and 5.12); [Special Eurobarometer 540, Europeans and their languages](https://europa.eu/eurobarometer/surveys/detail/2979){rel=""nofollow""}, fieldwork September–October 2023, published May 2024 (47 % of EU respondents can hold a conversation in English); [Mondo Agit, interpreting rates](https://www.mondoagit.com/tarifas/tarifas-en-interpretacion/){rel=""nofollow""} and [translation rates](https://www.mondoagit.com/tarifas/tarifas-en-traduccion/){rel=""nofollow""}, Spain, retrieved 11 October 2026; [SFT × AIIC, survey of interpreters 2023](https://www.sft.fr/docs/2024091507_webinaire-resultats-enquete-interpretes-2023-sft-aiic.pdf){rel=""nofollow""}, France; salaries: Jooble, "impiegata commerciale estero", retrieved 29 July 2026; Indeed, "assistant export", retrieved 5 October 2026; vendor documentation for Microsoft Teams, Zoom and Google Meet, checked October 2026. Vendors change features and language lists; check their pages for the current state.* # How to export a Microsoft Teams chat (2026): what users can do, what admins can do, and why history goes missing - **Teams has no Export button.** A member can copy or share to Outlook; export paths belong to admins. - **Missing history is a retention policy.** Messages it deletes cannot be recovered, and every path out hands you the chat in the language it was written. - **InterMIND keeps the whole space in each member's language,** chat, recaps and files per reader, and a self-service backup on plans with export, next to Teams rather than instead of it. Guests join free by link, no account; you pay only for active members. The moment you need a Teams chat outside Teams — a customer dispute, a handover, a colleague leaving, a decision someone wants in writing — you discover the thing the search results dance around: **the Teams client has no Export button.** Microsoft's documentation describes two export paths, both for administrators, and a handful of things an ordinary member can do. This guide lists all of them exactly as documented, checked August 2026, and then the second question people actually arrive with: why the history they wanted to export is no longer there. ## What a member can do (no admin needed) - **Copy the messages.** Select text in the chat and paste it into a document. It's manual, it loses formatting and attachments, and it's the only fully self-service path Microsoft documents for a member. - **Share to Outlook.** A message or thread can be sent to Outlook from Teams ("Share to Outlook") — useful to get a specific exchange into email, where it can be filed or printed to PDF. It's a message-by-message action, not a chat export. - **Share history when adding someone.** When you add people to an existing group chat, "you can also choose how much of the chat history to include" — and "you can include chat history only when adding someone to an existing group chat, not for a one-on-one." This doesn't export anything, but it's the documented way to hand a chat's past to a new person inside Teams. - **Download a meeting transcript.** For meetings that were transcribed, organizers and co-organizers can download the transcript as a .docx or .vtt file from the meeting chat or the Recap tab. That covers what was *said* in a meeting, not the chat. None of these produce a file of the chat. For that, Microsoft documents the two paths below. ## What an admin can do: the two documented export paths ### 1. Teams Export APIs (Microsoft Graph) "Teams Export APIs allow you to export 1:1, group chat, meeting chats, and channel messages from Microsoft Teams." The documented shape: - They run as an **application**, not a signed-in user: "application permissions are used by apps that run without a signed-in user present. Only an administrator can approve application permissions" — *Chat.Read.All*, *ChannelMessage.Read.All*, *User.Read.All*, plus transcript and recording permissions for meetings. - They require "an active Microsoft Teams license assigned to the users whose data is being exported"; no Purview DLP plan is needed. - What comes out: messages with attachments metadata, reactions, control messages ("User A added User B to the chat and shared all chat history"), edit history where a retention policy is set, and links to meeting recordings (MP4) and transcripts (VTT or DOCX). - Deleted messages "can be accessed using export APIs up to 21 days from the time of deletion"; messages from deleted teams and channels for 30 days. In practice this is a developer or a certified archiving partner writing against Graph, with an admin approving the app. It's the path for "export everything, regularly". ### 2. Purview eDiscovery / Content search The compliance path. Teams messages are journaled into Exchange Online: "all Microsoft Teams 1:1 or group chats are journaled through to the respective users' mailboxes. All standard channel messages are journaled through to the group mailbox representing the team." An eDiscovery search over those mailboxes finds them, and the export lands as a `.pst` you open in Outlook — "all conversations are located in the Team Chat folder under Conversation History" — or as an Excel output where Teams data "appears as IM or Conversations". Running it requires the eDiscovery Manager role in the Purview portal. That's the path for "export this chat for legal, HR or a dispute" — by someone with the role, not by the person in the chat. ## Why the history you wanted is missing The second search behind "export teams chat" is "teams chat history missing", and Microsoft documents exactly one mechanism: **retention policies**. An organization can set Teams chats and channel messages to be deleted after a period; when it fires, "a system message will replace the ones deleted by an org's retention policy", "messages deleted by a retention policy can't be recovered", and the advice is "to figure out how long your org's retention policy is, reach out to your IT admin." Two documented details explain the surprises: - The deletion applies to the conversation, not just to your tenant's users: "the corresponding message in the Teams client app is deleted for all users in the conversation" — including people from another organization with a longer policy, who then "won't be able to see the message in Teams" even though a copy may still exist in their mailbox for eDiscovery. - What you see isn't the record: "messages visible in the Teams app are not an accurate reflection of whether they're retained or permanently deleted for compliance requirements." A user-deleted message stays discoverable for 21 days; policy-expired messages sit in a hidden folder for at least a day before permanent deletion, and any legal hold suspends deletion. So if the chat is gone from your screen, an eDiscovery search by an admin may still find it — for a while. ## Where this leaves a team Put together, Teams' documentation describes a space whose history belongs to the tenant: members read it, admins export it, retention decides how long it exists, and every path out — API, PST, copy-paste — hands you the messages in the language they were written in. For a single-language team inside one organization that's a coherent design. It gets awkward in two cases: a member who needs *their* history without an admin, and a team whose history is in three languages, where the export is only as readable as the reader's languages. ## What an export looks like when the history is built to be kept We build [InterMIND](https://intermind.com/chats) around the record a space leaves behind, so the equivalent facts, stated the same way: - **Self-service export.** On plans that include data export, *Settings → Backup & Restore → Create Backup* produces a ZIP of your chats — messages, meeting transcriptions, files, images and recordings — and *Restore from Backup* brings selected chats back, with pins, reactions and translations. No admin role, no API. Documentation: [Backup & Restore](https://intermind.com/docs/settings/data-export). - **The meeting's record has a permanent link.** Every meeting's recap — summary, decisions, action items, recording — lives at one address, minted when the meeting is scheduled, open to signed-in members of that meeting. Channels keep the recap of every session. ([Meeting recap](https://intermind.com/blog/meeting-recap)) - **The history reads in each member's language.** Chat history, recap and documents are rendered per reader — a member who reads Polish reads last month's decision in Polish, without exporting anything. ([How much of your meeting still exists a week later](https://intermind.com/blog/the-meeting-a-week-later)) - **Retention you control.** Data stays until you or your team owner delete it — the criterion is written into the privacy policy — and the team audit log exports as CSV for owners and admins. Deletion and export are self-service in the product, which is also what our [DPA](https://intermind.com/legal/dpa) says. ## Which path for which need | You need | Teams: documented path | Who can do it | | ----------------------------------------------- | ---------------------------------------------------------------------- | -------------------------------------- | | A few messages in a document or email | Copy, or Share to Outlook | Any member | | A new colleague to see the past of a group chat | Add them and choose how much history to include (group chats only) | Any member | | What was said in a meeting | Download the transcript (.docx / .vtt) | Organizer, co-organizer | | The whole chat as a file, for a dispute or HR | Purview eDiscovery / Content search → .pst | eDiscovery Manager role | | All messages, continuously, into an archive | Teams Export APIs via Graph, admin-approved app | Admin + developer or archiving partner | | History that disappeared | Ask the admin about the retention policy; eDiscovery may still find it | Admin | | Your own chats as a ZIP, and back | InterMIND Backup & Restore | You, on plans with data export | ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener in any of 23 languages. - **[Start your first meeting](https://intermind.com/chats)** — guests join by link, each in their own language. - **[Read the Backup & Restore docs](https://intermind.com/docs/settings/data-export)** — what the ZIP contains and how restore works. --- ## FAQ **How do I export a Teams chat?** As a member: copy the messages, or share individual messages to Outlook. As an admin: run a Purview eDiscovery / Content search over the participants' mailboxes and export the result as a .pst, or use the Teams Export APIs through an admin-approved application. Microsoft's client documentation offers no Export button for a chat. **How do I export a Teams chat to PDF?** Microsoft doesn't document a PDF export. The documented routes end in a .pst (eDiscovery), JSON via Graph (Export APIs), or a message shared to Outlook — from Outlook, an email prints to PDF. Copying the chat into a document and saving it as PDF is the practical member-level route. **Why is my Teams chat history missing?** Because of a retention policy, per Microsoft: deleted messages are replaced by a system message, "can't be recovered", and the advice is to ask your IT admin how long the policy keeps messages. The deletion applies to everyone in the conversation, including people in other organizations. **Can I see chat history from before I was added to a group chat?** Only if the person who added you chose to include it: when adding people to an existing group chat, the adder chooses how much history to include; for one-on-one chats there's no such option. **Can an admin export a Teams chat between two people?** Yes — 1:1 chats are journaled into the mailboxes of both participants, so an eDiscovery search on either mailbox finds them, and the Export APIs cover "1:1, group chat, meeting chats, and channel messages". **How do I export my own chats without an admin?** In Teams, you can't beyond copy and Share to Outlook. In InterMIND, Backup & Restore on plans with data export creates a ZIP of your chats, transcriptions, files and recordings, and restores selected chats later. **Same question, but the chat is on WhatsApp?** Different tool, different limits — Export chat, what it carries, and what to do when the menu item isn't there: [how to export a WhatsApp chat](https://intermind.com/blog/export-whatsapp-chat). --- *Sources: [Microsoft Learn — Export content with the Microsoft Teams Export APIs](https://learn.microsoft.com/en-us/microsoftteams/export-teams-content){rel=""nofollow""}, [Microsoft Learn — Finding content in Microsoft Teams in eDiscovery](https://learn.microsoft.com/en-us/purview/edisc-search-teams){rel=""nofollow""}, [Microsoft Learn — Learn about retention for Teams](https://learn.microsoft.com/en-us/purview/retention-policies-teams){rel=""nofollow""}, [Microsoft Support — Teams messages about retention policies](https://support.microsoft.com/office/teams-messages-about-retention-policies-c151fa2f-1558-4cf9-8e51-854e925b483b){rel=""nofollow""}, [Microsoft Support — Chat with others in Microsoft Teams](https://support.microsoft.com/en-us/office/chat-with-others-in-microsoft-teams-0c71b32b-c050-4930-a887-5afbe742b3d8){rel=""nofollow""}, [Microsoft Support — Share to Outlook from Microsoft Teams](https://support.microsoft.com/en-us/office/share-to-outlook-from-microsoft-teams-f9dabbe9-9e9b-4e35-99dd-2eeeb67c4f6d){rel=""nofollow""}, [Microsoft Support — Start, stop, and download live transcripts in Microsoft Teams meetings](https://support.microsoft.com/en-us/teams/meetings/start-stop-and-download-live-transcripts-in-microsoft-teams-meetings){rel=""nofollow""}. Microsoft changes features and admin tooling over time; check the pages for the current state. All facts checked August 2026.* # How to export a WhatsApp chat (2026): what Export chat does, what it doesn't, and what to do when the option isn't there - **One conversation, as a text file.** Export chat sends a single chat, with or without media, through the share sheet: a copy, not a backup or transfer. - **It is not always there.** Advanced Chat Privacy lets the other participant block it, WhatsApp Web lacks it, and Germany has lacked it since 2019. - **InterMIND keeps the whole conversation in each member's language,** chat, recap and files at a permanent address, with no export to run. Guests join free by link, no account; you pay only for active members. "Export chat" is one of those WhatsApp menu items people tap without knowing what it does — and search for afterwards. The short version: it sends **one conversation** out of WhatsApp as a text file, optionally with recent media, through whatever your phone can share to. It isn't a backup, it isn't a transfer to a new phone, and it isn't available everywhere. Here is the feature as WhatsApp documents it, checked August 2026, and the cases people actually have when they reach for it. ## What "Export chat" means Export chat produces a file of a single chat's messages — a `.txt` with one line per message, timestamped — and hands it to your phone's share sheet. WhatsApp's help article describes the destinations as the usual share targets: "you can export chat history using methods such as Message, Mail, or Add to Notes." If you choose to include media, "the most recent media sent will be added as attachments" to that share. Two consequences follow from that design: - **It's per chat.** There is no "export all chats" — that's what backup is for (below). - **It's a copy, not a move.** The chat stays in WhatsApp; the file is yours to email, save or print. Nothing about the conversation changes. ## How to export a chat on Android and iPhone - **Android:** open the chat → *More options* (⋮) → *More* → *Export chat* → choose *Include media* or *Without media* → pick where to send it. - **iPhone:** open the chat → tap the contact or group name → scroll down → *Export chat* → choose *Attach media* or *Without media* → pick where to send it. The exact labels come from the app; WhatsApp's help article for the feature is [How to export your chat history](https://faq.whatsapp.com/1180414079177245){rel=""nofollow""}. Media adds size fast — for a long group chat, *Without media* is usually the version that actually sends. ## Does the other person see that I exported the chat? WhatsApp's documentation of Export chat describes no notification to the other side. What it does document, since April 2025, is the reverse control: with **Advanced Chat Privacy** turned on for a chat, "you can block others from exporting chats, auto-downloading media to their phone, and using messages for AI features" — "you can turn this on by tapping the chat name, then tapping on Advanced Chat Privacy." So if *Export chat* is greyed out or missing in one specific chat, the other participant may have switched that on. ## Export, backup, transfer: three different things People search "export chat" for three different jobs. Only one of them is Export chat. | You want | The WhatsApp feature | What it produces | | ------------------------------------------------------ | --------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------ | | One conversation as a file you can read, send or print | **Export chat** | A `.txt` (plus recent media, optionally) via the share sheet | | All your chats saved so you can restore them | **Chat backup** — Google Account (Android) or iCloud (iPhone); optional end-to-end encrypted backup | A backup only WhatsApp can restore, on the same phone number | | Your chats on a new phone | **Transfer chat history** — Android→Android, iPhone→iPhone, or across platforms | The full account moved, "including all of your messages and media" | Backups and transfers stay inside WhatsApp; only Export chat gives you a file you can open elsewhere. And WhatsApp itself keeps none of it: "we do not retain your messages in the ordinary course of providing our Services to you. Once your messages are delivered, they are deleted from our servers." The record of a WhatsApp conversation exists on the participants' phones and in their backups — nowhere else. ## When the option isn't there - **In Germany, Export chat isn't offered.** The option has been absent from the app for German users since 2019, as reported in the press at the time; WhatsApp's help center doesn't document the restriction or its reason (checked August 2026). The documented alternatives — backup and transfer — work, but produce nothing you can read outside WhatsApp. - **In one specific chat:** see Advanced Chat Privacy above — the other participant can block exporting. - **On WhatsApp Web / Desktop:** Export chat is a phone feature; export on the phone. ## Export chat to PDF WhatsApp exports text, not PDF. The documented route to a PDF is the share sheet: send the export to Mail or Notes, open it on a computer, and print to PDF — or share the `.txt` straight to a file app. Third-party "WhatsApp to PDF" tools do the same conversion, with the difference that they need the chat taken out of the encrypted app and handed to them first. ## When the chat you're exporting is your team's record Most exports are one-offs: a landlord's message, an order confirmation, a conversation someone wants on paper. The recurring export is a different signal. If you're exporting the same group every month because the decisions live there, or because the customer conversation has to be filed, or because half the group writes in a language the other half can't read, you're using a phone messenger as a record system — and the export is doing the job the tool doesn't. That case is what we build [InterMIND](https://intermind.com/chats) for, and the export changes shape: - **The history is the record, not a file.** A meeting becomes a channel; chat, recap and documents stay at a permanent address that signed-in members open in their own language — a member who reads Portuguese reads last month's decision in Portuguese, without exporting anything. ([How much of your meeting still exists a week later](https://intermind.com/blog/the-meeting-a-week-later)) - **When you do want a file, it's all of it, and it restores.** *Settings → Backup & Restore* produces a ZIP of your chats — messages, meeting transcriptions, files, images, recordings — and restores selected chats later, on plans that include data export. ([Backup & Restore](https://intermind.com/docs/settings/data-export)) - **It's translated for every member, live and afterwards** — 23 languages for voice, chat and notes — and participants join by link, free, without an account. ([Why participation is free](https://intermind.com/blog/free-for-participants)) - **It runs in the EU at every hop.** ([Where one InterMIND meeting actually runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs)) WhatsApp's own message translation — long-press → *Translate*, on the device — covers reading a message you receive; we wrote up the whole feature and where it stops: [how to translate WhatsApp messages](https://intermind.com/blog/whatsapp-translate). For Telegram groups there's a bridge into InterMIND channels; for WhatsApp, Export chat is the documented way out. ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener in any of 23 languages. - **[Read the Backup & Restore docs](https://intermind.com/docs/settings/data-export)** — what the ZIP contains and how restore works. --- ## FAQ **What does "export chat" mean on WhatsApp?** It sends one conversation out of WhatsApp as a text file — with or without recent media — through your phone's share sheet, to Mail, Messages, Notes or a file app. The chat itself stays in WhatsApp unchanged. It's not a backup and not a transfer to a new phone. **How do I export a WhatsApp chat?** Android: open the chat → ⋮ → *More* → *Export chat* → with or without media → choose a destination. iPhone: open the chat → tap the name at the top → *Export chat* → with or without media → choose a destination. **Does exporting a WhatsApp chat notify the other person?** WhatsApp's documentation describes no notification. It does document the opposite: a participant can turn on Advanced Chat Privacy for a chat, which blocks others from exporting it. **Why can't I export a WhatsApp chat?** Three documented reasons: the other participant has Advanced Chat Privacy on for that chat; you're on WhatsApp Web or Desktop, where export isn't offered; or you're in Germany, where the option hasn't been available since 2019 — a restriction reported in the press and not documented by WhatsApp's help center. **How do I export a WhatsApp chat as a PDF?** Export the chat without media to Mail or Notes, open it on a computer and print to PDF. WhatsApp itself exports text only. **Is export the same as backup?** No. A backup (Google Account or iCloud, optionally end-to-end encrypted) saves all your chats in a form only WhatsApp can restore, on the same phone number. Export chat gives you one conversation as a readable file. Transferring chat history is a third feature, for moving to a new phone. **How long does WhatsApp keep my chats on its servers?** It doesn't, once delivered: "once your messages are delivered, they are deleted from our servers"; an undelivered message is kept "in encrypted form on our servers for up to 30 days" while delivery is retried. Your chats exist on the phones in the conversation and in their backups. --- *Sources: [WhatsApp — How to export your chat history](https://faq.whatsapp.com/1180414079177245){rel=""nofollow""}, [WhatsApp — How to back up your chat history](https://faq.whatsapp.com/481135090640375){rel=""nofollow""}, [WhatsApp — How to transfer your chat history](https://faq.whatsapp.com/209942271778103){rel=""nofollow""}, [WhatsApp — About end-to-end encrypted backup](https://faq.whatsapp.com/490592613091019){rel=""nofollow""}, [WhatsApp blog — Introducing Advanced Chat Privacy](https://blog.whatsapp.com/introducing-advanced-chat-privacy){rel=""nofollow""}, [WhatsApp — Privacy policy](https://www.whatsapp.com/legal/privacy-policy){rel=""nofollow""}, [WhatsApp blog — Introducing message translations](https://blog.whatsapp.com/introducing-message-translations){rel=""nofollow""}; the Germany restriction as reported by [MSPoweruser (2019)](https://mspoweruser.com/whatsapp-removes-export-chat-history-feature-in-germany/){rel=""nofollow""} — not documented in WhatsApp's help center. WhatsApp changes features and availability over time; check its pages for the current state. All facts checked August 2026.* # The false-fluency trap: when "good-enough" English is worse than no English - **Knowing a language poorly is worse than not knowing it.** A visible gap gets an interpreter; a fluent-sounding error gets minuted as agreed, surfacing weeks later. - **Aviation and medicine already acted on it.** ICAO made operational English a licence requirement; Flores found an untrained bilingual interpreter no better than none. - **InterMIND keeps the whole meeting in each member's language,** so nobody works in a language they do not own, with per-pair quality published monthly. Guests join free by link, no account; you pay only for active members. > **TL;DR — Knowing a language poorly is worse than not knowing it at all.** > > *Not* knowing it makes the gap visible: the room agrees on an interpreter and reorganizes around it. :br*Poorly* knowing it hides the gap: fluent-sounding errors get minuted as agreed; the cost surfaces weeks later in the contract review. > > Aviation regulators acted on this mechanism in 2008. Medical research has been counting it since 2003. The boardroom hasn't. Every cross-border meeting today defaults to a shared language nobody fully owns — almost always English. The arrangement *feels* like it works. The rest of this post is the evidence that it works less than people think, drawn from three independent literatures (aviation safety, medical interpretation, international-business research), and an honest engagement with the strongest published counterargument (the *Foreign-Language Effect*). --- ## How many people in the room are operating in a second language? Of the roughly 1.5 billion English speakers in the world, about **400 million are native**; the remaining 1.1 billion learned English as a second or additional language (David Crystal, *English as a Global Language*, Cambridge University Press, 2nd ed., 2003; Ethnologue speaker estimates). In any cross-border business meeting the ratio is usually worse than the global average, because English is over-represented in professional contexts. EF Education First publishes an annual [English Proficiency Index](https://www.ef.com/wwen/epi/){rel=""nofollow""} covering more than 100 countries. "Very high proficiency" is defined there as the ability to *"use nuanced language in social, professional, and academic situations."* That is the bar most measured populations *do not* clear. The median country sits in the "Moderate" band; "High" and "Very High" are concentrated in a small set of Northern European and a few East Asian economies. In practice, the average global business meeting is staffed mostly by people operating somewhere between **B1 and C1** on the Common European Framework — fluent enough to function in routine conversation, *not* fluent enough to argue contract language, regulatory nuance, or technical edge cases without loss. That is the population the rest of this post is about. --- ## Failure mode 1 — False precision Fluent-sounding non-native speech is the most expensive failure mode in this space, because it removes the signal that anything needs checking. Lev-Ari and Keysar showed that listeners judge information delivered in a non-native accent as **less credible**, even when the content is identical and the speaker is reading from a script ([*Why don't we believe non-native speakers?*, Journal of Experimental Social Psychology, 2010](https://doi.org/10.1016/j.jesp.2010.05.025){rel=""nofollow""}). The bias is automatic, robust, and one-directional. The *opposite* half of the same bias is the more expensive one in business. When a non-native speaker produces a sentence that *sounds* fluent — grammar correct, intonation natural — listeners assume comprehension is symmetric: that the speaker understood the surrounding discussion as well as they appear to have produced their own sentence, and that the listener understood the speaker as well as they appear to have spoken. Both assumptions are routinely wrong. Tenzer, Pudelko, and Harzing surveyed employees across 15 multinational teams and found that perceived language proficiency systematically inflated trust attributions, with the imputed competence regularly turning out to be misplaced ([*The impact of language barriers on trust formation in multinational teams*, Journal of International Business Studies, 2014](https://doi.org/10.1057/jibs.2013.64){rel=""nofollow""}). The mechanism in the room: - The speaker emits a sentence whose grammar is correct and whose meaning is *off by 15%.* - Listeners hear the fluency, not the 15%. - Nobody asks the clarifying question, because the sentence "sounded fine." - The 15% gap is written into the minutes as agreed. A confidently wrong sentence is more dangerous than an obvious gap, because **the gap earns a follow-up question; the false clarity gets minuted.** This is *false precision* — the load-bearing cost of operating in shared imperfect English. --- ## Failure mode 2 — Self-censorship of nuance The person most likely to know the answer is often the person least equipped to express it in the working language. Volk, Köhler, and Pudelko reviewed the cognitive-neuroscience literature on L2 processing in multinational corporations and reported measurable additional load on working memory, processing speed, and emotional regulation when professionals operate in a non-native language ([*Brain drain: The cognitive neuroscience of foreign language processing in multinational corporations*, Journal of International Business Studies, 2014](https://doi.org/10.1057/jibs.2014.26){rel=""nofollow""}). The first thing to disappear under that load is *nuance* — the qualifiers, hedges, conditional clauses, and counter-arguments that a native speaker deploys without thinking. The observable consequence is documented in the international-business literature: senior subject-matter experts who would dominate a meeting in their native tongue become the **quietest people in the room** when forced to operate in English ([Tsedal Neeley, *Global Business Speaks English*, Harvard Business Review, 2012](https://hbr.org/2012/05/global-business-speaks-english){rel=""nofollow""}; Neeley, *[The Language of Global Success](https://press.princeton.edu/books/hardcover/9780691175379/the-language-of-global-success){rel=""nofollow""}*, Princeton University Press, 2017). They are not silent because they have nothing to add. They are silent because the cost of expressing their actual view in English — finding the right verb tense, hedging without sounding evasive, qualifying without sounding weak — exceeds the cost of staying quiet. The decision is then made by whoever *can* express themselves fluently. Who are not, in general, the people who know most. Hinds, Neeley, and Cramton called this *language as a lightning rod*: language proficiency becomes a proxy for status, and status determines who speaks ([*Language as a lightning rod*, Journal of International Business Studies, 2014](https://doi.org/10.1057/jibs.2013.62){rel=""nofollow""}). **The most knowledgeable person in the room becomes the least articulate.** --- ## Failure mode 3 — Fluency outranks authority In any negotiation conducted in shared English, the native-English side holds an advantage *before any substance is exchanged.* The non-native side spends part of its cognitive budget on language production; the native side spends all of it on substance. This is a measurable processing asymmetry, not a personality effect. The neuroscience review cited above reports working-memory penalties of roughly 20–30% on equivalent tasks when the same person operates in L2 versus L1. Translated into a live negotiation: the non-native side is running on perhaps 70% of its cognitive budget while the native side runs on all of it. The visible consequence is not that the non-native side speaks *less*. The consequence is that the non-native side **agrees more.** Hedges drop. "I think we could probably consider" collapses into "OK." The native side gets the wording it wanted; the non-native side feels it got *most* of what it wanted; the gap only surfaces in the contract review weeks later. This is the part of the language tax that is hardest to see in the moment and most expensive to fix afterwards. --- ## The strongest evidence: where "good-enough" English literally kills The three failure modes above are well-attested in research literatures, but skeptical readers can dismiss them as soft-science findings about feelings. The strongest evidence for the thesis comes from the two domains where second-language English has been measured against a hard outcome — and where regulators have already acted on what the data shows. ### Aviation — when ICAO regulated the problem **Tenerife, 27 March 1977.** A KLM 747 and a Pan Am 747 collided on the runway at Los Rodeos. 583 people died — still the worst accident in aviation history. The investigation identified several contributing causes, including a non-standard radio exchange. KLM Captain Van Zanten, operating in second-language English under heavy time pressure, told the tower *"we are now, uh, at takeoff."* The tower acknowledged with *"OK."* Van Zanten's phrasing was ambiguous between *"we are in the takeoff position"* and *"we are in the process of taking off"*; the Pan Am crew, also second-language English speakers, were still on the runway. Subsequent reforms by ICAO and national authorities introduced standardized phraseology specifically to remove this class of ambiguity ([Spanish Aviation Authority final report; SKYbrary case study](https://skybrary.aero/accidents-and-incidents/b742-b741-tenerife-airport-spain-1977){rel=""nofollow""}). **Avianca 052, 25 January 1990.** A Boeing 707 ran out of fuel and crashed near Cove Neck, New York, killing 73. The flight crew, operating in second-language English with New York ATC, reported being *"running out of fuel"* — a phrase that does not exist in ICAO standard phraseology and that ATC did not interpret as a declared emergency. The standard term *"fuel emergency"* or *"minimum fuel"* was never used. The NTSB's final report identified the failure of the flight crew to use standard phraseology among the probable causes ([NTSB Aircraft Accident Report AAR-91/04](https://www.ntsb.gov/investigations/AccidentReports/Reports/AAR9104.pdf){rel=""nofollow""}). **The regulatory response.** In 2003, ICAO adopted **Language Proficiency Requirements (LPRs)** — Annex 1 (Personnel Licensing) and Annex 10 (Aeronautical Telecommunications) — making demonstrated English proficiency a licensing requirement for international flight crew and air traffic controllers worldwide. A six-level rating scale was defined; **Level 4 ("Operational") is the minimum** for international operations. Below Level 4, the licence is not valid for international flight. The implementation deadline was March 2008 ([ICAO Doc 9835, *Manual on the Implementation of ICAO Language Proficiency Requirements*](https://store.icao.int/en/manual-on-the-implementation-of-icao-language-proficiency-requirements-doc-9835){rel=""nofollow""}). The regulator's reasoning here is the thesis of this post, written into binding international law: *non-native English at "good-enough" level is unsafe in high-stakes communication; either everyone speaks the language at a defined operational standard, or they don't get to fly the airplane.* ### Medicine — when the comparison is measurable The other domain with a hard outcome is medical interpretation, and here the comparison is even cleaner: same clinical encounter, same patient, *with* versus *without* a trained interpreter. Glenn Flores and colleagues audio-recorded 57 emergency-department encounters with Spanish-speaking limited-English-proficient patients in two pediatric EDs and counted every interpretation error and its potential clinical consequence ([Flores et al., *Errors of medical interpretation and their potential clinical consequences: a comparison of professional versus ad hoc versus no interpreters*, Annals of Emergency Medicine, 2012](https://doi.org/10.1016/j.annemergmed.2012.01.025){rel=""nofollow""}). Headline findings: - **1,884 interpretation errors** identified across the 57 encounters. - **18% of all errors had potential clinical consequences.** - The clinically consequential error rate dropped to **12%** when a **professional interpreter with ≥100 hours of training** was used. - The rate was **22%** with **professional interpreters with <100 hours of training**, **20%** with **ad hoc interpreters** (family members, untrained bilingual staff), and **20%** with **no interpreter at all**. Two things to read out of this. First: ad-hoc interpretation by a fluent-sounding bilingual person who is not a trained interpreter performs **no better than no interpreter at all** on clinical-consequence rates. The fluency does not translate into accuracy on the parts that matter. Second: the protective effect only kicks in once interpretation crosses a *defined training threshold* — exactly the same regulatory pattern as ICAO Level 4. "Good enough" is not a category that exists in this data. Either you cross the threshold or you don't. Earlier work by the same author had already shown the same pattern in primary care ([Flores et al., *Errors in medical interpretation and their potential clinical consequences in pediatric encounters*, Pediatrics, 2003](https://doi.org/10.1542/peds.111.1.6){rel=""nofollow""}). The 2012 study quantified it against a defined competency standard. ### Why this matters in the boardroom The boardroom is not the cockpit and it is not the ED. The stakes per minute are lower; the consequences arrive in months, not seconds; the cost is in dollars and reputation rather than lives. But the *mechanism* is identical. A non-native speaker operating in a shared imperfect language emits fluent-sounding utterances whose semantic content has shifted; listeners receive the fluency as a signal of accuracy; the gap is not detected at the moment of emission; the gap surfaces only when the artifact built on top of it (the procedure, the dispatch instruction, the contract clause) is executed against reality and turns out to mean something different than the room believed. Aviation and medicine matter for the boardroom because they are the two domains where the cost of running this mechanism was *quantified*, and a regulator agreed it was unacceptable. They are the natural experiment for the thesis. --- ## The cost in business — where there is data Business doesn't have a Tenerife or a Flores study with the same scientific cleanliness. What it has is survey data — self-reported, mixed-mechanism, but at scale. **The Economist Intelligence Unit, 2012.** A survey of more than 500 senior executives across 51 countries — *Competing across borders: How cultural and communication barriers affect business.* Among the findings: - **49% of respondents reported that misunderstandings have stood in the way of major international transactions, incurring significant losses for their company.** - **64% reported that differences in language and culture make it difficult to gain a foothold in unfamiliar markets.** - **67% reported that miscommunication is interfering with their international business efforts.** Where that cost sits inside an export deal, stage by stage, with the prices the export desk pays for the partner's language today, is in [*English gets the first contact. The deal runs in the partner's language*](https://intermind.com/blog/english-gets-the-first-contact). The report does not split "language miscommunication" from "cultural miscommunication" cleanly, but for the half of respondents reporting *failed major transactions*, the cost line is real even if the mechanism inside is mixed. The business literature lacks the controlled "with vs without interpreter" comparison that medicine has, and the regulatory backstop that aviation has — but the underlying mechanism is the one the cleaner literatures have already pinned down. --- ## "But doesn't operating in L2 make people better decision-makers?" The strongest published counterargument to this post's thesis is the **Foreign-Language Effect**, demonstrated by Keysar, Hayakawa, and An at the University of Chicago ([*The Foreign-Language Effect: Thinking in a Foreign Tongue Reduces Decision Biases*, Psychological Science, 2012](https://doi.org/10.1177/0956797611432178){rel=""nofollow""}). Their experiments showed that when people considered classic decision-theory problems — framing effects, loss aversion, the Asian disease problem — *in their second language*, they exhibited **less** of the standard cognitive bias than when considering the same problems in their L1. Subsequent work has replicated the effect across multiple language pairs and decision-bias paradigms (see also Costa et al., *Cognition*, 2014). This is a real finding. So why doesn't it refute the thesis? Three reasons: 1. **The Foreign-Language Effect is about individual reasoning, not multi-party communication.** Keysar et al. measured what happens when one person decides a problem alone in their head, in their L2, with no listener and no communication partner. The three failure modes in this post are all properties of *interaction* — false precision and self-censorship and the fluency-authority gradient only exist because there is more than one person in the room. The Foreign-Language Effect doesn't enter that domain at all. 2. **The effect operates on emotional/heuristic biases, not on semantic accuracy.** The mechanism is that L2 creates emotional distance from the framing of the problem, so the listener falls back on more analytical (System 2) processing. Useful for reducing loss aversion. Not useful for *transmitting* a contract clause without semantic drift, which is what the boardroom is doing. 3. **Aviation and medical regulators have already weighed both effects against each other.** ICAO and the medical-interpretation literature both know the L2 reasoning literature exists. Neither field decided that the bias-reduction benefit was worth the false-precision cost. Both went the other way: define a proficiency standard, enforce it, and require interpreters or standardized phraseology for everyone below the standard. The honest summary: operating in L2 makes *you* — alone, in your head — slightly more rational on certain framing tasks. It makes *the room* you are in less able to transmit information accurately. The Foreign-Language Effect is a property of individual cognition; the three failure modes above are properties of multi-party communication. They don't cancel. --- ## Why "good-enough" machine translation does not fix any of it A generic machine-translation layer slotted on top of an English meeting addresses none of the three failure modes, and in some configurations makes them worse: - **False precision compounds.** A good-enough MT layer also emits fluent-sounding output, now layered on top of fluent-sounding non-native English. Two stacks of unverified fluency separate source intent from listener comprehension. - **Self-censorship persists.** If the working language of the meeting is still English and translation only serves the *listeners*, the speakers still pay the L2 cost. They still drop the nuance. The translation pipeline preserves the loss faithfully. - **The fluency–authority gradient flips, but does not flatten.** A poorly tuned translation layer just moves the advantage to whoever has the best engine in their corner, not to whoever knows most. The fix is not "add translation on top of an English meeting." The fix is to remove the requirement that *any* participant operate in a language they do not fully own. That is a different architectural choice — and the one we're building toward. --- ## What changes when every participant speaks their native language The structural change is simple to state and hard to engineer: 1. **Every participant speaks their own native language** — no L2 cognitive load, no nuance drop, no self-censorship. 2. **Every participant hears every other participant in their own native language**, live, with tone preserved. 3. **The translation layer is auditable**: source utterance, target utterance, per-language transcripts exported as a single bundle, with per-pair quality measured and [published monthly on real traffic](https://intermind.com/benchmark) rather than asserted as a marketing number. All three failure modes are linked to the *same* requirement — that someone in the room operate in a shared imperfect language. Removing that requirement removes them together. Adding translation on top of that requirement does not. That is the difference the next class of cross-border meeting tooling is going to have to be measured against. Aviation regulators didn't accept "everyone speaks pretty good English" as the answer. Medical regulators didn't either. The boardroom should not be the last domain that does. --- ## A reading list The load-bearing sources for this post, in roughly the order they were used: **On the cognitive and social mechanism** - Lev-Ari, S., & Keysar, B. (2010). [*Why don't we believe non-native speakers?*](https://doi.org/10.1016/j.jesp.2010.05.025){rel=""nofollow""} Journal of Experimental Social Psychology, 46(6), 1093–1096. - Tenzer, H., Pudelko, M., & Harzing, A.-W. (2014). [*The impact of language barriers on trust formation in multinational teams.*](https://doi.org/10.1057/jibs.2013.64){rel=""nofollow""} Journal of International Business Studies, 45(5), 508–535. - Hinds, P. J., Neeley, T. B., & Cramton, C. D. (2014). [*Language as a lightning rod: Power contests, emotion regulation, and subgroup dynamics in global teams.*](https://doi.org/10.1057/jibs.2013.62){rel=""nofollow""} Journal of International Business Studies, 45(5), 536–561. - Volk, S., Köhler, T., & Pudelko, M. (2014). [*Brain drain: The cognitive neuroscience of foreign language processing in multinational corporations.*](https://doi.org/10.1057/jibs.2014.26){rel=""nofollow""} Journal of International Business Studies, 45(7), 862–885. - Neeley, T. (2012). [*Global Business Speaks English.*](https://hbr.org/2012/05/global-business-speaks-english){rel=""nofollow""} Harvard Business Review. - Neeley, T. (2017). [*The Language of Global Success.*](https://press.princeton.edu/books/hardcover/9780691175379/the-language-of-global-success){rel=""nofollow""} Princeton University Press. - Keysar, B., Hayakawa, S. L., & An, S. G. (2012). [*The Foreign-Language Effect: Thinking in a Foreign Tongue Reduces Decision Biases.*](https://doi.org/10.1177/0956797611432178){rel=""nofollow""} Psychological Science, 23(6), 661–668. **Aviation** - ICAO. [*Manual on the Implementation of ICAO Language Proficiency Requirements (Doc 9835).*](https://store.icao.int/en/manual-on-the-implementation-of-icao-language-proficiency-requirements-doc-9835){rel=""nofollow""} International Civil Aviation Organization. - NTSB. [*Avianca, The Airline of Colombia, Boeing 707-321B, HK 2016, Fuel Exhaustion, Cove Neck, New York, January 25, 1990 (AAR-91/04).*](https://www.ntsb.gov/investigations/AccidentReports/Reports/AAR9104.pdf){rel=""nofollow""} - SKYbrary. [*Tenerife airport disaster, 1977 — accident case study.*](https://skybrary.aero/accidents-and-incidents/b742-b741-tenerife-airport-spain-1977){rel=""nofollow""} **Medicine** - Flores, G., Abreu, M., Barone, C. P., Bachur, R., & Lin, H. (2012). [*Errors of medical interpretation and their potential clinical consequences: a comparison of professional versus ad hoc versus no interpreters.*](https://doi.org/10.1016/j.annemergmed.2012.01.025){rel=""nofollow""} Annals of Emergency Medicine, 60(5), 545–553. - Flores, G., et al. (2003). [*Errors in medical interpretation and their potential clinical consequences in pediatric encounters.*](https://doi.org/10.1542/peds.111.1.6){rel=""nofollow""} Pediatrics, 111(1), 6–14. **Business** - Economist Intelligence Unit. (2012). *Competing across borders: How cultural and communication barriers affect business.* Sponsored by EF Education First. **Population** - Crystal, D. (2003). *English as a Global Language* (2nd ed.). Cambridge University Press. - EF Education First. [*English Proficiency Index*](https://www.ef.com/wwen/epi/){rel=""nofollow""} (annual). — The Mind.com Team **Aviation said it in 2008. Medicine has been counting it for twenty years. The boardroom is the last room still pretending that "good enough" is good enough.** # The 9 best Fireflies.ai alternatives in 2026 (tested for multilingual meetings) - **Most do the same job as Fireflies.** Otter, Fathom, tl;dv, Notta, MeetGeek, Read AI, Krisp and the suite notetakers record now and let you read later. - **A notetaker solves recall, not comprehension.** Fireflies transcribes in 100+ languages but does not translate the live meeting; in a multilingual room it records the problem. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes and documents translated while it happens, the summary last. Guests join free by link, no account; you pay only for active members. Fireflies.ai is a good product at the thing it was built for: it joins your call, transcribes it in 100+ languages, and hands you a searchable summary afterward. If you're reading this, something about it isn't fitting — the per-seat price at team scale, the storage caps on the lower plans, the bot in every meeting, or a need it simply wasn't built for. This guide compares the 9 alternatives people actually shortlist in 2026, with verified pricing and limits. Full disclosure up front: **we build one of them** ([InterMIND](https://intermind.com){rel=""nofollow""}), and it's the right choice only for a specific case — meetings that happen in more than one language. For everything else, we'll tell you honestly which competitor to pick. Every card links to the vendor's pricing; numbers below were checked in July 2026 and can drift. > Want the deeper 1-on-1 comparisons? See [InterMIND vs Fireflies](https://intermind.com/compare/fireflies) and [InterMIND vs Otter](https://intermind.com/compare/otter), the head-to-head [Otter vs Fireflies](https://intermind.com/blog/otter-vs-fireflies), or the category-level [buyer's guide to AI meeting translation tools](https://intermind.com/blog/best-ai-conference-translation-tools). Leaving Otter instead? [The 9 best Otter.ai alternatives](https://intermind.com/blog/otter-ai-alternatives). --- ## The verdict table | Tool | Best for | Free plan | Paid from\* | Languages | | ---------------------------------------------------- | --------------------------------------------- | ------------------- | ------------------------------- | ------------------ | | [InterMIND](https://intermind.com/#tool-1) | Meetings in 2+ languages, translated live | Yes (Basic) | per active member, 14-day trial | 23 voice / 30 docs | | [Otter.ai](https://intermind.com/#tool-2) | English-first teams who live in transcripts | 300 min/mo | \~$8.33/user/mo | 6 | | [Fathom](https://intermind.com/#tool-3) | Individuals who want free unlimited recording | Unlimited recording | \~$16/mo | 38 | | [tl;dv](https://intermind.com/#tool-4) | Sales teams that clip and coach | Unlimited recording | \~$18/seat/mo | 30+ | | [Notta](https://intermind.com/#tool-5) | Asian-language and translated transcripts | 120 min/mo | \~$9/mo | 58 | | [MeetGeek](https://intermind.com/#tool-6) | Auto-capture across a whole team | 3 h/mo | $9.99/user/mo | 100+ | | [Read AI](https://intermind.com/#tool-7) | Engagement metrics + notes | 5 meetings/mo | $15/user/mo | 16+ | | [Krisp](https://intermind.com/#tool-8) | Noisy environments, call centers | Trial | \~$8/user/mo | 16+ | | [Built-in notetakers](https://intermind.com/#tool-9) | Teams already paying for a suite | Included | with suite plan | varies | \*Lowest advertised per-user price on annual billing, July 2026. Month-to-month is typically 1.5–2× higher. --- ## How to choose in 30 seconds - **Your meetings are English-only and you want a record** → [Otter](https://intermind.com/#tool-2) if you live in transcripts, [Fathom](https://intermind.com/#tool-3) if you want free and unlimited. Don't overthink it. - **You transcribe a lot of non-English audio** → [Notta](https://intermind.com/#tool-5) (58 languages, translated transcripts) or [MeetGeek](https://intermind.com/#tool-6) (100+). - **Your meetings happen in more than one language at once** — two or three languages in one room → a notetaker records the problem; it doesn't fix it. You need live translation: that's [InterMIND](https://intermind.com/#tool-1). - **You're mostly annoyed by the price** → your platform's [built-in notetaker](https://intermind.com/#tool-9) may already be good enough. --- ## The 9 best Fireflies.ai alternatives []{#tool-1} ### 1. InterMIND — when the meeting itself isn't in one language Every other tool on this list does the same job as Fireflies: record now, read later. InterMIND does a different job — it translates the meeting **while it's happening**. Each participant picks a language when they join, and from then on they *hear* every speaker in it (in the speaker's own voice, as it is said), and *read* the chat, the shared notes, and dropped-in documents in it too. The AI summary at the end is just the last surface, not the product. - **Price:** free Basic plan; Pro and Business are billed per active member (each renewal counts the members active in the previous 28 days), with a 14-day trial; see [pricing](https://intermind.com/pricing). - **Languages:** 23 for live voice, chat, and notes; 30 for document translation. [The honest per-surface breakdown.](https://intermind.com/blog/how-many-languages-do-you-support) - **Limits:** plans meter voice minutes and chat words on a rolling 30-day window, shared across the team. - **Best for:** recurring meetings where the room doesn't share a fluent common language — international teams, cross-border sales, distributed standups. - **Honest caveat:** if every meeting you run is in one language, InterMIND is the wrong tool — a notetaker below is cheaper and built for exactly that. Two things you can check rather than take on faith: translation quality is [published monthly per language pair](https://intermind.com/benchmark), not marketed as a language count, and [the live demo](https://intermind.com/demo) plays the production pipeline on a real meeting, live — no signup needed. []{#tool-2} ### 2. Otter.ai — the default English notetaker The most-searched Fireflies alternative: transcription in six languages, live collaboration on the transcript, OtterPilot for auto-joining. The trade Fireflies users notice first: Otter caps *transcription minutes* (Fireflies caps storage instead), and its language list is short. - **Price:** free 300 min/mo (30 min per conversation); Pro $8.33/user/mo billed annually ($16.99 monthly), 1,200 min/mo; Business $19.99/user/mo annually ($30 monthly), unlimited meetings up to 4 h each. - **Languages:** 6 — English, Spanish, French, German, Japanese, Chinese. - **Best for:** English-heavy teams who want the transcript to be the workspace. - **Vs Fireflies:** better live-transcript UX; far fewer languages (6 vs 100+) and metered minutes. []{#tool-3} ### 3. Fathom — the best free recorder Fathom's free plan is genuinely unlimited — recordings, transcription, and instant summaries at no cost, which makes it the easiest "just leave Fireflies" move for individuals. In September 2026, the AI email client Superhuman acquired Fathom. Per TechCrunch, the free plan had already driven Fathom past 400,000 monthly active users, with more than 1 million people having used it to record a meeting. - **Price:** free unlimited recording + transcription; Premium $16/mo billed annually ($20 monthly); Team $15 and Business $25/user/mo annually (2-user minimum). - **Languages:** 38 for transcription. - **Best for:** individuals and small teams who want a free, low-friction recorder. - **Vs Fireflies:** more generous free tier; lighter on team knowledge-base features. []{#tool-4} ### 4. tl;dv — sales teams on a budget tl;dv records and transcribes free without limits, then charges for the AI layer (summaries, multi-meeting reports, CRM sync, coaching). Its 2026 positioning is squarely sales-team enablement. - **Price:** free plan with unlimited recording/transcription but tightly limited AI summaries; Pro ~~$18/seat/mo billed annually (~~$29 monthly); Business \~$59/seat/mo annually. - **Languages:** 30+ for transcription. - **Best for:** sales teams that clip calls and coach reps without paying Gong prices. - **Vs Fireflies:** cheaper way to record everything; the useful AI features sit behind Pro. []{#tool-5} ### 5. Notta — the multilingual transcriber Notta's pitch is the transcript in another language: 58 transcription languages, translated transcripts on paid plans, and bilingual/real-time translation views as add-ons. If your problem is "my recordings aren't in English," Notta is the notetaker to shortlist. - **Price:** free 120 min/mo (short per-recording cap); Pro from \~$9/mo billed annually ($13.99 monthly), 1,800 min/mo; Business \~$16.67/seat/mo annually. Real-time translation is a paid add-on (from \~$6/mo). - **Languages:** 58 for transcription; transcript translation on paid plans. - **Best for:** individuals working across Asian and European languages who need the *record* translated. - **Vs Fireflies:** better translation of the transcript; still after-the-fact — the meeting itself stays untranslated. []{#tool-6} ### 6. MeetGeek — set-and-forget auto-capture MeetGeek auto-joins everything on the calendar and quietly builds a searchable meeting library with summaries and workflow automations — the "capture the whole team by default" pick. - **Price:** free 3 h of transcription/mo; Pro $9.99/user/mo, 20 h/mo; Business $17/user/mo, unlimited. - **Languages:** 100+ with automatic language detection. - **Best for:** managers who want every team call captured and summarized without anyone pressing record. - **Vs Fireflies:** similar breadth at a slightly lower entry price; smaller ecosystem of integrations. []{#tool-7} ### 7. Read AI — meeting analytics on top of notes Read AI layers engagement and sentiment metrics on top of transcripts and summaries — who talked, who tuned out, how the meeting *went*, plus reports that chase you into email and Slack. - **Price:** free 5 meeting transcripts/mo (1 h cap); Pro $15/user/mo billed annually ($19.75 monthly); Enterprise $22.50, Enterprise+ $29.75/user/mo annually. - **Languages:** 16+ for meeting reports. - **Best for:** leaders who want meeting-culture metrics, not just minutes. - **Vs Fireflies:** adds analytics Fireflies doesn't have; costs more per seat and covers fewer languages. []{#tool-8} ### 8. Krisp — notes plus noise cancellation Krisp started as the noise-cancellation app and grew an AI notetaker on top. Because it processes audio on-device, it works across *any* calling app without a bot joining — and the transcript quality benefits from the cleaned-up audio. - **Price:** Core \~$8/user/mo billed annually ($16 monthly) with unlimited AI notes; Advanced \~$15/user/mo annually; free 7-day trial. - **Languages:** 16+ for transcripts and summaries. - **Best for:** noisy environments, call centers, and the bot-averse. - **Vs Fireflies:** no meeting bot — noise removal runs on-device before the notetaker; lighter on search and knowledge-base features. []{#tool-9} ### 9. The built-in notetakers (Zoom, Teams, Meet) Before paying any third party, check what your suite already includes: Zoom AI Companion, Copilot in Teams, and Gemini in Meet all summarize meetings on their paid tiers now, and each platform has some level of translated captions. We've written up exactly how far each one goes and where it stops: [Zoom](https://intermind.com/blog/zoom-live-translation), [Teams](https://intermind.com/blog/teams-live-translation), [Google Meet](https://intermind.com/blog/google-meet-live-translation). - **Price:** bundled with the suite plan you may already pay for. - **Best for:** teams that live inside one platform and need "good enough" notes. - **Vs Fireflies:** free-ish and zero-setup; weaker cross-meeting search, and captions ≠ translation of the actual conversation. --- ## The question none of these lists ask Every comparison above — ours included — can be reduced to price × languages × limits. But there's a split that matters more, and it's the reason this guide exists: **A notetaker solves recall. It does not solve comprehension.** If your meetings happen in one language, recall is the whole job, and you should pick from cards 2–9 with confidence. But if the room speaks more than one language, a better transcript is a record of a meeting that already failed. The people who couldn't follow the discussion live won't be rescued by a summary of it — [translated after the fact, quality unverified](https://intermind.com/blog/why-translation-quality-marketing-is-broken). That's the case InterMIND was built for, and it's why it looks odd on this list: it's not a better notetaker, it's [live, per-participant translation](https://intermind.com/blog/real-time-meeting-translation) of the voice, chat, notes, and documents — with the notes as a by-product. If that's your actual problem, no notetaker on this page solves it. --- ## FAQ **Is there a completely free Fireflies alternative?** Fathom is the most generous: unlimited free recording, transcription, and basic summaries. tl;dv also records and transcribes free but tightly limits AI summaries. Fireflies' own free plan transcribes without limits but caps *storage* at 400 min per team. **What's the best Fireflies alternative for non-English meetings?** For transcribing recordings in other languages: Notta (58 languages) or MeetGeek (100+). For meetings that *happen* in several languages at once and need live translation rather than an after-the-fact transcript: [InterMIND](https://intermind.com/compare/fireflies). **Does Fireflies.ai translate meetings?** No. Fireflies transcribes in 100+ languages and can detect the language automatically, but it doesn't translate the live meeting — participants still need a common language during the call. **Otter or Fireflies — which is better?** Otter has the better live-transcript workspace; Fireflies covers far more languages (100+ vs 6) and prices storage instead of minutes. English-only and transcript-centric: Otter. Multi-language recordings or unlimited transcription: Fireflies. We wrote the full head-to-head: [Otter vs Fireflies](https://intermind.com/blog/otter-vs-fireflies). **Do I even need a third-party notetaker?** Maybe not — Zoom, Teams, and Meet all bundle AI summaries on paid tiers now. Third-party tools still win on cross-meeting search, CRM sync, and working across platforms. --- ## Try the part that's hard to fake If language — not note-taking — is your real bottleneck, the only test that matters is your own language pair: - **[Run the live demo](https://intermind.com/demo)** — InterMIND's production pipeline translating a real meeting live, in any of 23 languages — no signup needed. - **[Read the benchmark](https://intermind.com/benchmark)** — monthly per-pair quality scores, full distribution, no cherry-picking. - **[InterMIND vs Fireflies, feature by feature](https://intermind.com/compare/fireflies)** — the detailed 1-on-1. — The Mind.com Team --- *Sources: vendor pricing pages ([Otter.ai](https://otter.ai/pricing){rel=""nofollow""}, [Fireflies.ai](https://fireflies.ai/pricing){rel=""nofollow""}, [Fathom](https://fathom.ai/pricing){rel=""nofollow""}, [tl;dv](https://tldv.io/app/pricing/){rel=""nofollow""}, [Notta](https://www.notta.ai/en/pricing){rel=""nofollow""}, [MeetGeek](https://meetgeek.ai/pricing){rel=""nofollow""}, [Read AI](https://www.read.ai/pricing){rel=""nofollow""}, [Krisp](https://krisp.ai/pricing/){rel=""nofollow""}), checked July 2026; [TechCrunch — Superhuman acquires Fathom](https://techcrunch.com/2026/09/14/superhuman-acquires-yc-backed-notetaker-fathom-as-productivity-platforms-push-for-agentic-work/){rel=""nofollow""}, checked September 2026. Prices are annual-billing rates unless noted and may change.* # Is InterMIND free for meeting participants? - **Yes, for every participant.** Joining, speaking, hearing and reading in your own language cost nothing; only the host's team holds a plan, and Basic is free. - **The account changes what you keep.** Members keep the recap and history; a guest leaves with nothing unless they keep the session or the host adds them. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, documents and the recap, priced like a room, not a seat. Guests join free by link, no account; you pay only for active members. Short answer: **yes — for every participant**. If someone invites you to an InterMIND meeting, everything on your side is free: joining, speaking and reading in your own language, receiving translated documents — and, with a free account, the recap afterwards. Whether you have an InterMIND account or not changes *what you can keep after the call* — it never changes the price, which for a participant is zero either way. This page exists because "free" on a landing page is usually followed by an asterisk. Here is the whole asterisk, spelled out. ## The model: one plan per room, not one plan per person InterMIND is priced like a room, not like a seat at the table. **The host's team has a plan. Everyone the host invites just joins.** That split is structural, not promotional: - **The host is the only person with a billing relationship** — and only on paid plans. A host on the free Basic plan pays nothing either; paid plans exist for teams that need more than Basic's limits. - **Participants draw on the host's plan.** When a participant reads chat in their own language or receives a translated document, that usage counts against the host's plan limits — never against the participant. - **Participants have no billing surface at all.** There is no paywall, no upgrade prompt, and no card form on the participant's path — with an account or without one. If you have ever set up a multilingual call on a per-seat product, this is the difference to notice: you don't need every participant licensed or provisioned. You need one plan — the host's. Inside the host's own team the seat is going away too: paid plans move to per-active-member billing, where each renewal counts only the members who were active in the previous 28 days — see [Pay only for the people who use it](https://intermind.com/blog/pay-only-for-active-members). ## What every participant gets, free Any participant in an InterMIND meeting — invited by link, at no cost: - **hears and reads the meeting in their own language** — live, whatever language each other participant is speaking or typing; - **speaks and writes in their own language**, and every other participant gets it in theirs; - **receives shared documents translated** into their language, when the host's plan includes document translation. You pick a language once, at the door. Nothing else to configure, nothing to pay. ## With an account or without one — what actually differs You can join a meeting without signing up at all: click the link, enter a name, pick a language. InterMIND calls that joining **as a guest**, and it exists so that a first-time invitee is never blocked at the door. To be precise about what it is: a guest is simply a participant who isn't signed in — nothing more. The difference shows up **after** the call, because everything InterMIND produces from a meeting needs somewhere to be delivered: - **Signed-in participants** get the recap in their own language, the links to the recording and meeting artifacts, and the meeting's chat history in the channel — readable in their language, for as long as the channel lives. - **Guests get none of that on their own.** A guest identity is temporary by design — it is deleted within about 24 hours (which is also a privacy feature: nothing about a guest is retained unless the guest asks the host, from the exit screen, to add them — that request, by name, stays with the meeting). There is no account to deliver a recap to, so the meeting ends and nothing follows. The recap, transcript and recording stay with the host's account and its members, and the chat of an ad-hoc call is wiped for everyone when the call ends, host included. When the call ends, the exit screen says plainly what this session leaves behind and offers two ways to keep it. **Keep this meeting** creates a free account — no card — and opens that one session's recap in your language once it is ready, a few minutes after the call; nothing else of the meeting. **Ask the host to add me** is one tap — nothing to type: the host sees your name on the recap page, and if they add you, an email invite follows to the address they have for you, and accepting it with a free account makes you a member of that meeting from then on: its next sessions and their recaps reach you in your language, and in a channel the chat and files too. Neither happens on its own — a guest who closes the screen keeps nothing. Guest mode is for joining a call by link, right now, with nothing to set up — what it doesn't give you is anything after the call. ## Where the limits actually live Every limit in InterMIND belongs to the host's plan — the full row-by-row breakdown is on the [pricing page](https://intermind.com/pricing), but the shape is: - **Basic (free plan):** free forever for the host too — multilingual meetings with chat translation capped at 10,000 words per rolling 30-day window; document translation not included. - **Paid plans:** lift the chat-translation cap and add document translation as a metered feature — counted in distinct files over a rolling 30-day window (10 on Pro, 30 on Business, 100 on Enterprise). None of these numbers are a participant's problem. They bound what the *room* can do; participants simply use whatever the room provides. ## Why we price it this way A multilingual meeting only works if **everyone** is in it. The moment the other side of the call has to pay or get provisioned, half of your invitees show up untranslated — and the meeting quietly falls back to whatever language dominates. Making participation free is not generosity; it is the only configuration in which the product does what it promises. ## Try it first - **[How to see who uses your translation minutes and storage](https://intermind.com/blog/how-to-see-who-uses-your-translation-minutes-and-storage)** — the meters, per host, and the email before the limit. - **[How to join a video meeting from your computer](https://intermind.com/blog/how-to-join-a-video-meeting-from-your-computer)** — the link, the pre-join screen, joining as a guest, your language. - **[Try the live demo](https://intermind.com/demo)** — join a real translated meeting from your browser, no signup needed. - **[See every limit side by side](https://intermind.com/pricing)** — the full plan comparison, row by row. ## FAQ **Do meeting participants need an InterMIND account?** Not to join — a link is enough. After the meeting, the recap, transcript and recording stay with the host's account and its members. A guest can keep that session from the exit screen with a free account, or ask the host to add them; without either, the meeting ends and nothing follows. **Who pays for the translation in a meeting?** The host's team plan covers the room. Participant usage — translated voice, chat, documents — draws on the host's plan limits. Participants themselves have no billing relationship with InterMIND at all, and a host on the free Basic plan pays nothing either. **Is there a free plan for hosts too?** Yes. The Basic plan is free and includes multilingual meetings with chat translation capped at 10,000 words per rolling 30-day window. Document translation starts on paid plans. The full breakdown is on the [pricing page](https://intermind.com/pricing). **What does a guest miss compared to a signed-in participant?** Inside the meeting — nothing: translation of voice, chat, and documents works the same. After the meeting — the recap, transcript, recording and the meeting's history, which stay with the host's account and its members; guest identities are deleted within about 24 hours. The exit screen offers to keep that one session with a free account, or to ask the host to add you. **Do participants need to install an app?** No — joining from a desktop or mobile browser works with just the link. Native mobile apps for iOS and Android exist for people who prefer them, but they are optional. **Can a participant be charged by accident?** No. There is no payment surface on the participant path — no card form, no upgrade prompt, no paywall. Billing exists only inside the host team's settings. # We finished our GDPR audit. Here's what we actually closed. - **Erasure, retention, export, EU runtime: all verified in code.** Deletion cascades through storage and Stripe, the retention criterion is in the Privacy Policy, every hop in the EU. - **No badge claimed.** GDPR is not a certificate and we hold no ISO certificate yet; the answers are architectural, verifiable, and published with the sub-processor list. - **InterMIND keeps the whole meeting in each member's language,** on an EU runtime with the AI gateway your organization chooses. Guests join free by link, no account; you pay only for active members. A few weeks ago we wrote that ["GDPR-compliant" on a video tool's homepage means less than you think](https://intermind.com/blog/gdpr-compliant-video-conferencing) — that GDPR is a set of obligations on *you*, the data controller, that a vendor either helps you meet or quietly leaves on your desk. The honest way to back that claim is to do the work on our own side and show it, line by line. So we did. We ran a full audit of the InterMIND codebase against the obligations that fall on us as a data processor, fixed every gap that had code behind it, and verified each one against the running product. This post is the close-out report — not a badge, a checklist with our answers. We're deliberately not claiming "100% GDPR-certified." GDPR isn't a certificate you pass — and we won't wave an ISO badge we don't yet hold. What we *can* say: the architectural and process obligations a DPO works through now have concrete, verifiable answers, each checked against the running code. --- ## What we closed ### Right to erasure (Art. 17) — the cascade actually runs Deleting your account doesn't just deactivate it. `POST /api/user/delete-account` runs a real cascade: it nukes your meetings → participants, messages, conferences, transcriptions; it sweeps your storage blobs out of Tigris **before** the database cascade so nothing is left orphaned — chat attachments *and* video-recording files, both columns; and it cancels your Stripe subscriptions and deletes the Stripe customer. On-demand deletion is there too — drop a channel or a message from the UI and it's gone. Anonymous (guest) accounts get their own deletion endpoint plus a background sweep every 6 hours, under a monitored cron. The audit surfaced one gap here — recording blobs that the database cascade dropped but storage kept — and we closed it: erasure now leaves nothing behind in object storage. ### Retention (Art. 5(1)(e)) — a documented criterion Art. 5(1)(e) doesn't require an automatic time-to-live. It requires a **defined retention criterion**. Ours is now written into the Privacy Policy: data is kept until you or your team owner delete it, and deleting your account erases everything. That's the same model collaboration tools like Slack and Notion run on — persistence is the expected behavior, and you stay in control of it. The criterion is stated, not implied. ### Analytics consent (Art. 6/7) — opt-out by default A Usercentrics consent banner (shown to EU visitors) gates analytics, and PostHog ships with `opt_out_capturing_by_default: true` — nothing is captured until consent is given, not the other way around. ### Data portability (Art. 20) — a real export `GET /api/user/export` builds a ZIP of your meetings, messages, recordings, and translations, with a 7-day download window and automatic cleanup. Access, deletion, and portability are tooling that works, not promises in a policy. ### Meeting content goes to one AI gateway, in the EU — chosen by the organization The single biggest flow of meeting content — live voice and chat translation — runs on **our own engine in France**, never a third-party LLM. The AI steps that *do* use a general-purpose model (the digest, document summaries, the note-editor's generative actions, Ask AI) run on **the AI gateway the organization selects** — Azure OpenAI in the EU Data Zone by default, Vertex AI EU or Amazon Bedrock Frankfurt by choice, each in our own tenant with zero data retention and no training on customer content, or the organization's own endpoint; one resolver in the code picks the gateway for every call site, so there is no second path. We also scrubbed participant names and utterance text out of the conference browser logs that PostHog session-recording could otherwise capture. The full vendor-by-vendor map is in [*Where one InterMIND meeting actually runs*](https://intermind.com/blog/where-one-intermind-meeting-actually-runs). ### Transparency — sub-processors and processing records, published The [sub-processor list](https://intermind.com/legal/subprocessors) is live, with what each vendor does and where it's domiciled — not "available on request." Behind it sits a Record of Processing Activities (ROPA) built from the live schema: 11 processing operations, the security measures on each, and the erasure / portability paths. Our [Privacy Policy](https://intermind.com/privacy) and [Terms](https://intermind.com/terms) now run under our own legal entity, with the real processing chain described. ### EU runtime — pinned, not promised Every runtime hop a meeting takes is in the EU: app and APIs on Vercel Frankfurt, the meeting server on Fly Paris, application data in Neon Postgres (AWS Frankfurt), errors on Sentry EU, analytics on PostHog EU, email via Resend Ireland. Object storage on Tigris is now **pinned to EU regions** (Frankfurt + Amsterdam) — every new write lands in the EU regardless of where the user is. The full architecture is on our [security page](https://intermind.com/docs/security). --- ## Why this matters for your procurement For most EU buyers — German Mittelstand, regulated teams running standard GDPR DPAs — the data-residency question now has a direct answer: the data doesn't leave the EU at runtime, erasure works, the retention criterion is stated, and the sub-processor list is on the table. That's a much shorter conversation than "let us get back to you on where the data goes." For French *souveraineté numérique* and SecNumCloud-grade procurement, vendor corporate domicile is itself a criterion — a deeper conversation about deployment topology that we'll have honestly rather than oversell. And the one thing we won't do is wave an ISO certificate we don't yet hold: certifications are on the roadmap, but our answer to the checklist is **architectural and verifiable today**. --- ## See it for yourself - [GDPR-compliant video conferencing: the full DPO checklist](https://intermind.com/blog/gdpr-compliant-video-conferencing) — the seven things to make any vendor answer, and where Zoom sits. - [Where one InterMIND meeting actually runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs) — the vendor map, with the gaps named. - [Is your meeting confidential?](https://intermind.com/blog/is-your-meeting-confidential) — the three questions to ask before the DPO checklist comes out. - [Security & Privacy](https://intermind.com/docs/security) · [Sub-processors](https://intermind.com/legal/subprocessors) · [Privacy Policy](https://intermind.com/privacy) · [Terms](https://intermind.com/terms) - **[Try the live demo](https://intermind.com/demo)** — hear the live, EU-runtime, multilingual pipeline on a real meeting — no signup needed. GDPR compliance isn't a badge you buy — it's work you do and can show. This is ours, line by line. If your DPO needs an answer this post doesn't give, write us. — The Mind.com Team --- *Sources: [Regulation (EU) 2016/679 (GDPR)](https://eur-lex.europa.eu/eli/reg/2016/679/oj){rel=""nofollow""} — the articles audited against; internal claims verified against the InterMIND codebase and running product; checked August 2026.* # GDPR-compliant video conferencing (2026): what it actually takes (and a Zoom alternative that translates) - **Seven verifiable things, not a badge.** A DPA, a sub-processor list, the runtime region, a transfer mechanism, audited security, rights tooling and retention you control. - **Zoom can be compliant when configured for it.** EU residency is an Enterprise and Education add-on, Zoom is US-domiciled, and the meeting still runs in one language. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, files and the recap, every runtime hop in the EU. Guests join free by link, no account; you pay only for active members. "GDPR-compliant" on a video platform's homepage is close to content-free. GDPR is not a certification you pass — it's a set of obligations on *you*, the data controller, that a vendor either helps you meet or quietly leaves on your desk. The useful question isn't "is this tool GDPR-compliant?" It's "**what does this tool make me responsible for, and where does my meeting data actually go?**" > **🔒 Update — we did this to ourselves.** Since this post went up, we ran InterMIND's own codebase through the full checklist below and closed every item — erasure, retention, EU runtime, sub-processors — verified against the code, not asserted on a page. **→ [Read the audit close-out, line by line](https://intermind.com/blog/gdpr-audit-what-we-closed).** This post is the plain-terms version of that question: the checklist a DPO actually works through, where Zoom sits on it (fairly — it's more compliant-capable than the internet implies), and where an EU-runtime alternative changes the answer. If you want the broader "how should real-time meetings work" frame, that's the [pillar guide](https://intermind.com/blog/real-time-meeting-translation); this one is specifically about the data-protection layer. --- ## The plain-terms checklist Strip the marketing and "GDPR-compliant video conferencing" comes down to seven things you can actually verify: 1. **A signed DPA.** A Data Processing Addendum that names the vendor as your processor, with documented purposes and instructions. No DPA, no lawful processing — full stop. 2. **A real sub-processor list.** Every third party that touches meeting data — transcription, storage, email, analytics, AI features — named, with what they do and where they're domiciled. 3. **Where data is processed at runtime.** The physical region your audio, transcripts, recordings, and metadata are handled in. This is what most data-residency clauses are actually about. 4. **The international-transfer mechanism.** If any data leaves the EEA, on what legal basis? Standard Contractual Clauses (SCCs), adequacy, or a residency setup that avoids the transfer entirely. This is the Schrems II question, and it doesn't go away because a homepage says "compliant." 5. **Security posture you can audit.** ISO 27001, ISO 27701, SOC 2 — independent attestations, not self-assertions. 6. **Data-subject rights tooling.** Can you actually fulfil access, deletion, and portability requests for meeting data, or only in theory? 7. **Retention and deletion you control.** Recordings, transcripts, and AI summaries deleted on your schedule, not the vendor's default. A tool is "GDPR-compliant" for your purposes only when all seven have concrete answers. Most homepages answer zero of them. --- ## Where Zoom actually stands (fairly) Zoom is more GDPR-capable than its reputation suggests, and it's worth being accurate about that rather than scoring cheap points: - It publishes a **global DPA with the 2021 EU Standard Contractual Clauses** built in. - It offers **EU Data Residency** — "Zoom EU Infrastructure" — for Enterprise and Education customers, covering Meetings, Webinar, Chat, Phone, and Contact Center. - It holds **ISO 27001 and, as of February 2026, ISO 27701** (the privacy-management extension), plus published EU public-sector sovereignty controls. So a properly configured Zoom deployment, on the right tier, can satisfy most of the checklist. The honest caveats are about defaults and domicile, not capability: - **EU residency is a tier-and-config add-on, not the default.** It's on Enterprise/Education and has to be turned on. The free and lower paid tiers don't get it. "We use Zoom" and "we use Zoom configured for EU residency" are different procurement facts. - **Zoom is a US-domiciled company.** Even with SCCs and EU residency, the *vendor's corporate domicile* is in scope for CLOUD-Act and sovereignty-grade evaluations. For standard GDPR this is manageable with SCCs; for French *souveraineté numérique* or SecNumCloud-grade procurement, corporate domicile is itself a criterion, and that's a harder conversation. - **The meeting still happens in one language.** Zoom's translated captions and AI Companion help, but the room doesn't become genuinely multilingual — every participant hearing the meeting live in their own language. If your compliance problem is also a *language* problem (cross-border audits, multi-site CAPA reviews), that gap is unsolved regardless of where the data lives. The short version: Zoom **can** be GDPR-compliant when configured for it. Whether that's *sufficient* depends on how sovereignty-sensitive your buyer is — and whether the meetings are multilingual. --- ## Where InterMIND sits on the checklist InterMIND is a space a host gives their team and their clients, each in their own language — meetings, chat, files, the recap. The checklist above is answered by default rather than by a configuration project; the part of it that's structural rather than promised is **where the meeting runs** — one line for the DPO, verified against the live deployment: - **Every runtime hop is in the EU.** App and server APIs on Vercel in Frankfurt (`fra1`); the meeting WebSocket server on Fly in Paris (`cdg`); application data in Neon Postgres on AWS Frankfurt (`eu-central-1`); recordings on Tigris, EU-pinnable; error/analytics on Sentry EU and PostHog EU; transactional email via Resend in Ireland. - **The translation engine is our own code, in France** (OVH) — not a US general-purpose model we resell. The single biggest flow of meeting content stays EU-resident and never touches a third-party LLM. Document translation goes to **DeepL in Cologne** — also an EU company. - **The sub-processor list with corporate-domicile detail ships with the DPA** as standard practice, not on request. **Meeting content goes to one AI gateway, in the EU, and the organization chooses it.** Everything derived from a meeting that needs a language model — the *post-meeting* AI digest (topics, decisions, action items), document summaries, the AI note-editor's generative actions (fix, extend, simplify), Ask AI — runs on the AI gateway your organization selects: Azure OpenAI in the EU Data Zone by default, Vertex AI on the EU multi-region endpoint or Amazon Bedrock in Frankfurt by choice, each in our own tenant with zero data retention and no training on customer content; or your own OpenAI-compatible endpoint. The post-meeting summary and the editor's *translate* action go through the translation tract, not the language model. The vendors behind the hosted gateways are US companies operating EU regions — stated plainly on the [trust page](https://intermind.com/trust), not hidden; corporate domicile is the criterion sovereignty-grade procurement adds on top of GDPR, and it applies to this hop exactly as it applies to Zoom above. The full vendor-by-vendor map is in [*Where one InterMIND meeting actually runs*](https://intermind.com/blog/where-one-intermind-meeting-actually-runs), and the build-vs-buy view is in [*What one InterMIND meeting is built from*](https://intermind.com/blog/what-one-intermind-meeting-is-built-from). One thing we **don't** claim: we are not going to wave an ISO certificate we don't yet hold. Our answer to the checklist is architectural — EU runtime, own engine, transparent sub-processors, a real DPA — and we'd rather you verify that than trust a badge. Certifications are on the roadmap; the runtime is real today. We ran our own codebase through this exact checklist and closed each item against the code — [the close-out report, line by line](https://intermind.com/blog/gdpr-audit-what-we-closed). And the part Zoom's residency settings can't add: the meeting is **multilingual by design** — every participant live in their own language across 23 languages, voice and chat and notes, with [translation quality published openly](https://intermind.com/benchmark) instead of asserted. How that works is in the [pillar guide](https://intermind.com/blog/real-time-meeting-translation); the regulated-meeting use case is in [*multilingual compliance meetings*](https://intermind.com/blog/multilingual-compliance-meetings). --- ## The checklist as a table The seven items against the two tools this post discusses in detail. Cells state only what each vendor documents (Zoom links in Sources below; InterMIND claims verified line-by-line in [the audit close-out](https://intermind.com/blog/gdpr-audit-what-we-closed) and [the runtime map](https://intermind.com/blog/where-one-intermind-meeting-actually-runs)) — for any other vendor, make them answer the left column in writing. | Checklist item | Zoom (documented) | InterMIND (documented) | | -------------------------------- | --------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | Signed DPA | Global DPA with 2021 EU SCCs | DPA; sub-processor list ships with it | | Sub-processor list | Published | Ships with the DPA, incl. corporate domicile per vendor | | Runtime region | EU Data Residency on Enterprise/Education, has to be enabled | EU at every hop by default: Frankfurt (app/API/DB), Paris (meeting server), own translation engine in France | | International-transfer mechanism | SCCs | Meeting data stays in the EEA — no transfer to paper over | | Auditable security posture | ISO 27001; ISO 27701 as of Feb 2026 | No ISO certificate yet — the answer is architectural and open to verification, certifications on the roadmap | | AI features and meeting content | Translated captions / AI Companion (see [our Zoom breakdown](https://intermind.com/blog/zoom-live-translation)) | AI features on the gateway the organization selects — Azure OpenAI EU Data Zone by default, Vertex AI EU or Bedrock Frankfurt, or its own endpoint — with zero data retention and no training; AI can be switched off for the organization | | Multilingual meeting | Captions translate text; the room stays one-language live | 23 languages live per participant: voice, chat, notes | --- ## FAQ **Is Zoom GDPR compliant?** It can be, on the right tier and configuration: Zoom publishes a global DPA with the 2021 EU SCCs, offers EU Data Residency for Enterprise and Education customers, and holds ISO 27001 and (since February 2026) ISO 27701. The honest caveats: EU residency is a tier-and-config add-on rather than the default, and Zoom remains a US-domiciled company — manageable under standard GDPR with SCCs, but a real criterion in sovereignty-grade procurement. **What makes a video conferencing tool GDPR compliant?** Seven verifiable things, not a homepage badge: a signed DPA, a real sub-processor list, a documented runtime region, a lawful international-transfer mechanism, independently audited security, working data-subject-rights tooling, and retention you control. A vendor is compliant *for your purposes* when all seven have concrete answers in writing. **Does GDPR require video meetings to stay in the EU?** No — GDPR requires a lawful transfer mechanism (SCCs, adequacy) when data leaves the EEA, not residency as such. Residency matters because it removes the transfer question entirely — the post-Schrems II analysis gets short when the data never leaves. That's the difference between "compliant with paperwork" and "nothing to paper over." **Which video conferencing tools run entirely in the EU?** Ask any vendor for their runtime map: region per hop — app, APIs, meeting media, database, recordings, analytics, email, AI features. InterMIND publishes exactly that ([every hop, vendor by vendor](https://intermind.com/blog/where-one-intermind-meeting-actually-runs)): Vercel Frankfurt, Fly Paris, Neon Frankfurt, translation engine on OVH France, AI features on the gateway the organization selects, in an EU region (Azure OpenAI EU Data Zone by default). Whatever tool you evaluate, the map — not the marketing page — is the answer. --- ## Which host this answers The owner or manager of an organization of 10–200 people whose team or clients speak another language, already on Teams or Workspace, setting up the room without an IT department. For that host the checklist is answered by default and the DPO conversation is short; the rest of the decision is whether the meeting itself runs in each member's language. Sovereignty-grade public procurement, where vendor domicile is itself part of the spec, is a different conversation, and we say so rather than oversell. --- ## Try it, then read the data map - **[Try the live demo](https://intermind.com/demo)** — hear the live, multilingual pipeline on a real meeting and hear what "EU-runtime *and* multilingual" actually feels like. No signup needed. - [InterMIND vs. Zoom](https://intermind.com/compare/zoom) — feature-by-feature, honestly. - [*Where one InterMIND meeting actually runs*](https://intermind.com/blog/where-one-intermind-meeting-actually-runs) — the full vendor map, gap included. "GDPR-compliant video conferencing" is a checklist, not a badge. Whichever tool you pick — ours or another — make the vendor answer all seven questions in writing. The ones that can are worth your time; the ones that can't are selling you a homepage. — The Mind.com Team --- *Sources on Zoom: [Zoom — GDPR](https://www.zoom.com/en/trust/gdpr/){rel=""nofollow""}, [Zoom — EU Data Residency / privacy in Europe](https://www.zoom.com/en/blog/zoom-privacy-europe/){rel=""nofollow""}, [Zoom — ISO 27701](https://www.zoom.com/en/trust/legal-compliance/iso-27701/){rel=""nofollow""}, checked August 2026. Vendor offerings and tiers change; verify the current configuration against Zoom's trust pages. InterMIND runtime facts are verified against the live deployment as described in the linked data-map post.* # Give every guest their language - **Translation belongs to the host, not the guest.** A good host provides what every guest needs before anyone asks; a feature one person switches on marks them. - **Everyone is smarter in their native language.** Speaking your own is a courtesy to the listener, who gets your actual reasoning; natives stop decoding second-language English. - **InterMIND keeps the whole space in each member's language,** voice, chat, documents and the recap, during the meeting and after it. Guests join free by link, no account; you pay only for active members. Think about what a good host does. They don't hand you a chair kit and an Allen key. They don't serve one dish and post the recipe for anyone who can't eat it. Whatever the guest needs to be fully present — a seat, a plate, a place at the table — the host provides it, for everyone, before anyone has to ask. Now look at how meetings handle language. The default meeting is furnished in exactly one language — usually the organizer's, or the corporate house language, which is to say English. Everyone else is welcome, of course. They're just expected to bring their own furniture: follow at speed, formulate replies under pressure, chase nuance in real time, and do it all silently, because the one thing worse than working in your second language is announcing that you're working in it. A meeting is precisely the room where professionals hide that effort hardest. The fix the industry keeps reaching for is personal equipment: an app *you* switch on, captions *you* enable, a feature marketed to the person who "needs help." That framing fails socially even when it works technically, because it asks one participant to raise a hand and mark themselves. Assistive tools with a public stigma get quietly declined — that's why the same function succeeds or fails depending on its symbolism. Nobody wants to be the person visibly compensating. There is an older, better model, and everyone already respects it: **the interpreter booth**. When the UN seats delegates, or any serious international body convenes, interpretation isn't an accessory some delegate switches on in shame. It's *infrastructure the host provides* — a mark of the occasion's seriousness and the host's respect. No delegate is "using assistance." The room simply speaks your language, because you were invited properly. ## Hosting is the fix That model — translation as something the **host provides for everyone**, not something a participant requests for themselves — is the entire idea behind InterMIND, and it changes three things at once. **It changes the social meaning.** When the room itself runs in every participant's language, using yours carries no signal. Nobody switched anything on; nobody is compensating. Language becomes like the lighting — provided, universal, unremarkable. And the norm it establishes is honest, because it applies to natives too: **everyone is smarter in their native language.** The English native who never has to spend cycles decoding accented, compressed second-language English gets sharper counterparts and loses nothing. Subtitles, after all, are watched mostly by people who hear fine. **It changes who benefits.** Here's the inversion that surprises people: speaking your own language is a *courtesy to the listener*. Formulate in the language you think in, and your counterpart — hearing you in theirs — receives your actual reasoning instead of the simplified version that survives translation-in-your-head. You speak generously; they lose nothing of what you meant. We've written about how much gets lost the other way: [the false fluency trap](https://intermind.com/blog/false-fluency-trap). **It changes the economics.** Hospitality means the guest never sees a bill. In InterMIND, the host's plan covers the room: [participants pay nothing and install nothing](https://intermind.com/blog/free-for-participants) — they click a link, pick their language once, and the meeting simply happens in it. Voice, [chat](https://intermind.com/features/multilingual-chat), notes, [documents](https://intermind.com/features/document-translation). One decision by one person furnishes the room for everyone. (That's also, practically, why this model spreads: you don't have to convince every participant — you have to be a good host once, and everyone at the table experiences it.) ## The hospitality extends past the meeting A dinner ends when the guests leave. A working relationship doesn't — and this is where hosting-in-your-language stops being a nicety and becomes structural. In InterMIND the meeting persists as a channel: the chat and its history readable in each member's language, the [recap](https://intermind.com/features/recap) delivered to every member in their own language after the call, the documents in the same space. Your guest wasn't accommodated for an hour; with a free account they become **a member who reads the record in their language for as long as the channel lives**. Next week's dispute, next month's onboarding, the decision someone cites in October — all of it exists in their language too, not just in the host's. We measured the industry against exactly this bar: [how much of a meeting still exists in your language a week later](https://intermind.com/blog/the-meeting-a-week-later). That's the difference between translating a *moment* and furnishing a *space*. Moments expire. A space you provided keeps being provided. ## What this asks of you Almost nothing — which is the point. Hosting multilingually isn't a program you roll out; it's one habit: 1. **Create the room and send the link.** Guests join from a browser, no account, free. 2. **Let people pick their language** — including you. Say what you actually think, in the language you think it in. 3. **Let the space do the follow-through.** Every signed-in member gets the recap in their language; the history stays readable in theirs. A guest gets the meeting itself — the record needs a free account. The counterpart who used to nod along now argues back. That's what you invited them for. ## Host one meeting this way - **[Try the live demo](https://intermind.com/demo)** — no signup; hear four perspectives of one room, each in its own language. - **[Start a meeting](https://intermind.com/chats)** — send one link, give every guest their language. - **[See the benchmark](https://intermind.com/benchmark)** — the translation quality you'd be offering your guests, measured monthly, per language pair, in public. --- ## FAQ **What does it mean to host a multilingual meeting?** It means the organizer provides translation for the whole room — the way venues provide chairs and conference hosts provide interpreters — instead of leaving each participant to arrange their own comprehension. In InterMIND the host creates the meeting; every guest joins by link, picks a language, and hears and reads everything in it — and signed-in members can reread it all afterwards. **Do my guests need an account or a paid plan?** No. Guests join by link in a browser, need no account, and pay nothing — the host's plan covers the room. Each guest picks their own language independently. The recap afterwards goes to signed-in members, each in their own language — a guest who wants to keep anything signs up for a free account. **Why provide translation for participants who speak good English?** Because the room gets smarter, not just kinder. People reason, argue and catch nuance best in the language they think in — natives included, since they stop decoding everyone else's second-language English. Provided-for-everyone is also what removes the stigma: when translation is the room's default, using your language signals exactly nothing. What that costs a team when it *isn't* provided is the subject of [the false-fluency trap](https://intermind.com/blog/false-fluency-trap); why we build the room around languages instead of around English is [the other bundle](https://intermind.com/blog/bundle-of-languages). --- # Google Meet live translation (2026): how it works, what it costs, and where it stops - **Yes, two ways.** Translated captions as text in 90+ languages and Gemini speech translation of the audio, both behind a Workspace or Google AI plan. - **One English-anchored pair at a time.** Six pairs, all including English, a beta capped at 90 minutes, not in live streams or recordings; no interpreter channels. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, files and the recap, next to Meet rather than instead of it. Guests join free by link, no account; you pay only for active members. If you searched "Google Meet live translation" or "does Google Meet translate in real time," the honest short answer is: **yes, Meet can translate a live meeting — two different ways — and which one you get depends on your plan.** Both are real and both are good at a specific job. Neither is built for a room where four nationalities each need to hear the meeting in their own language at the same time. This post explains how each works, how to turn it on, and exactly where the ceiling is — so you can tell which side of it your meeting lands on. > This is the platform how-to companion to our foundational guide, [*Real-time meeting translation: how it works, and how to evaluate one*](https://intermind.com/blog/real-time-meeting-translation). If you want the category-wide version of "how should this work," start there. For the Zoom and Microsoft Teams versions of this post, see [Zoom](https://intermind.com/blog/zoom-live-translation) and [Teams](https://intermind.com/blog/teams-live-translation). New to interpretation as a category? Start with [*Simultaneous interpretation: booth, RSI, or AI*](https://intermind.com/blog/simultaneous-interpretation-guide). --- ## The two features, and why they're not the same thing Google Meet has shipped live translation in two distinct forms. People conflate them constantly, so separate them first: ### 1. Translated captions (text) The older feature. The speaker talks; Meet shows **on-screen caption text translated into another language**. It's a reading experience — subtitles, not audio. Google's help page lists **90+ languages** to and from, and availability on **Business Standard, Business Plus, Enterprise Standard, Enterprise Plus, and Google AI Pro for Education** Workspace editions. Useful when one person presents and others follow along in text, or for accessibility. It does not change what anyone *hears*. ### What Meet does not have: interpreter channels People also search "Google Meet language interpretation" expecting the feature Zoom and Teams ship — audio channels for human interpreters you hire. Google's Meet help documents no such feature (checked August 2026): Meet's two translation features are the AI captions and the AI speech translation above. If your event has contracted interpreters, that is [Zoom's Language Interpretation](https://intermind.com/blog/zoom-interpreter) or [Teams' interpretation channels](https://intermind.com/blog/teams-live-translation), not Meet. ### 2. Speech translation (audio) The newer, Gemini-powered feature, rolled out through 2025–2026. This one translates the **spoken audio itself**, in near real-time, "in a voice like yours" — so a listener hears the speaker's words in their own language, in a voice resembling the speaker's. This is the headline feature, and it's genuinely impressive. It's also where the limits live, so it's worth being precise about them. --- ## How to turn on speech translation in Google Meet 1. You (and the feature) must be on a qualifying plan: **Google AI Pro or Ultra**, or Workspace **Business Standard/Plus**, **Enterprise Standard/Plus**, **Frontline Plus**, **AI Pro for Education**, or **AI Expanded Access**. On Workspace, an admin may need to enable it. 2. In a meeting, open the captions/translation controls and turn on **speech translation**, then pick *Language you speak* and *Language you prefer to hear* — each participant sets their own. 3. Wait for the translation indicator on the speaker's tile to clear before you respond — there's a built-in delay of a few seconds for the translation to complete. That's the whole setup. The friction isn't the toggle; it's what the toggle can and can't do. --- ## What Google Meet translation costs Neither feature is sold on its own — both come with a plan. Google's Workspace list prices as shown on its pricing page (EUR, per user per month, checked August 2026; the page notes a 16% saving on annual commitment): - **Business Starter — €6.80.** No translated captions, no speech translation. - **Business Standard — €13.60.** Translated captions and speech translation; "Gemini in Meet" is listed from this tier. - **Business Plus — €21.10.** Same translation features. - **Enterprise Standard / Plus — custom pricing.** Same translation features. - **AI Expanded Access** is listed as an add-on that includes real-time speech translation for editions that don't carry it. - **Google AI Pro / Ultra** — consumer subscriptions that also unlock speech translation for personal accounts. So the translation itself is free at the point of use; the gate is which plan the account is on, and every participant who wants to *hear* a translation needs to be on a qualifying plan themselves. ## The two features side by side | | Translated captions | Speech translation | | -------------------------- | ------------------------------------------------- | -------------------------------------------------------------------------------------- | | What you get | On-screen text in your language | Spoken audio in your language, in a voice resembling the speaker's | | Languages | 90+ | 6 pairs, all anchored on English (French, German, Hindi, Italian, Portuguese, Spanish) | | Who picks the language | Each participant | Each participant (speak / hear), within the English pairs | | Plan | Business Standard and above; AI Pro for Education | Business Standard and above, Frontline Plus, AI Expanded Access, Google AI Pro/Ultra | | Time limit | None stated | 90 minutes per meeting (beta) | | Recordings / live streams | Captions can be embedded in a recording | Not available in live streams or recordings | | Human interpreter channels | — | — (Meet has no such feature) | --- ## The limits that actually decide if it fits This is the part the feature announcements don't lead with. As of August 2026, Meet's speech translation is, by Google's own documentation: - **English-anchored.** Translation runs **between English and French, German, Hindi, Italian, Portuguese, or Spanish** — six pairs, and that's the full list. Every pair includes English. There is no German↔Japanese, no Spanish↔Arabic, no path that doesn't route through English. If your meeting's languages aren't "English plus one of those six," speech translation doesn't cover it. - **English plus one, per person.** Each participant picks the language they speak and the language they hear, but both must sit on one of the six English pairs. A room with an English, a Spanish, and a German speaker can be served only as far as each of them pairs with English — there is no Spanish↔German path in that room. - **Beta, with hard caps.** It's a beta feature: **90 minutes per meeting**, not available in live streams or recordings, participants under 18 can't use it, and meeting-room hardware can only listen, not translate. - **A few seconds of delay.** Google tells users to wait for the translation symbol to disappear before replying. That's fine for taking turns; it's turn-taking, not the continuous flow a fast back-and-forth needs. On privacy, Google is clear and good here: no audio is saved, and no models are trained on your voice. None of this makes the feature bad. It makes it **a bilingual, English-anchored tool** — built for an English speaker and a Spanish speaker taking turns, not for a genuinely multilingual room. --- ## The structural ceiling, in one sentence **Google Meet translates *a pair of languages, anchored on English, one at a time.* A genuinely multilingual meeting needs *every participant in their own language, at once.*** Those are different architectures, not different settings — which is why "more languages" can't be a future toggle on the pair-at-a-time model; it's a different way of building the room. If your meetings are "English plus one other language, two parties, under 90 minutes," Meet's speech translation may be all you need, and it's built into a tool you already have. If your meetings have three or more languages in the room — or two that aren't English — you've hit the ceiling, and the question becomes which tool was built for the other side of it. --- ## When you've outgrown the pair-at-a-time model This is the job we built InterMIND for: not bilingual-with-English, but **every participant in their own language, simultaneously, live.** Concretely, where Meet's speech translation does one English-anchored pair, InterMIND does: - **23 languages live**, on voice, chat, and shared notes — with no requirement that English be one of them. A French speaker and a Japanese speaker can meet without anyone touching English. ([The full end-to-end translation stack](https://intermind.com/features/realtime-translation) is its own page.) - **Per-listener audio.** Each participant hears the meeting in their own picked language at the same time — five people, five languages, one room. (How that actually works under the hood is in [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Continuous, not turn-based.** Each participant hears it live, in their own language; the design target is a conversation that flows, not turn-taking around a translation indicator. - **Document, chat, and notes translation too** — 30 languages for files dropped in chat — not just spoken audio. - **Quality you can audit.** We publish per-language-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark), rather than asking you to take a launch post's word for it. We're not claiming Meet is bad — for its bilingual case, voice-preserving speech translation is a strong feature. We're claiming it's a different shape of meeting. The honest comparison is in [*Real-time meeting translation*](https://intermind.com/blog/real-time-meeting-translation) and across our [platform comparisons](https://intermind.com/compare). --- ## What stays after the call, and where it lands The live part is the half of the meeting a vendor demos; the other half starts when the call ends. What InterMIND keeps, and where it can go — each item has its own guide: - **The recap, in each member's language.** After every transcribed meeting the signed-in participants get the AI summary, the full transcript and the recording on one permanent, members-only link; each reads the summary in their own language, and a channel keeps the recap of every past session. — [Meeting recap: what you get after the call](https://intermind.com/blog/meeting-recap) - **A copy in your CRM or help desk, by email.** The host adds the tool's inbound address as a recap copy recipient, confirms it once through a test email, and every recap of that room is sent there as a hidden BCC. — [How to get a copy of every meeting recap in your CRM by email](https://intermind.com/blog/how-to-get-a-copy-of-every-meeting-recap-in-your-crm-by-email) - **Structured, into any system.** A Zapier trigger, a signed `recap.ready` webhook, and an API with an OpenAPI 3.1 contract for Make, n8n, Pipedream and AI agents. — [Zapier, a webhook, or the API](https://intermind.com/blog/how-to-send-meeting-recaps-to-your-crm-with-zapier-or-the-api) - **The channel's history.** A meeting that persists as a channel keeps its chat, files, document summaries and recaps, readable by every member in their own language — and a client outside the team can be a member of it by email. — [How to add an external client to a team chat channel](https://intermind.com/blog/how-to-add-an-external-client-to-a-team-chat-channel) - **What the team sends in from elsewhere.** Every channel has its own email address, so a ticketing system or a monitoring tool posts into it without a bot; a file shares in from any app's share sheet on a phone or a Mac. — [Email to channel](https://intermind.com/blog/email-to-channel-no-bot), [Share from any app](https://intermind.com/blog/how-to-share-a-file-into-your-team-chat-from-any-app) The record is also where Meet draws an edition line. Google's help lists the Workspace editions that can record a meeting — Business Standard and Plus, Enterprise Starter, Standard and Plus, Essentials and Enterprise Essentials, Education Plus, Teaching and Learning Upgrade, Workspace Individual, and Google One with 2 TB or more — and Business Starter is not on the list; on a listed edition, nobody records if the host lacks the permission (checked October 2026). In InterMIND the recording, the transcript and the summary are on every plan, the free one included; the free plan's limits are 24 hours per meeting and 2 hours of translation per month. A guest of a meeting — a participant without an account — gets the live part in full and none of the record; the account is free, and it is what makes the record reachable. --- ## Try the other side of the ceiling - **[Try the live demo](https://intermind.com/demo)** — hear a real meeting translated live, per listener, in any of 23 languages, instead of one English-anchored pair — no signup needed. - **[Start your first meeting](https://intermind.com/chats)** — guests join by link, each in their own language. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month translation quality on real traffic, with the methodology written down. - [InterMIND vs. the platforms you know](https://intermind.com/compare) — honest, feature-by-feature. - Running a webinar or training across languages? The event workflow: [events & webinars](https://intermind.com/use-case/events). - Just need a record, not live translation? The notetaker head-to-head: [Otter vs Fireflies](https://intermind.com/blog/otter-vs-fireflies). Google Meet live translation is a real, useful feature with a clearly drawn edge. Knowing where that edge is — English-anchored, one pair, 90 minutes — is the whole decision. --- ## FAQ **Does Google Meet translate audio or only captions?** Both, on different plans. Translated captions show the speech as text in your language (Business Standard/Plus, Enterprise Standard/Plus). Speech translation — the Gemini-powered feature — translates the spoken audio itself, in a voice resembling the speaker's, on Google AI Pro/Ultra and qualifying Workspace editions. **Which languages does Google Meet speech translation support?** As of August 2026: between English and French, German, Hindi, Italian, Portuguese, or Spanish — six pairs, every one of them anchored on English. Translated captions are a separate, text-only feature with 90+ languages. **Does Google Meet translate in real time?** Yes, two ways: translated captions render the speech as text in your language with a short lag, and Gemini speech translation plays the spoken audio in your language a few seconds behind the speaker — Google tells you to wait for the translation indicator to clear before replying. **Does Google Meet have language interpretation?** Not as Zoom and Teams mean it. Google's Meet help documents no audio channels for human interpreters (checked August 2026). Meet's translation is AI captions or AI speech translation; interpreter channels are a [Zoom](https://intermind.com/blog/zoom-interpreter) or [Teams](https://intermind.com/blog/teams-live-translation) feature. **How do I turn on translation in Google Meet?** Captions: turn on captions in the meeting and choose a translation language (organizer on Business Standard or above). Speech translation: open the captions/translation controls, turn on speech translation, and pick the language you speak and the language you prefer to hear — on a qualifying plan, with an admin enabling it on Workspace. **Can Google Meet translate speech, not just captions?** Yes — Gemini speech translation translates the spoken audio itself, in a voice resembling the speaker's, on Google AI Pro/Ultra and qualifying Workspace editions. It is limited to six English-anchored pairs, 90 minutes per meeting, and doesn't work in live streams or recordings. **Is Google Meet speech translation free?** No. It requires Google AI Pro or Ultra, or a qualifying Workspace edition (Business Standard/Plus, Enterprise Standard/Plus, Frontline Plus, or AI Pro for Education), and on Workspace an admin may need to enable it. **How long can a translated Google Meet meeting run?** Speech translation is a beta capped at 90 minutes per meeting. It also doesn't work in live streams or recordings, and participants under 18 can't use it. **Why can't I record my Google Meet?** Because recording is an edition feature, not a button to unlock. Google's help lists the editions that can record — Business Standard and Plus, Enterprise Starter, Standard and Plus, Essentials and Enterprise Essentials, Education Plus, Teaching and Learning Upgrade, Workspace Individual, Google One 2 TB+ — and Business Starter is not among them; even on a listed edition the host must hold the permission, or no one records (checked October 2026). In InterMIND the recording, the transcript and the summary in each member's language come with every plan, including the free one, which is limited to 24 hours per meeting and 2 hours of translation per month. **What if the conversation isn't in Google Meet at all?** The same question comes up for a French, Spanish or Russian speaker talking to an Italian one: a phrase app handles a menu, a conversation needs a room where everyone speaks their own language. Our guides on the [French–Italian](https://intermind.com/blog/traduttore-francese-italiano-vocale), [Spanish–Italian](https://intermind.com/blog/traduttore-spagnolo-italiano-vocale) and [Russian–Italian](https://intermind.com/blog/traduttore-italiano-russo-vocale) voice translator draw that line, and the [Italian voice translator overview](https://intermind.com/blog/traduttore-vocale) covers the rest. — The Mind.com Team --- *Sources: [Google Meet — Learn about Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, [Google Workspace — Gemini updates](https://blog.google/products/workspace/google-workspace-gemini-may-2025-updates/){rel=""nofollow""}, [Google Meet — Use translated captions](https://support.google.com/meet/answer/10964115){rel=""nofollow""}, [Google Workspace — plans and pricing](https://workspace.google.com/pricing){rel=""nofollow""}, [Google Meet — Record a video meeting](https://support.google.com/meet/answer/9308681){rel=""nofollow""} (checked October 2026). Google expands supported languages and plan bundles over time; check the help and pricing pages for the current state. All facts checked August 2026.* # Google Workspace alternatives for teams that work across languages (2026) - **The lists compare the wrong axes.** What matters is who reads Chat in their language, who hears the meeting in theirs, and whose language keeps the history. - **Each alternative answers differently.** Microsoft 365 translates messages for everyone, meetings per Copilot seat; Zoho Cliq behind an admin switch; Proton and Nextcloud keep the original. - **InterMIND keeps the whole space in each member's language,** meetings, chat, documents and history, next to the office bundle you keep. Guests join free by link, no account; you pay only for active members. Search "Google Workspace alternatives" and the lists agree with each other: mailbox size, storage per user, how close the Docs clone is, price per seat. Useful if the bundle is your problem. Useless if your actual problem is that **your team's everyday communication happens in more than one language** — the Chat space, the Meet call, the doc someone pastes at 6 pm — because on those lists every alternative is the same product: a bundle of apps around communication in one language. This is the other comparison. If you're leaving Workspace (or deciding not to) because a Lagos account manager, a Kraków engineer and a Jakarta support lead share one space, four axes decide the purchase — and none of them is the mailbox: 1. **Messages: does each member read the space in their own language — automatically, or one message at a time on request?** 2. **Meetings: does every participant hear the call in their own language, or does someone hold a plan or license that the rest don't?** 3. **Afterwards: what does the history look like a month later — and in whose language?** 4. **Where it lives: can you name the jurisdiction the messages, files and recordings sit in?** Here is Google's own baseline on those axes, then the alternatives people actually evaluate — Microsoft 365, Zoho Workplace, Proton, Nextcloud Hub — then us, with one table across all of them. Every competitor fact comes from the vendor's public documentation, checked August 2026, linked in the footer. Prices are quoted from the vendors' pricing pages on the check date; they change. --- ## The baseline: what you'd be leaving Workspace comes in four editions — Business Starter, Standard, Plus and Enterprise — listed at €6.80, €13.60 and €21.10 per user per month for the three Business tiers on Google's EU pricing page (Enterprise on request), with Gemini "in Gmail" on Starter and "in Gmail, Docs, Meet, and more" from Standard up. On the four axes: - **Messages:** Google Chat's **Automatic Translation** turns incoming messages into "your preferred language set in your Google account settings"; "this feature requires an eligible Google Workspace or Google AI plan", and "translated messages are only visible to you". It covers the languages of Google's Neural Machine Translation model. - **Meetings:** Meet's speech translation runs **between English and five languages, one language pair per meeting**, as a **90-minute beta**, unavailable in recordings. Meet's *Take notes for me* writes a Google Doc in eight languages — "one language at a time. Multiple languages spoken in the same meeting aren't currently supported." Participant caps: 100 (Starter), 150 (Standard), 500 (Plus), 1,000 (Enterprise). Details: [Google Meet live translation](https://intermind.com/blog/google-meet-live-translation). - **Afterwards:** Chat history per the admin's retention settings, in the original language; the translated view is per reader. Meet notes in one language. - **Where it lives:** **Data regions** — "the United States or Europe" — on Business Standard and Plus, Enterprise, Frontline and Education editions, covering Chat messages, attachments, room names, and Meet recordings and transcripts. Users on other editions "aren't covered by data region policies". If that fits your team, staying is a defensible choice. The question is what the alternatives change. ## Microsoft 365 (Teams) The alternative on every list, and the one with the most language machinery: - **Messages:** a Teams chat or channel message is translated on request or automatically — "Teams can automatically translate received messages" — in 100+ languages, with no plan or license named for it. - **Meetings:** translated captions in 31 languages need the **organizer's Teams Premium or Microsoft 365 Copilot license**; the **Interpreter agent** (synthetic translated speech, 10 languages) is licensed **per listener** and metered at 20 hours per user per month. Captions aren't saved; recordings keep original audio. Details: [Teams live translation](https://intermind.com/blog/teams-live-translation). - **Afterwards:** each message stays in the language it was written in; a Recap exists for recorded or transcribed scheduled meetings, with AI notes behind Premium or Copilot. - **Where it lives:** Teams data "resides in the geographic region associated with your Microsoft 365 or Office 365 organization"; the **EU Data Boundary** commits Microsoft to store and process Microsoft 365 Customer Data within EU/EFTA for tenants signed up there, with documented exceptions. Against Workspace, Microsoft 365 trades Gemini editions for Copilot seats: message translation for everyone, meeting translation per licensed listener. The full comparison from the Teams side: [Microsoft Teams alternatives](https://intermind.com/blog/microsoft-teams-alternatives). ## Zoho Workplace Zoho's page for exactly this search bundles "Zoho Mail, Zoho Cliq, Zoho Writer, Zoho Sheet, Zoho Show, Zoho WorkDrive, and Zoho Meeting", sold as MailLite or Workplace Professional per user per month, mix-and-matched "under the same bill". - **Messages:** Cliq has **message translation** — an admin enables it in the Admin Panel (Configurations → Conversations → Message Translation), after which "users will be able to select the translation mode"; with **Automatic Translation** a user's incoming messages in languages they don't know are "translated to their default language". Zoho documents two engines, its own Zia or Google Translator (the latter with a purchased API key), and states that "Zoho Cliq does not use customer experience data to train, retrain or improve AI models in translation." - **Meetings:** Zoho Meeting is in the bundle; its documentation doesn't describe translated audio or captions per participant (checked August 2026). - **Where it lives:** Zoho runs European data centers in **Amsterdam (primary) and Dublin (secondary)**; "based on the country chosen" at sign-up, "the corresponding datacenter is chosen for your account". Against Workspace, Zoho gives the chat layer automatic translation as a standard feature behind an admin switch, EU residency by sign-up country, and a meeting layer without documented translation. ## Proton for Business The privacy-first alternative, and since 2025 a full bundle: "Mail, Calendar, Drive, Docs, Sheets, VPN, Pass, Meet, and Lumo AI" in "a single, convenient subscription", from Proton AG in Geneva — "based in Switzerland". - **Messages and meetings:** "End-to-end encrypted by default." **Proton Meet** encrypts "all calls, screen shares, and chat messages" with Messaging Layer Security; the Professional plan hosts up to 100 participants for up to 24 hours, and external participants join "even if they don't have a Proton Account". No translation feature is documented for Mail, Docs or Meet (checked August 2026) — and end-to-end encryption by design leaves no server-side place for one. - **Where it lives:** Switzerland, end-to-end encrypted. Against Workspace, Proton answers the fourth axis as completely as a bundle can, and answers the first two with the original language only. ## Nextcloud Hub The self-hosted bundle: "Files", "Talk" ("calls, chat and videoconferencing"), "Groupware" (calendar, contacts, mail), "Office" and a "private and local AI assistant" — and "you decide where your data is: on your company's server, with a provider you trust, or maybe at home, on your own machine." - **Messages:** translation in Talk and other apps runs through Nextcloud's translation API, backed by the **translate / translate2** apps — local machine translation on your server — or another provider you register. - **Meetings:** the **live\_transcription** app provides live transcription and translation in Talk calls — "the transcription is done on your own server… while the translation is done using a translation task processing provider" — with Nextcloud 33, the High-Performance Backend, and an NVIDIA GPU with at least 10 GB VRAM or a 4-thread x86\_64 CPU. - **Where it lives:** wherever you deploy it. Enterprise pricing on request. Against Workspace, Nextcloud puts every axis on your own hardware, including the GPU that does the transcribing. ## InterMIND We are not a bundle of office apps — no mailboxes, no spreadsheets. If those are what you're replacing, keep them: Workspace, Microsoft 365, Zoho or Proton do that job. What we build is the other bundle: **a bundle of languages around your team's communication** — meetings, chat, documents and their history, each in every member's own language, in a jurisdiction you choose. Stated on the same four axes: - **Messages:** the space is translated for each member as its default behavior — chat and shared notes in **23 languages**, documents in **30**. No per-message *Translate*, no eligible-plan gate, no admin switch: a member who reads Polish reads the channel in Polish. ([Why the numbers differ per pipeline.](https://intermind.com/blog/how-many-languages-do-you-support)) - **Meetings:** every participant picks their language on joining and **hears every speaker in it, simultaneously**, in the speaker's own voice — no English anchor, no per-meeting pair, no per-listener license. **Participants pay nothing and need no account** — a link is enough. ([Why participation is free.](https://intermind.com/blog/free-for-participants)) - **Afterwards:** the meeting persists as a channel — chat history readable in each member's language, the recap delivered to signed-in members in theirs, documents in the same space; your own chats export as a ZIP and restore. ([How much of your meeting still exists a week later](https://intermind.com/blog/the-meeting-a-week-later) · [Meeting recap](https://intermind.com/blog/meeting-recap)) - **Where it lives:** **EU at every runtime hop** — translation on our own engine on dedicated servers in France, orchestration in Paris, database in Frankfurt, EU-resident storage; the recap on the AI gateway the organization selects, in an EU region (Azure OpenAI EU Data Zone by default), with zero data retention; document translation through one named EU sub-processor (DeepL). ([Where one InterMIND meeting actually runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs)) Quality is published monthly, per language pair, on real traffic — [/benchmark](https://intermind.com/benchmark). --- ## The comparison, in one table | | Messages in each member's language | Meetings: everyone hears their own language? | Who pays for translation | History a month later | Where it can live | | ------------------------- | ------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- | ----------------------------------------------- | --------------------------------------------------------------------------------- | --------------------------------------------------- | | **Google Workspace** | Automatic Translation, visible only to you; eligible Workspace or Google AI plan | Meet: English ↔ 5, one pair per meeting, 90-min beta; notes in one language | Eligible edition per user | Original text per retention policy | US or Europe data regions on Business Standard+ | | **Microsoft 365 (Teams)** | On request or auto on view, 100+ languages; no license named | Interpreter agent, 10 languages, per licensed listener, 20 h/month; captions 31 (organizer Premium/Copilot) | Organizer + each listener (Copilot) for voice | Original text; Recap for recorded/transcribed scheduled meetings | Tenant region; EU Data Boundary for EU/EFTA tenants | | **Zoho Workplace** | Cliq Automatic Translation to each user's default language; Zia or Google Translator (API key); admin-enabled | Not documented for Zoho Meeting | In the plan (Zia) or your Google API key | Original text | Amsterdam / Dublin by sign-up country | | **Proton for Business** | Not documented | Proton Meet, end-to-end encrypted (MLS), original language; join without an account | — | Original, end-to-end encrypted | Switzerland | | **Nextcloud Hub** | Via the translate apps on your server | Live transcription on your server + translation via a task provider (GPU/CPU) | Your hardware | On your server | On-premises or a provider you trust | | **InterMIND** | Yes — 23 languages chat and notes, 30 documents, as the default | Yes — every participant hears every speaker in their language, 23 languages | Host's plan only; participants free, no account | Channel history in each member's language; recap to signed-in members; ZIP export | EU at every runtime hop: France, Paris, Frankfurt | --- ## How to choose (including when not to switch) - **Your team writes and meets in one language.** Stay on Workspace — or move for the reasons the other lists cover (price, mailbox, Docs). A multilingual space solves a problem you don't have. - **You want the office bundle plus message translation for everyone:** Microsoft 365 documents Teams message translation without a license; Zoho Workplace documents Cliq automatic translation behind an admin switch. Meeting translation is per Copilot seat on Microsoft's side and not documented on Zoho's. - **Jurisdiction and end-to-end encryption outrank translation:** Proton (Switzerland, E2EE by default, Meet without accounts) or Nextcloud Hub on your own servers — with translation on your own GPU if you run the live\_transcription app. - **Free:** Nextcloud is free to self-host; Proton Meet's free tier hosts calls without an account; InterMIND is free for every participant — guests join by link, the host's plan covers the room, and the [live demo](https://intermind.com/demo) needs no signup. - **The space itself is multilingual** — members replying to each other in three languages, guests without your licenses, a team that needs to reread last month's decision in their own language, and a compliance officer who wants a jurisdiction they can name: that's the case we built [InterMIND](https://intermind.com/chats) for — keep your mailboxes where they are. ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener in any of 23 languages. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, monthly translation quality on real traffic, with the methodology public. - **[Compare feature-by-feature](https://intermind.com/compare/google-workspace)** — InterMIND vs Google Workspace, with every competitor cell sourced. --- ## FAQ **What can I use instead of Google Workspace?** For the office bundle: Microsoft 365, Zoho Workplace, Proton for Business, or self-hosted Nextcloud Hub. For a team that doesn't share one language, compare the fences instead of the logos: Teams translates messages for everyone and meetings per Copilot seat; Zoho Cliq translates automatically behind an admin switch; Proton and Nextcloud keep the original language (Nextcloud can translate on your own GPU); InterMIND translates the whole space — chat, meetings, documents, history — for every member on the host's plan, and leaves mail and spreadsheets to the bundle you keep. **Is there a free Google Workspace alternative?** Nextcloud Hub is free to self-host; Proton Meet's free tier hosts calls with no account needed; Zoho and Microsoft price per user. InterMIND is free for participants by design — guests join by link without an account, and the host's plan covers the room; the live demo needs no signup. **Is it cheaper to use Google Workspace or Microsoft 365?** Compare the editions that actually contain what you use. Google's EU pricing page lists Business Starter at €6.80, Standard at €13.60 and Plus at €21.10 per user per month (regular pricing, checked August 2026); on the language axes, Chat translation needs an eligible plan and Meet's speech translation is a beta. On Microsoft's side message translation is documented without a license, while meeting translation sits on Teams Premium or Copilot licenses per organizer and listener. The cheaper bundle depends on which of those layers your team needs. **Which Google Workspace alternatives keep data in Europe?** Workspace itself offers a Europe data region on Business Standard and above. Microsoft 365 stores EU/EFTA tenants' data within the EU Data Boundary; Zoho assigns Amsterdam or Dublin by sign-up country; Proton is in Switzerland; Nextcloud runs wherever you deploy it. InterMIND runs in the EU at every hop — France, Paris, Frankfurt — on every plan. **Which Google Workspace alternatives translate chat and meetings?** Chat: Teams (100+ languages, no license), Zoho Cliq (automatic, admin-enabled), Nextcloud with its translate apps, InterMIND (23 languages, as the default). Meetings: Teams' Interpreter agent (10 languages, per licensed listener), Nextcloud's live transcription with translation on your own hardware, InterMIND (every participant hears every speaker in their language, 23 languages). Google's own Meet translates English ↔ five languages, one pair per meeting; Proton documents none. **Does Google Chat translate messages automatically?** Yes — Automatic Translation converts incoming messages to the language set in your Google account, "requires an eligible Google Workspace or Google AI plan", and the translations "are only visible to you". The stored message stays in the language it was written in. --- *Sources: [Google Workspace — Pricing](https://workspace.google.com/pricing){rel=""nofollow""}, [Google Chat — Use Automatic Translation in Chat](https://support.google.com/chat/answer/15711193?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}, [Google Meet — Learn about Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}, [Google Workspace — Choose a geographic location for your data](https://knowledge.workspace.google.com/admin/compliance/choose-a-geographic-location-for-your-data){rel=""nofollow""}, [Google Workspace — Data covered by data regions](https://knowledge.workspace.google.com/admin/compliance/data-covered-by-data-regions){rel=""nofollow""}, [Microsoft — Translate a message in Microsoft Teams](https://support.microsoft.com/en-us/teams/chat/translate-a-message-in-microsoft-teams){rel=""nofollow""}, [Microsoft — Interpreter in Teams meetings and calls](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft — Use live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""}, [Microsoft Learn — Location of data in Microsoft Teams](https://learn.microsoft.com/en-us/microsoftteams/location-of-data-in-teams){rel=""nofollow""}, [Microsoft Learn — What is the EU Data Boundary?](https://learn.microsoft.com/en-us/privacy/eudb/eu-data-boundary-learn){rel=""nofollow""}, [Zoho Workplace — Google Workspace alternative](https://www.zoho.com/workplace/google-workspace-alternative.html){rel=""nofollow""}, [Zoho Cliq — How can an admin enable message translation in Cliq?](https://help.zoho.com/portal/en/kb/zoho-cliq/admin-guides/configurations/articles/how-can-an-admin-enable-message-translation-in-cliq){rel=""nofollow""}, [Zoho Cliq — How can a user enable automatic translation in Cliq?](https://help.zoho.com/portal/en/kb/zoho-cliq/user-guides/conversations/messages/articles/how-can-a-user-enable-automatic-translation-in-cliq){rel=""nofollow""}, [Zoho — Know your datacenter](https://www.zoho.com/know-your-datacenter.html){rel=""nofollow""}, [Proton for Business](https://proton.me/business){rel=""nofollow""}, [Proton Meet for Business](https://proton.me/business/meet){rel=""nofollow""}, [Nextcloud Hub](https://nextcloud.com/hub/){rel=""nofollow""}, [Nextcloud — Live Transcription and Translation in Nextcloud Talk](https://docs.nextcloud.com/server/stable/admin_manual/ai/app_live_transcription.html){rel=""nofollow""}, [Nextcloud — Local Machine translation 2 (translate2)](https://docs.nextcloud.com/server/31/admin_manual/ai/app_translate2.html){rel=""nofollow""}. Vendors change plans, prices, language lists and beta status over time; check their pages for the current state. All facts checked August 2026.* # Hindi to English voice translator — and English to Hindi — live, in a real conversation - **A phrase and a conversation are different problems.** Phone apps relay one sentence at a time; earbuds work one-to-one in person; a call needs both directions at once. - **Hindi to English is always English to Hindi too.** A tool that relays one direction at a time turns the conversation into a queue. - **InterMIND keeps the whole conversation in each member's language,** voice, chat and notes, live in both directions, for ten people or two. Guests join free by link, no account; you pay only for active members. Searching for a **Hindi to English voice translator** usually means one of two very different situations. Either you need one phrase spoken aloud — a tourist moment, a quick exchange — or you need a **conversation** to work across the two languages: a call with a client who speaks only English, an interview, an online lesson, a parent on the other side of the arrangement. The first problem was solved years ago. The second is where most tools quietly give up — and it's the one this guide is really about. One more thing the search phrase hides: a real conversation is never one-directional. "Hindi to English" and "**English to Hindi**" are the same need — you speak Hindi and they hear English, they answer in English and you hear Hindi. Any tool that only relays one direction at a time turns the conversation into a queue. --- ## The three kinds of Hindi–English voice translator ### Phone phrase apps Google Translate's conversation mode, Apple Translate, and dozens of "speak and translate" apps. Tap the mic, speak Hindi, it speaks English — then pass the phone over. Genuinely good for one sentence at a time, and most are free. The mechanic is a relay: speak → transcribe → translate → speak back, one direction at a time, one shared device. For a menu or an auto stand, perfect. For a discussion, the relay is the bottleneck — you operate a translator in turns instead of talking. ### Earbud translators AirPods Live Translation, Pixel Buds, and dedicated translator earbuds. You hear the other person translated in your ear — nicer than a screen, but **one-to-one, in person, and usually needing matching gear on both sides**. Built for a traveler and a host standing face to face, not for a call. ### Live meeting translation A different architecture: the *call itself* is bilingual. You speak Hindi and hear Hindi; they speak English and hear English — **both directions at once, continuously, live**. No phone passing, no turn-taking, and it works for three or ten participants as well as for two. --- ## Which one do you need? - **One phrase, in person** — a phone app. Don't over-buy; the free ones are good. - **Face to face, both people equipped** — earbuds are the nicest experience. - **A call, a meeting, an interview, a lesson — any real back-and-forth** — live meeting translation. The other two kinds technically "work" and quietly double the length of every exchange. The Hindi–English pair lands in the third case more often than most: the common scenario isn't a tourist phrase but **work and family across the two languages** — a client call where your English-speaking counterpart has no Hindi, a remote interview, an online class, a household video call spanning two countries. --- ## Where InterMIND fits InterMIND is the third kind: live meeting translation, with Hindi ↔ English as one live pair among many. It starts with one person — you open the room and send the link; the other side joins free, without an account, and hears you in their own language. - **Hindi and English, both directions, live** — you speak Hindi, each listener hears their own picked language; they answer in English, you hear Hindi. Continuous, per-listener, live. - **23 languages on voice, chat and shared notes** — so a three-way call can run Hindi ↔ English ↔ Japanese or any other mix, nothing forcibly routed through English. ([The full translation stack](https://intermind.com/features/realtime-translation) is its own page.) - **Guests join from one link** — browser, no signup. Send the link to your counterpart; their side needs no setup at all. - **Web, desktop, iOS and Android** — the phone is a full meeting participant, not a shared device passed across the table. - **Free meetings up to 24 hours** — enough for a full working day, not a token trial. - **Quality published, not promised** — per-language-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark), methodology included. Check how Hindi ↔ English stands before you rely on it. --- ## Try it - **[Try the live demo](https://intermind.com/demo)** — *hear* a real meeting translated live, per listener, Hindi ↔ English included — no signup needed — instead of reading promises about it. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month translation quality on real traffic. - Start with the category guide: [*Real-time meeting translation*](https://intermind.com/blog/real-time-meeting-translation). - Comparing specific language pairs? See the voice-pair guides for [English ↔ Italian](https://intermind.com/blog/traduttore-inglese-italiano-vocale), [French ↔ Italian](https://intermind.com/blog/traduttore-francese-italiano-vocale), [Spanish ↔ Italian](https://intermind.com/blog/traduttore-spagnolo-italiano-vocale), [Italian ↔ Russian](https://intermind.com/blog/traduttore-italiano-russo-vocale) and [Romanian ↔ Italian](https://intermind.com/blog/traduttore-rumeno-italiano-vocale). — The Mind.com Team --- *Sources: [Google Translate — Live translate](https://support.google.com/translate/answer/6142474){rel=""nofollow""}, [Apple — Live Translation with AirPods](https://support.apple.com/en-us/123185){rel=""nofollow""}, [Google — Translate with Pixel Buds](https://support.google.com/googlepixelbuds/answer/7573100){rel=""nofollow""}, checked August 2026. Vendors change features and language lists over time — check their pages for the current state.* # "How many languages do you support?" — and why our honest answer is six numbers, not one - **Six numbers, one per surface.** Voice, chat and notes are 23 languages; files 30; the site 33; Arabic is withdrawn while below the bar. - **The gaps are stated, not papered over.** Hindi runs live but not in files, eleven site locales lead the product, and every pair's quality is published monthly. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes and documents, with the real number next to every pair. Guests join free by link, no account; you pay only for active members. It is the first question on every procurement call and the first question in every demo. We get it three times a week: > "How many languages does InterMIND support?" The honest answer is: **it depends on which surface you mean.** We have six of them, and they have different language lists for good reasons. This page is the definitive answer so we stop giving inconsistent ones. --- ## The short version | Surface | Languages | | -------------------------------------------------------------------------------------------- | --------: | | Platform API (`createParticipant` accepts) | **24** | | Real-time voice translation in meetings | **23** | | Real-time chat-message translation | **23** | | Real-time shared-notes translation | **23** | | On-demand file translation in chat (DeepL Document API) | **30** | | Website UI (localized at [intermind.com](https://intermind.com){rel=""nofollow""}) | **33** | > **The product is 23 languages.** Files: **30**. Site: **33**. Speech engine: **24** — Arabic is in the engine but withdrawn from the product while it is below the bar. Voice, chat, and notes share the same 23 — the engine list minus Arabic. Files are wider because the file pipeline can be. The website has its own list because localizing a public site is a different cost — and a different lever — than translating in-product copy. Everything below is why those numbers are not the same. --- ## Why there isn't a single number A translation platform is not one product. It is at least three: 1. **A real-time speech pipeline** — audio in, translated audio out while the speaker is still talking, in a meeting where the latency budget is brutal. 2. **A real-time text pipeline** — chat messages and shared notes, character-by-character, propagated to every viewer in their language. 3. **An asynchronous document pipeline** — a 40-page PDF dropped into chat, translated as a whole file with formatting and structure preserved. Each pipeline has its own engine, its own latency budget, and its own per-pair quality envelope. A language that is production-grade for documents (slow, careful, many passes) can be unusable for live voice (fast, one shot, no retries). Treating those as "one language count" is what produces marketing pages that say "200+ languages" and tell you nothing. So we publish per-surface. --- ## 1. Platform API — 24 languages This is the widest list, because it is the engine surface. The [`createParticipant` endpoint](https://api.mind.com/#operation/createParticipant){rel=""nofollow""} accepts these 24 codes: `ar, cs, da, de, en, es, fi, fr, hi, hu, is, it, ja, ko, nl, no, pl, pt, ro, ru, sv, tr, uk, zh` If you are an integrator building on Mind directly, you can hand any of those 24 to a participant. That **does not** mean every one of those 24 scores the same on our quality bar. It means our engine can emit text in that language. The product shows 23 of them — Arabic is withdrawn while below the bar — and publishes each pair's quality openly (next section). --- ## 2. Voice, chat, and notes inside the product — 23 languages When a user joins an InterMIND meeting, the language picker shows all **23** engine languages — including **Hindi (`hi`)**, which we previously held back. **Arabic (`ar`)** is withdrawn from the picker as of August 2026: the engine is below our bar in both directions (voice into Arabic measured at 5 % coverage on the weekly benchmark, speech recognition from Arabic looping tokens), and a language that fails in a live call is worse than one that is absent. It returns when the measured pairs clear the bar. For weak-but-working pairs the trade-off is different: instead of hiding a language wholesale, we surface it and let the public per-pair numbers on [`/benchmark`](https://intermind.com/benchmark) tell the truth. Every pair — strong or weak — is measured on real traffic and deep-linkable by URL, so a user (or an auditor) can check `en→ar` before they rely on it rather than discover its quality mid-meeting. This is still the honest version, just tuned. Most of the category lists everything the model can emit and stays silent on quality; the opposite extreme (hide anything below a bar) makes a real, in-demand language invisible. We do neither by default: show the list, publish the number next to it, and withdraw a language only when it fails outright rather than underperforms — Arabic today. If a pair isn't good enough for your use case, the benchmark says so out loud. The same 23-language list applies across the three real-time surfaces: - **Voice translation** — per-viewer translated audio, live. Each participant picks their own listening language at the start of the call. - **Chat messages** — every message translated as it is typed; edits produce per-language diffs ([see v1.2](https://intermind.com/blog/intermind-v1-2-release)). - **Shared notes** — character-by-character live translation of the host's notes pane, per viewer, with diff history. One picker, one set of 23 languages, three places it shows up. --- ## 3. On-demand file translation — 30 languages Drop a PDF, DOCX, DOC, PPTX, or XLSX into the chat. Each participant can request the file in their language. The translated copy is returned as the same file format with structure preserved (tables, headings, lists). This surface uses the **DeepL Document API**; our file pipeline maps **30 target languages** — wider than our real-time voice pipeline. If you can translate the PDF to Estonian on DeepL today, you can translate it to Estonian in InterMIND chat today. The file list includes some languages our real-time pipeline does not — for example **Bulgarian, Greek, Estonian, Indonesian, Lithuanian, Latvian, Slovak, Slovenian**. **Arabic** is on the file list but currently withdrawn from real-time (see above): a French participant can request the contract PDF in Arabic, but cannot listen to the meeting in Arabic today. The one real-time language **not** on the file list: **Hindi.** Our document pipeline doesn't map it yet, so Hindi is available for live voice, chat, and notes but not for on-demand file translation — the reverse of the Arabic asymmetry. We flag this in the file picker rather than hide it. Why the file list is bigger in general: - Documents are **asynchronous**. There is no live-conversation budget, so the pipeline can afford a slower, more careful engine that handles more pairs well. - DeepL is a dedicated document-translation engine, and we use it directly for files. We do not try to route documents through the same engine that runs voice. Different problem, different tool. --- ## 4. Website UI — 33 languages [intermind.com](https://intermind.com){rel=""nofollow""} is currently shipped in **33 locales**: English, German, Spanish (Latin America), French, Italian, Portuguese (Brazilian), Dutch, Polish, Czech, Swedish, Danish, Norwegian, Finnish, Hungarian, Romanian, Greek, Slovenian, Lithuanian, Ukrainian, Russian, Turkish, Arabic, Hebrew, Hindi, Bengali, Urdu, Kazakh, Indonesian, Vietnamese, Thai, Chinese (Simplified), Japanese, and Korean. Eleven of those — **Arabic, Bengali, Greek, Hebrew, Indonesian, Kazakh, Lithuanian, Slovenian, Thai, Urdu and Vietnamese** — are localized on the public site but are **not** available for in-meeting translation: the speech engine doesn't cover the other ten, and Arabic is withdrawn while it is below the bar. So you can read the landing pages, blog, and docs in Thai or Arabic, but if you join a meeting, voice and chat translation won't run in them. We flag this in the language switcher rather than let you discover it in a live call. The other twenty-two locales are full products — site and in-meeting both. Why the site list differs from the product list: - A marketing site has its own translation cost — and its own quality bar. Landing pages, FAQs, pricing, legal copy. It is not free. - Localized pages are how a host finds us before the speech engine reaches their language: the site list leads the product in eleven languages on purpose, as a standalone capture layer. - One live language — Icelandic — runs in a meeting but has no site locale yet; there the product is ahead of the pages. Danish, Finnish, Hungarian, Norwegian, Romanian, Swedish, Slovenian and Lithuanian got their site locales in October 2026. This list will grow as pipeline grows. It is not capped on principle. It is capped on cost. --- ## The pattern, and how to read it on any vendor page Every multilingual vendor has these same surfaces. Most of them quote you the widest one and let you discover the others on your own. The honest version is: - The **engine** list is widest, because it is what the model emits. - The **product** list is narrower, because not every engine output meets a product bar. - The **document** list often differs from the **voice** list, because the engines are different. - The **website** list is counted separately, because translating your own site costs cash — it can lead the product or trail it. When you evaluate any platform in this category, ask for the four numbers separately. If a vendor refuses to split them — or doesn't know — you are not getting a useful answer. --- ## What we will not pretend - **Some pairs are weaker than others, and we say so.** Hindi is in the voice/chat/notes picker, but not every pair scores the same. Rather than hide a working language, we publish per-pair quality on [`/benchmark`](https://intermind.com/benchmark) — a weak pair shows its real number instead of being quietly dropped. Check the pair you need before you rely on it. Arabic is the one language we do withdraw outright, because its pairs currently fail rather than underperform. - **The file list (30) being wider than the voice list (23) is a real gap, not a feature.** A French user can request an Estonian translation of the PDF but cannot listen to the meeting in Estonian. We will not paper over this by quoting the bigger number and hoping you don't notice. - **The site leading the product in eleven languages is a gap, not a feature.** You can read the site in Thai or Bengali but not yet run a meeting in them. We flag it in the switcher instead of letting you find out mid-call. We close it as the speech engine adds them. --- ## Try it yourself - **[Try the live demo](https://intermind.com/demo)** — runs the production voice + chat pipeline against your audio, in any of the 23 product languages. The same pipeline that scores [`/benchmark`](https://intermind.com/benchmark). - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month quality on real traffic. Every pair in the picker, strong or weak, deep-linkable by URL. - **[Read the methodology](https://intermind.com/benchmark/methodology)** — what the numbers are, what they aren't, who the judge is. Six numbers, six surfaces, one engine. That is the honest answer to "how many languages do you support." --- ## FAQ **How many languages does InterMIND translate live?** 23 — the same list across voice, chat, and shared notes: `cs, da, de, en, es, fi, fr, hi, hu, is, it, ja, ko, nl, no, pl, pt, ro, ru, sv, tr, uk, zh`. Every pair's quality is published per month at [`/benchmark`](https://intermind.com/benchmark). **How many languages does document translation support?** 30, via the DeepL Document API — drop a PDF, DOCX, DOC, PPTX, or XLSX into chat and request it in your language with formatting preserved. The file list is wider than the live list (it adds e.g. Bulgarian, Greek, Estonian) but misses Hindi. **Why is the website list different from the product's?** The site ships in 33 locales because localizing a marketing site is a separate decision from in-product translation. Eleven site locales lead the product on purpose — flagged in the language switcher. — The Mind.com Team --- *Sources: [DeepL — supported languages](https://developers.deepl.com/docs/getting-started/supported-languages){rel=""nofollow""}, [Mind API — createParticipant](https://api.mind.com/#operation/createParticipant){rel=""nofollow""}; product surface lists verified against the shipped code, checked August 2026.* # How to add an external client or partner to a team chat channel — by email, with no account on their side yet (2026) - **Type their email in the member drawer.** A registered user is in at once; anyone else gets an email and joins on sign-up, free. - **A channel member is not a meeting guest.** A member reads the whole channel, calls included, in their own language; a guest sees one meeting, then nothing. - **InterMIND keeps the whole channel in each member's language,** messages, files and every call's recap, so the client lives in the project. Guests join free by link, no account; you pay only for active members. The client project runs in a channel; the client runs in email. If you searched "add an external user to a team chat", the short answer for InterMIND is: open the channel's member drawer, type their email, and they are invited — a registered user is in at once, anyone else joins on sign-up via the emailed link. This guide is the rest: who may add whom, what an external member sees, the invite link and how to revoke it, and how a channel member differs from a guest of a single meeting. One property first, because it is the reason to do this at all: a member of a channel reads the whole channel in their own language — every message, every file's summary, every recap — whatever language the team writes in. A client from another country is not asked to follow a foreign thread; the thread arrives in theirs. ## Add someone to a channel 1. **Open the member drawer.** Click the participant avatars in the chat header, or right-click the channel in the sidebar → **Manage group** (host only). 2. **Search.** The field at the top looks across your team, your contacts, the people you have met in meetings, and your organization directory. Type a name or an email. 3. **Click the person.** A registered InterMIND user is added immediately, no confirm step. Someone outside — an email you type — gets a **pending invite** and an email; they join the channel on sign-up via the link. The drawer tells you who is who: **In channel**, **Pending**, **Met before** for someone you have been in a finished meeting with, **External** for anyone outside your team. Hosts see an **Invited — pending** section with a **Revoke invite** button on each outstanding invite. ## The invite link and email invites The **Invite members** button in the drawer opens the other two ways in: - **Invitation link** — anyone with the link can join the channel. **Copy** it into the contract email or the kickoff deck. If it leaks, **Regenerate**: the old link stops working immediately. - **Email invites** — paste addresses separated by commas, spaces or new lines and click **Send Email Invites**. Each recipient gets a link to join this channel; addresses already in the channel or already invited are flagged before anything is sent. ## What an external member gets Everything the channel is: the messages, the files and their summaries, the history from before they joined, and every call started from the channel — the **Join** button at the top of the chat is theirs too, no approval step, because the channel's membership is the guest list. After each call the recap posts back into the channel, and they read it in their own language. What they do not get is your team: joining a channel by invite makes someone a member of that channel, not of your organization. The team's other channels, its directory and its settings belong to the team's members. ## A channel member or a meeting guest | | Guest of one meeting | Member of a channel | | -------------- | ------------------------------------------------------ | ------------------------------------------------------- | | Account | None — a name on the Join screen; the host admits them | Yes — invited by email, joins on sign-up | | Sees | That meeting, while it lasts | The channel: history, files, recaps, every call from it | | Language | Hears and reads the meeting in their own | Reads the whole channel in their own, always | | After the call | Nothing — no recap, no history | The recap in the channel, in their language | | Good for | A one-off interview or a first call | A client, a partner, a contractor who is in the project | For the one-off case, the [guide to joining a meeting](https://intermind.com/blog/how-to-join-a-video-meeting-from-your-computer) covers the guest path. ## Remove, rename, archive Tap a member row to remove that person; the host's row is fixed. Rename the channel from its header or the sidebar menu (host only). When the project ends, right-click → **Archive**: the channel leaves the main list, stays searchable in the archive view, and can be restored. Deletion — permanent, all messages and files — is available from the archive view only, after a confirmation. ## FAQ **Can I add someone who does not have an InterMIND account to a channel?** Yes. Type their email in the member drawer, or send an email invite. They get a link and join the channel on sign-up; the account is free. **Will my client understand a channel written in another language?** Yes. Every member reads the channel in their own language — messages, file summaries, recaps — whatever language it was written in. **Can an external member join calls from the channel?** Yes. The Join button at the top of the chat is the same for every member; the channel's membership is the guest list, so there is no approval step. **What can an external member see of my team?** The channel they were added to — its history, files and calls. Membership of the team, with its other channels, directory and settings, is a separate invitation. **What if the invitation link leaks?** Click Regenerate in the invite dialog. The old link stops working immediately. ## Try it - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Channels and members](https://intermind.com/docs/chat/channels)** — the member drawer, invites, archiving. - **[How to start a call from a team chat](https://intermind.com/blog/how-to-start-a-call-from-a-team-chat)** — one click from the channel, the recap comes back. # How to check your network and switch camera, microphone or speakers during a video call — without leaving it (2026) - **Both live inside the call.** Network statistics are under Devices in the meeting settings, open to every participant; devices switch from the control-bar submenu without dropping the call. - **Only your language follows your account.** Resolution, self-view and picked devices last one session, meeting defaults stay on the browser; the test room checks everything beforehand. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, files and the recap, the same diagnostics for everyone. Guests join free by link, no account; you pay only for active members. "You're breaking up" is a diagnosis nobody can act on. If you searched "check connection during a video call" or "switch microphone without leaving the meeting", the short answer for InterMIND is that both live in the meeting itself: the network statistics are in the **Devices** section of the meeting settings, open to every participant, and the camera, microphone and speakers switch from a submenu in the control bar without dropping the call. This guide is the rest: where each control is, what to look at, what happens when a device disappears mid-call, and what to check before the next one. ## The network statistics, for everyone Open the cockpit **Settings** (the gear in the **More** menu) and expand **Devices**. The **Network statistics** panel is there — for every participant in the room, not only the host or a moderator. Read it when the call degrades: it separates a weak link on your side from one on the speaker's, which is the question the room is really asking. If the numbers are the problem, two levers are next to them: the **Resolution** control caps the video resolution at 720p, 360p or 180p to save bandwidth on a slow connection, and the **Self-view** toggle hides your own tile while you present. ## Switch a device without leaving The control bar's microphone and camera buttons each have an arrow: it opens the device submenu — every microphone, camera and speaker the browser can see, in one place. Pick another one and the call continues on it; switching mid-call no longer leaves the room without audio or video, because the engine reacquires the device from the live list and retries if the first attempt fails. A device that is unplugged, or taken by another application, is reacquired the same way when it returns. The audio-level indicator on the microphone button shows whether the microphone is picking anything up. ## Which settings survive The meeting settings are split in two: - **Per session** — what you set for this call: resolution, self-view, the devices picked from the submenu. - **Persistent** — what InterMIND remembers between calls on this browser: your meeting defaults. The one meeting preference synced to your account rather than the browser is your translation language, set from the account menu. The pre-join screen appears the first time you join on a device and again whenever your camera, microphone or speaker setup has changed since — so a new headset is offered to you before the call, not discovered in it. ## Before the next call: the test room The [test room](https://intermind.com/browser-test) is a meeting-shaped page with nobody in it: your camera preview, your microphone level, your speakers, screen sharing, and the network — whether it reaches the outside world, how fast it answers, and a five-second bandwidth estimate against 360p, 720p and 1080p. One badge at the top says how many checks came back short. No account and no meeting link needed; the camera and microphone you pick there are the ones your next meeting starts with. ## FAQ **Can participants see the network statistics, or only the host?** Every participant. Open Settings from the More menu, expand Devices, and the Network statistics panel is there for everyone in the room. **How do I change my microphone during a call?** Click the arrow next to the microphone button and pick another device from the submenu. The call continues on it; the same submenu holds cameras and speakers. **My headset was unplugged mid-call. Do I have to rejoin?** No. When it returns, the engine reacquires it from the live device list and retries if the first attempt fails. **How do I test my setup before a meeting?** Open the test room at intermind.com/browser-test: camera, microphone, speakers, screen sharing and a network check, no account and no link needed. **Which settings are remembered?** Meeting defaults are kept per browser; your translation language is synced to your account; resolution, self-view and the devices picked from the submenu apply to the current session. ## Try it - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Meeting controls](https://intermind.com/docs/meetings/controls)** — every control in the bar, settings, shortcuts. - **[How to join a video meeting from your computer](https://intermind.com/blog/how-to-join-a-video-meeting-from-your-computer)** — the pre-join screen and the one setting that matters. # How to forward, select and bulk-delete messages in a team chat — and move through the history from the keyboard (2026) - **One gesture each.** Forward from the menu or by dragging onto a channel, select by dragging on blank space, delete the selection after one confirmation. - **Not everything travels.** Text, images and files go; reactions, pins, edit history and transcripts do not. The host can delete anyone's message, you delete your own. - **InterMIND keeps the whole conversation in each member's language,** so a forwarded message is read by every member of the target channel in theirs. You pay only for active members. A thread that belongs in another channel, ten test messages to clear, a decision to keep for yourself: if you searched "how to forward a message in a team chat" or "delete multiple messages", the short answer for InterMIND is that every one of those is one gesture — a menu item or a drag — and the forward waits for your comment before it goes. This guide is the full version: the two ways to forward, what travels with a forward, how selection works, who may delete what, and the keyboard. One property first, because it changes what "forward" means here: a message forwarded to a channel is read by every member of that channel in their own language, whatever language it was written in. ## Forward a message Two ways: - **From the menu.** Open the message's menu → **Forward** and pick a target from the submenu. Targets are the channels you belong to, plus your own **Inbox** (shown as "Saved (Inbox)"). - **Drag and drop.** Drag the message bubble onto a channel in the sidebar; the row highlights when it will accept the drop. Either way the forward is **staged**, not sent: a chip appears above the target chat's input ("Forward N messages"), you type a comment if you want one, and it goes out with your **Send**. Discard it with the chip's ×. What travels with a forward, and what does not: | Travels | Does not travel | | ---------------------------------------------------------------------------------------------- | ------------------------------------ | | Text, images, files | Reactions, pins, edit history | | A "Forwarded from *name*" label with the original author | Transcripts (the menu explains this) | | A recap document, as a link — opening it still requires membership of the source meeting | — | | A photo album, as one unit; a message that is part of a selection forwards the whole selection | — | The copy is sent by you, under the original author's name in the label. ## Select several messages Drag on **blank space** in the message list — beside or between bubbles — to select whole messages; dragging on the text itself keeps the normal text selection. On a touch device, tap messages to toggle them once a selection is active. A selection bar appears at the bottom with the count and the bulk actions: - **Forward** — the whole selection to a channel, staged as above. - **Delete** — every selected message after one confirmation. Available only when every selected message is yours, or you are the host; when it is locked, the bar says why. - **Cancel** — or **Escape**, or a click on blank space. Right-clicking a selected message shows the same selection-scoped actions instead of the single-message menu. ## Who may delete what You delete your own messages; the meeting host can delete any participant's message — the same **Delete** in the message menu, available on others' messages when you are the host. A deleted message is removed for everyone. Edits are a different story: only the author edits, and readers who enable **Show edit history** in the chat's display settings see the previous versions as word-level diffs — when they read in translation, the diff is built between translated versions. ## Drop a file anywhere Files go into a chat the same way messages move between them: drop a file anywhere on the app window and it uploads to the chat — a collapsed sidebar opens during the drag and closes after. Up to 25 MB per upload; a document shared this way is summarized automatically and read by each member in their own language. The [file sharing documentation](https://intermind.com/docs/chat/files) has the formats and the storage rules. ## Move through the history from the keyboard When the chat is focused — the in-meeting sidebar or a channel on the Channels page: | Keys | What they do | | ----------------------------- | ------------------------------------------------------------------------------------- | | **PageUp** / **PageDown** | Page the history — even while you are typing | | **↑** / **↓** | Scroll a line at a time when the message box is empty (otherwise they move the caret) | | **Home** / **End** | Jump to the oldest / newest message, same rule | | **Alt/Option + ↑ / ↓** | Recall your previous / next sent message | | **Cmd/Ctrl + F** | Chat search; **Enter** and **Shift + Enter** step through the matches | | **Enter** / **Shift + Enter** | Send / new line | The full list, including the in-meeting shortcuts, is in the [keyboard shortcuts documentation](https://intermind.com/docs/settings/keyboard-shortcuts). ## What Slack and Microsoft Teams state about forwarding Two documented maps, quoted, with the check date. Nothing here is an evaluation. | | Slack | Microsoft Teams | InterMIND | | ------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- | | Forwarding a message | "Hover over the message and click Forward message. Choose where you'd like to share the message and add a note if you'd like. Click Forward." | "Hover over the message and choose More options > Forward"; "Optionally, add a message above your forwarded content for context" | Message menu → **Forward**, or drag the message onto a channel; staged as a draft with your comment | | Several messages at once | Not stated on the forwarding page | "You can forward up to five messages at a time"; bundled "into a single message" in the original order | Drag-select on blank space, then **Forward** or **Delete** the whole selection | | What travels | Not stated on the forwarding page | "Chat messages, files, Loop components, app cards, and images"; "up to five images in a single message" | Text, images, files; a recap as a link; not reactions, pins, edit history or transcripts | | What the reader sees | Not stated on the forwarding page | "Look for the timestamp in the forwarded message header. Select the timestamp to open the original chat or channel message" | The forwarded text in the reader's own language; a "Forwarded from" label | The rows are drawn from the two help pages listed in the footer. "Not stated" means the page did not state it at check time, not that the product lacks it. ## FAQ **How do I forward a message to another channel?** Open the message's menu and choose Forward, or drag the bubble onto the channel in the sidebar. A chip appears above that chat's input; add a comment if you like and press Send. **Can I forward a message to myself?** Yes. Your own Inbox is a forward target, shown as "Saved (Inbox)". **How do I delete several messages at once?** Drag on blank space beside the messages to select them, then click Delete in the selection bar and confirm once. Bulk delete is available when every selected message is yours, or when you are the host. **Does a forwarded message keep its reactions and edit history?** No. Text, images and files travel; reactions, pins and edit history do not. Transcripts cannot be forwarded. **Can I read old messages while typing a reply?** Yes. PageUp and PageDown page the history even while you type; Home and End jump to the oldest and newest message when the message box is empty. ## Try it - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Messages](https://intermind.com/docs/chat/messages)** — forwarding, selection, editing, replies, pins. - **[Keyboard shortcuts](https://intermind.com/docs/settings/keyboard-shortcuts)** — global, in-meeting and in-chat keys. *Sources: [Slack Help Center — Forward messages in Slack](https://slack.com/help/articles/203274767-Forward-messages-in-Slack){rel=""nofollow""}, [Microsoft Support — Forward messages in Microsoft Teams](https://support.microsoft.com/en-us/office/forward-messages-in-microsoft-teams-b3190ce7-00da-45aa-978d-a45a7b041d21){rel=""nofollow""}. Vendors change their apps and documentation over time; check their pages for the current state. All facts checked September 2026.* # How to get a copy of every meeting recap in your CRM or help desk by email — no integration, one confirmed address (2026) - **No integration needed.** Add the CRM's inbound address as a recap copy recipient, confirm it once by test email, and every recap arrives there as a hidden BCC. - **The copy is the summary, not the room.** One text in the host's language; the recap and transcript links require signing in as a member. - **InterMIND keeps the whole meeting in each member's language,** and the linked recap page reads in each participant's own. Guests join free by link, no account; you pay only for active members. The recap is only useful where the next person will look for it. If you searched "send meeting notes to my CRM automatically", the short answer for InterMIND needs no integration at all: the host adds the CRM's inbound address as a **recap copy** recipient on the meeting or channel, confirms it once, and every recap of that room is sent there as a hidden BCC. This guide is the rest: where the field is, how the confirmation works, what the copy contains, who can open the links inside it, and when the email route stops being enough. ## Set it up The host of a meeting or channel adds the address in one of two places: - **Meetings page** — expand the meeting's row and fill the **Recap copy:** field. - **Channel chat** — the display-settings menu (the gear icon) → **Recap copy**. Type the inbound address of the tool — a Pipedrive Smart BCC address, a HubSpot forwarding address, a Zendesk support address, a tracker's mail-in address. A confirmed address is saved to your personal address book, up to ten, and can be reused across your meetings and channels; addresses can apply to all your meetings or to one channel or meeting. ## Confirm it once A new address must confirm delivery before any copy is sent. InterMIND sends a **test email** shaped like a real recap; someone opens it inside the receiving tool and clicks its confirmation link within **one hour**. Until then the address is marked pending and no copies go out. If the window passes, pick the address again in the field for a fresh test. If the test email does not arrive, allow `noreply@intermind.com` as a sender in the receiving tool. The confirmation is the whole security model of the route: a recap is never mailed to an address nobody has proven they control. ## What the copy contains The copy is the same email the participants get: the summary text, plus links to the full recap and the transcript. The summary in the email is one text in one language — the host's summary language; the recap page linked from it is where each signed-in participant reads the summary in their own language. The links inside the copy still require signing in as a member of the meeting. So the note in the CRM carries the summary in full, and the transcript and recording behind it stay members-only — a colleague who was not in the meeting reads the note, not the room. ## Every session, every recap The copy is sent for every session of the room. A channel keeps the recap of every past session; an ad-hoc meeting keeps its latest one. Whichever it is, each session's recap goes to the address the moment it exists, and the recap message in the chat updates its title if a member edits the summary afterwards — the copy already sent is the version at send time. Available on every plan. ## When email stops being enough The email route puts the summary where the people are. When the *system* needs it — a field on the deal rather than a note, a ticket comment created from a template, a row in a sheet — the same recap is available as a Zapier trigger, a signed webhook and an API with an OpenAPI contract. The [guide to Zapier, the webhook and the API](https://intermind.com/blog/how-to-send-meeting-recaps-to-your-crm-with-zapier-or-the-api) covers those three; the [recap documentation](https://intermind.com/docs/meetings/recap) covers everything the recap itself is. ## FAQ **How do I get meeting notes into my CRM automatically?** Add the CRM's inbound email address as a recap copy recipient on the meeting or channel — Meetings page, expand the row, Recap copy — and confirm it through the test email. Every recap of that room is then sent there. **Do I need Zapier or an API key for this?** No. The recap copy is a hidden BCC to an address you confirm once. Zapier, the webhook and the API exist for the cases where the tool needs structured fields rather than an email. **Why does the address have to be confirmed?** So that a recap is never mailed to an address nobody controls. The test email is shaped like a real recap; someone clicks its confirmation link inside the receiving tool within an hour. **Can the CRM open the transcript from the copy?** The copy carries the summary in full; the links to the recap page and the transcript require signing in as a member of the meeting. **How many addresses can I keep?** Up to ten confirmed addresses in your personal address book, reusable across your meetings and channels. ## Try it - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Meeting recap](https://intermind.com/docs/meetings/recap)** — where the recap lives, who can open it, the recap copy. - **[How to send meeting recaps to your CRM with Zapier, a webhook or the API](https://intermind.com/blog/how-to-send-meeting-recaps-to-your-crm-with-zapier-or-the-api)** — when the tool needs fields, not an email. # How to get a summary of every document shared in a team chat — automatically, in your language, with links to the source (2026) - **It is already summarized.** A few moments after a file lands in the chat, its card offers an AI summary: bullets, each with a ¶ link to the source paragraph. - **The extracted text is never translated.** The summary is translated for each reader; the source stays in the author's words. Scanned, password-protected and linked documents get no summary. - **InterMIND keeps the whole space in each member's language,** files and the recap included: document summaries feed the meeting recap. You pay only for active members. A forty-page PDF lands in the channel at 17:40. If you searched "summarize a document in a team chat" the short answer for InterMIND is: it is already summarized. A few moments after the file lands, its card offers an **AI summary** — the key points as bullets, each linked to the paragraph it came from — and every member of the channel reads it in their own language. This guide is the rest: how to read a summary and check it against the source, which files are covered, what the card says when there is nothing to summarize, where the text is processed, and how the summaries end up in the meeting recap. Summaries are included on every plan, at no cost and with no quota. ## Read the summary, check the source Each file card in a chat carries a status strip with two links: **AI summary** and **Preview**. Clicking the card body opens the document, like in any messenger; **AI summary** opens the summary in a resizable window with two tabs: - **Summary** — the key points as bullets. Each bullet ends with a **¶ link**; click it and you land on the exact source paragraph, so every claim can be checked against the document. - **Extracted text** — the document's full text as it was read from the file. While the summary is being prepared, the strip says **Preparing summary…** and flips on its own when it is ready. The **Open document** button in the header opens the original file in the built-in preview — translated into your language if the file is in another one. ## Your language, the author's words The summary is written in the document's own language first, then translated for each reader: you see it in your language — the same one your meeting translation uses — and if your translation is not ready yet, the original appears first and is replaced a few seconds later. The **extracted text is never translated**: it stays the document's source of truth, so the ¶ links always land on the author's exact words. ## Which files | Family | Extensions | | ----------------------- | -------------------------- | | Word and text documents | DOC, DOCX, DOCM, ODT, RTF | | PDF | PDF with a text layer | | Presentations | PPT, PPTX, PPSX, PPTM, ODP | | Spreadsheets | XLS, XLSX, XLSM, ODS, CSV | | Plain text | TXT, MD, Markdown | | E-books | EPUB | A very large document is summarized from the beginning of its text; the **Extracted text** tab notes when the text was truncated. Files shared before the feature launched are not summarized retroactively. ## When there is no summary, the card says why | The card says | What it means | | -------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | | Scanned document | The pages are images — no text layer to read; OCR is not performed yet | | This file has no readable text | The file opened but contained no extractable text | | Password-protected file | Encrypted documents are not opened | | File is too large for text extraction | Over the extraction size ceiling | | Text extraction isn't supported for this file type | A format outside the table above | | No summarizable content found | Text was extracted but held no substance; the Extracted text link still opens it | | Sent from mobile / Sent via Telegram | Files arriving from the mobile app or Telegram are not extracted yet | | Linked document | A Google Drive or OneDrive link shares a pointer, not the file — the content stays with its provider | | Summary generation failed | Retried and gave up; the extracted text remains available | ## Where the text is processed, and who can read it Text extraction runs **in your browser** — the file's text is read on your machine, not mailed to a third party for parsing. The summary is written by EU-hosted AI models with zero data retention. Extracted text and summaries are stored on InterMIND's servers only, never in public file storage, and are readable **only by members** of the meeting or channel. The [document summaries documentation](https://intermind.com/docs/chat/document-summaries) has the full statement. ## Into the meeting recap Document summaries feed the [meeting recap](https://intermind.com/blog/meeting-recap): when a recap is written, the documents shared during the session contribute their summaries alongside what was said — and a session with no speech but with shared documents still produces a recap. What was in the deck is in the record, in each member's language. ## FAQ **Do I have to click anything to get a document summarized?** No. Every document shared in a channel or meeting chat is summarized on its own; the card shows Preparing summary… and then AI summary. **Can I trust the summary?** Check it: every bullet ends with a ¶ link to the exact paragraph it came from, and the Extracted text tab holds the document's full text in the author's own words. **Will my colleagues see the summary in their language?** Yes. The summary is translated for each reader into their own language; the extracted text stays in the document's language so the links always land on the source. **Which files are not summarized?** Scanned PDFs without a text layer, password-protected files, files over the extraction size ceiling, formats outside the supported list, files arriving from the mobile app or Telegram, and linked Google Drive or OneDrive documents. The card names the reason. **Where does the document go?** The text is extracted in your browser; the summary is written by EU-hosted AI with zero data retention; text and summaries are stored on InterMIND's servers and readable only by members of the meeting or channel. ## Try it - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Document summaries](https://intermind.com/docs/chat/document-summaries)** — formats, statuses, privacy. - **[How to share a file into your team chat from any app](https://intermind.com/blog/how-to-share-a-file-into-your-team-chat-from-any-app)** — the share sheet, the Mac's Share menu, the Inbox. # How to hand over a meeting or a channel to another host — mid-call or when someone leaves the company (2026) - **Make host, one click.** In the member drawer, pick the colleague and confirm; the room, its link, chat and recaps stay where they are, even mid-call. - **Same team, paid plan.** The host is the account the room bills to, so only a licensed member of the same team can take over; a team admin can do it for a leaver. - **InterMIND keeps the whole meeting in each member's language,** whoever hosts it. Guests join free by link, no account; you pay only for active members. The weekly customer call was created by someone who is on leave; the channel with the partner belongs to an account that is being offboarded. If you searched "change the meeting host" or "transfer a channel to another owner", the short answer for InterMIND is **Make host** in the member drawer: the room, its link, its chat and its recaps stay exactly where they are, and a colleague becomes the host — in one click, even in the middle of a call. This guide is the rest: who can hand over to whom, the one rule behind it, what changes for the participants, and where it is recorded. ## What the host is The host of a meeting or channel is three things at once: the person the room **bills to** — translation minutes, storage and every other allowance of the room count against the host's plan; the person with the **host controls** — admitting guests, muting participants, setting participant permissions, ending the meeting for all; and the person who **manages the members** of a channel. Handing over the room hands over all three. ## Hand over a meeting or a channel 1. **Open the member drawer.** Click the participant avatars in the chat header, or right-click the channel in the sidebar → **Manage group**. 2. **Pick the colleague** and choose **Make host**. 3. **Confirm.** The dialog says what changes: they will manage members and settings from now on; the current host becomes a regular participant; limits and translation minutes stay with your team's plan. Everyone in the room sees "*name* is now the host". Nothing else moves: the link is the same, the chat and the recaps stay with the room, the participants stay members. ## Mid-call A hand-over during a live meeting takes effect on the spot. The new host becomes the meeting's moderator immediately — the host controls flip to them — and the previous host stays in the call as a presenter. Billing and limits already resolve per request from the new host, and because the new host bills to the same account, nothing shifts for the room. ## The one rule: same team, paid plan The host is the room's billing sponsor, so the room can only be handed to someone who bills to the same account. The gate, in the order the dialog checks it: | The hand-over is refused when… | The message | | --------------------------------------------------------------------------- | ----------------------------------------------------- | | The chat is the team-wide chat or an Inbox | "This chat cannot change its host" | | The person handing over is neither the host nor an admin of the host's team | "Only the host or a team admin can change the host" | | The colleague is already the host | "They are already the host" | | The colleague is not a member of this meeting | "They must be a member of this meeting first" | | The host's plan is Basic | "Changing the host is available on paid plans" | | The colleague is not a licensed member of the same team | "The new host must be a licensed member of your team" | So the path for offboarding is: the leaver's rooms are handed to a licensed colleague by the leaver, or by a **team admin** on their behalf — the admin does not need to be a participant to do it, only an admin of the host's team. ## Where it is recorded Every hand-over is written to the team's **audit log** as a host transfer — who did it, from whom, to whom, for which room — next to the other membership events. The [audit log documentation](https://intermind.com/docs/users/audit-log) describes what the log keeps and who can read it. ## FAQ **Can I change the host of a meeting during the call?** Yes. Open the member drawer, pick the colleague and choose Make host. They become the moderator on the spot; the previous host stays in the call as a participant. **Who can hand over a room?** The host, or an admin of the host's team — for example to reassign the rooms of someone who has left the company. **Can I make a guest or an outside participant the host?** No. The new host must be a licensed member of the same team, because the host is the account the room bills to. The current host's plan must be a paid one. **What happens to the recaps and the chat history?** Nothing. The room keeps its link, its chat and every recap; only the host changes. **Does the previous host lose access?** No. They become a regular participant of the room and keep reading it like any other member. ## Try it - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Channels and members](https://intermind.com/docs/chat/channels)** — the member drawer, invites, archiving. - **[Team audit log](https://intermind.com/docs/users/audit-log)** — what the log records. - **[How to add an external client to a team chat channel](https://intermind.com/blog/how-to-add-an-external-client-to-a-team-chat-channel)** — membership from the other side. # How to improve team productivity: fewer meetings, written status, and a history every office can read (2026) - **Team productivity improves when attention stops leaking.** Keep the meetings that decide, move status into writing by a set time, and keep one history the whole team reads. - **The writing has to land somewhere.** In Teams, Zoom, Google Workspace and Slack a meeting leaves one document, in the room's language. - **InterMIND keeps the whole channel in each member's language,** status, chat and every recap, next to Teams or Slack rather than instead of them. Guests join free by link, no account; you pay only for active members. Team productivity is what a team finishes per week of its attention. Not hours logged, not messages sent, not meetings attended: the things that reached done, divided by the attention it took to get them there. A team of ten to two hundred that finishes less than it plans is rarely short of motivation or tools. It is short of attention — the week is spent in meetings that decide nothing, in status that is asked for five times and written down nowhere, and in looking for what was agreed three weeks ago. This guide is the craft first: what team productivity is and how to measure it without a dashboard, the three levers that move it — fewer meetings, written status, one readable history — and the arithmetic behind each. Then the mechanics: a weekly status template you can copy, a 30-day plan, where the written status and the record of a meeting live in the tools your team already uses, and one way the job gets done when the team sits in more than one office and reads in more than one language. ## What team productivity is — and what it isn't The word gets measured in three different ways, and only one of them is useful to a lead: | | What it counts | What it tells you | Example | | ---------------------------- | --------------------------------------------------- | ---------------------------------------------------- | ------------------------------ | | **Activity** | Hours, messages, meetings attended, tickets touched | How busy people are | 34 hours in meetings this week | | **Output** | Things finished and in someone's hands | Whether the team ships | 6 of 8 planned items done | | **Throughput per attention** | Output divided by the attention it took | Whether the team ships *for the attention it spends* | 6 items for 320 person-hours | Activity is the easiest to measure and the most misleading: a team can be fully booked and finish nothing. Output is the honest number. Throughput per attention is the one that tells you *where to intervene*, because it falls in two ways — fewer things finished, or the same things finished for more attention — and the second is where meetings and status requests hide. Team productivity is also not individual productivity summed. A team of eight where each person is efficient and nobody knows what the others decided finishes less than a team where three people are slow and everyone can read the plan. The levers below are all about the team's shared attention: what interrupts it, what it has to reconstruct, and what it has to ask for. ## How to measure it without a dashboard Three numbers, written down once a week by the lead, are enough to see whether a change worked. None of them needs a tool. 1. **Finished this week.** The count of items that reached done — shipped, sent, signed, closed. Against the count planned on Monday. A team that plans eight and finishes six is at 75%; the number itself matters less than its direction over a month. 2. **Hours in recurring meetings per person.** Headcount times length times frequency, from the calendar. For most team members two to four hours a week is a workable range; above six, the meetings are doing the work's job. The [meeting cadence](https://intermind.com/blog/meeting-cadence) guide has the arithmetic per meeting. 3. **Questions that were already answered.** Count, for one week, the times somebody asked in chat or in a meeting for something that was decided or reported earlier: "what did we agree on pricing", "is the export done", "who owns the client's reply". Each one is a reconstruction — attention spent re-creating a record that should have existed. Ten in a week for a team of ten is normal; thirty means there is no history anyone reads. The first number is the output. The second and third are the two biggest leaks of attention in a team that works mostly in meetings, and they point at the three levers in order. ## Lever 1: fewer meetings — the test for each one A meeting costs everyone's attention at the same time, which is why it is the most expensive way a team has to communicate and the right one for exactly one thing: a decision that needs several people's judgement in the same minute. Everything else a meeting is used for — reporting, informing, collecting input — is cheaper in writing. Run every recurring meeting through one test: **what does it leave behind?** Take the last recap, or the memory of the last occurrence, and sort each item it covered: | What the item was | What it leaves behind | Verdict | | --------------------------------------------------------- | ---------------------------------------------------- | ------------------------------------------------------------------------------ | | **A decision** several people had to make together | A sentence that starts "we agreed", with an owner | Keep the meeting; this is what it is for | | **Information** one person told the others | The same text, read by each person at their own time | Move it to a written update; the meeting gets shorter | | **A status round** — each person says where their work is | A list that was true for an hour | Move it to a written status by a set time; keep a short live call for blockers | | **A discussion** where input was collected | Opinions, spoken once, written by nobody | Collect the input in writing first; meet for what the writing could not settle | A weekly team meeting that is forty minutes of status rounds and five minutes of decision is, after the test, a fifteen-minute decision meeting plus a written status. A stand-up that has become a report to the lead is a written daily by a set time plus a live call twice a week for blockers; the [stand-up meeting](https://intermind.com/blog/stand-up-meeting) guide has the asynchronous variant. A leadership meeting with nine people and two deciders is a meeting of two with a recap to seven. What stays: the decision meetings, each with an agenda where every item has an owner, a time box and the outcome it needs — the [meeting agenda template](https://intermind.com/blog/meeting-agenda-template) is built for exactly that — and the last five minutes reserved for reading every decision and action back. Fewer meetings only improves productivity if the ones that remain [are run so they end with their outcomes written down](https://intermind.com/blog/how-to-run-an-effective-meeting); a short meeting that decides nothing is a cheaper waste, not a gain. The arithmetic for a team of twelve: a 60-minute weekly cut to 25 minutes saves seven hours a week. A daily stand-up of fifteen minutes is fifteen hours a week for twelve people; a three-line written daily plus two live calls of fifteen minutes is about eleven, once the five minutes each person spends writing are counted. Eleven hours a week, for a change that costs nothing but the habit of writing. ## Lever 2: written status — one message, by a set time Status is the information a team reads most and keeps least. It is asked for in meetings, in direct messages, in the corridor; it is answered from memory, differently each time; and it is written down nowhere, so the next person asks again. A written status update replaces all of that with one message, from each person or each team, by a set time, in one place. Four rules keep a written status from becoming a report nobody reads: **One message, same shape, every time.** Shipped, not shipped and why, decisions needed, blocked, next. The reader learns the shape once and reads the update in thirty seconds. A different format every week is a document; the same format every week is a signal. **By a set time, in one place.** Friday at four, Monday at nine — the hour matters less than the fact that it is fixed and that the update is a message in the team's channel, with an author and a time, rather than a cell in a sheet or a slide. A message can be replied to under itself, searched, and read on a phone. **Finished, not worked on.** "Finished the export, it is in QA" is a status; "worked on the export" is an activity. The first is true or false next week; the second is never false and tells the reader nothing. **Decisions needed are listed, not described.** One line each: the question, the options, who decides, by when. This is the part of the status that creates the next meeting's agenda — or removes the need for one, when the decider answers in the thread. ### A weekly written status template > **\[Team] — week of \[date]** · posted by \[name] · by \[day, time] :br**Shipped:** \[what is done and in whose hands — one line each] :br**Not shipped, and why:** \[what slipped — the reason — the new date] :br**Decisions needed:** \[question — options — who decides — by when] :br**Blocked:** \[what — by whom or what — since when] :br**Next week:** \[the two or three things that will be finished, with a name each] :br**Numbers:** \[the two or three the team watches, with last week's beside them] The block is plain text; it pastes into a chat message, a canvas or an email without reformatting. For a team across offices, each person writes it in their own language and the channel does the rest — the mechanics are in the last section. ### The daily variant For work that changes by the day — support, delivery, a release week — the same shape shrinks to three lines per person by a set hour: finished since yesterday, will finish by tomorrow, blocked by. Spoken works as well as typed: a one-minute voice note from the road, transcribed into the channel, is often more honest than a sentence composed at a desk. The rules that keep an asynchronous daily from becoming a report are in the [stand-up guide](https://intermind.com/blog/stand-up-meeting); the short version is one message per person, a thread per blocker, and a live call on a fixed cadence for what a thread could not clear. ## Lever 3: one history every office can read The third leak is the quietest. A team finishes something, decides something, promises something — and three weeks later nobody can find it. The decision is in one person's notes, the task in another's inbox, the recap of the call in the organizer's mailbox. So the team asks the room, and the room reconstructs from memory, and the reconstruction is different from what was agreed. For a team in one office this costs a few hours a week. For a team in two or three offices, each with its own working language, it costs more: the record, where it exists, is in the language of whoever typed it. A history that improves productivity has three properties: 1. **One place.** The decisions, the status updates and the recaps of the team's meetings are in the same channel, in date order, searchable — not spread across a calendar, a drive, a notebook and five inboxes. A new member reads the channel from the top and knows the plan on day one. 2. **Written at the moment, not afterwards.** The decision is read back in the last five minutes of the meeting and lands in the recap the same day; the status is posted by its set time. A record written a week later from memory is a second reconstruction. 3. **Readable by everyone it concerns.** The office that did not sit in the meeting reads the same recap as the one that did; the member who was on leave reads the month's status updates on their return. Readable means in a language the reader works in, on a phone, without asking anyone. The [decision log template](https://intermind.com/blog/decision-log-template) covers the decisions; the [action items](https://intermind.com/blog/action-items) guide covers the tasks and how the recap keeps the list. The rest of this guide is about where all three live. ## A 30-day plan to improve team productivity Four weeks, one change a week, each measured by the three numbers above. **Week 1 — measure.** Write down finished-versus-planned, hours in recurring meetings per person, and the count of already-answered questions. Do not change anything yet; a baseline is what makes week four a result rather than a feeling. **Week 2 — cut the meetings.** Run every recurring meeting through the test. Shorten the ones that stay to their decision items; move the information and status items to writing; cancel the ones with nothing left. Announce the new cadence in the channel in one message, with the reason next to each change. **Week 3 — start the written status.** Post the template, set the day and hour, and post the first update yourself. The lead's own update on time, in the shape, does more than any instruction. Reply in the thread to every "decisions needed" line within a day — a written status that gets no answer stops being written. **Week 4 — put the history in one place.** Choose the channel where decisions, status and recaps will live from now on; move the recurring meetings into it; agree that a decision not written there was not made. Then write the three numbers down again and compare. What to expect: meeting hours fall first, because that change is arithmetic on the calendar; repeated questions fall as the history fills; finished-versus-planned moves more slowly, because it depends on the work, but it moves in the same direction once attention is no longer spent reconstructing. ## Where the status and the meeting record live in the tools you already use A written status needs a place with an author, a time and a thread; a meeting needs a record that reaches the people who were not in it. Each major platform offers both, and each stops at a different point. Documented behaviour only, from the vendors' own pages; each cell names the month its fact was checked, and the pages are in the *Sources* footer. | Platform | Where a written status lives | What a meeting leaves behind | Who can read it later, and in which language | | -------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | *Notes* in the meeting controls, or *Add an agenda* in the meeting's Details — a Loop component that any attendee or organizer can edit, with tasks assigned by tagging people (checked October 2026) | A recap — recording, transcript, shared files, notes, agenda and follow-up tasks — after meetings that were recorded or transcribed; the AI summary and notes require Teams Premium or a Microsoft 365 Copilot license; "not currently available for ad-hoc events" (checked August 2026) | The notes are saved automatically and reachable from the Teams calendar and the recap; external attendees cannot access or edit them (checked October 2026). The recap is generated in the language the meeting was held in (checked August 2026) | | **Zoom Workplace** | The meeting summary can be posted to the meeting's group chat in Team Chat (checked August 2026) | A meeting summary with AI Companion — quick recap, summary, next steps — on paid Zoom Workplace plans, sent by email and listed on the Summaries page (checked August 2026) | Participants receive it when the host chose to share it; only the host can edit it; unauthenticated users do not receive the email. The documentation does not state that a summary can be produced in a different language per participant (checked August 2026) | | **Google Workspace** | The Calendar event's description; on eligible Workspace editions and Google AI plans, *Take notes for me* is switched on in Calendar when the event is created (checked October 2026) | A Google Doc with summary, decisions and next steps, when *Take notes for me* was on (checked October 2026) | The Doc is emailed to the organizer and attached to the event, shared with all guests, organization guests or hosts only, per the setting; "this feature supports one language at a time" (checked October 2026) | | **Slack** | Messages in the team channel; a huddle has "a dedicated message thread to share notes, links, and files" (checked October 2026) | A canvas from the meeting-agenda template, with sections for objectives, time allocations, next steps and action items with due dates (checked October 2026) | The canvas stays in the channel; what was said in the huddle is not in it unless someone types it (checked October 2026) | The written status itself needs only a chat where a message has an author and a time, and the table does not compare the four on that. What a meeting leaves behind is the same across them: one document or one summary, in the language it was written or held in, for the people the host or an admin chose; none of the pages cited states that a reader gets it in a language of their own. For a team in one office, in one language, the table is the whole answer. The next section is one way the job gets done where it is not. ## How status, tasks and the history live in a channel InterMIND is a communication space where a team's recurring meetings live in a channel, so the three levers have one home. The written status is a message in the channel, by its set time; the decision meeting is the channel's meeting, with a permanent link and a recurrence set once in Google Calendar or Outlook; and the history is the channel itself. The whole of it stays **in each member's language**: the chat is translated per reader — the Milan office types in Italian, the Bucharest office reads it in Romanian and answers in Romanian, and each side has the original one toggle away. A status update from the road is a voice note from the phone, up to ten minutes, transcribed within seconds and read by each teammate as text in their own language. An update from someone who lives in a system that only sends email — a field team, a ticketing tool, a client — lands in the channel by email: every channel has its own address, the sender is named, attachments are kept. During the decision meeting, the week's status or the agenda goes on everyone's screen next to the video tiles with **Share to conference**: the sharer edits it live while the room watches, and every participant reads it in their own language. When the call ends, the recap is written from the meeting itself — a summary and the action items with owners — and arrives by email to each signed-in member, as a message in the channel and as a link in the calendar event, each member reading it in their own language rather than the one the room happened to use. Any member can edit it; every edit keeps author and revision history. The channel keeps the recap of every past session, not only the latest, so the decision of three weeks ago is a search in the channel rather than a question to the room. An ad-hoc meeting by link keeps only its latest recap, and its chat is wiped when the call ends; a team's history belongs in a channel. The tasks get the same treatment as the decisions. In an organization with team status pages on, the open tasks its meetings recorded are read back when the next recap of a channel's meeting is written and judged against what was said: an item someone reported finished is marked done, an item discussed but not finished is marked not done with the reason in the words of the meeting, and an item nobody brought up stays open — and at the start of the next session Mia names the open items and their owners, so last week's list is the first thing spoken about. The same pages collect the tasks, problems and requests the organization's meetings stated, each row with the verbatim quote from the recap it rests on, so the written status and the spoken decisions end up in one list rather than two. The recap does not have to stay in the channel. The host can add a recap copy to any address — a CRM or a tracker inbound mailbox, up to ten saved addresses, on every plan — and every recap of that meeting or channel also goes there, so the outcomes reach the system of record without anyone forwarding anything. Teams that want the recap on the deal or the ticket itself use the [Zapier trigger, the webhook or the API](https://intermind.com/blog/how-to-send-meeting-recaps-to-your-crm-with-zapier-or-the-api). A channel is members-only. A colleague in the other office, a contractor or a client who belongs in the team's history is added by email invitation onto a free account and reads the channel in their language from then on. Someone who needs one meeting only — a supplier for one review, a candidate for one call — joins an ad-hoc meeting by link, from a phone, without an account and at no cost, hears the meeting live in their own language and gets nothing afterwards: the account is free, and it is what makes the record reachable. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing) — joined a meeting, wrote in a chat, asked Mia. A member on leave for a month keeps access and costs nothing that month; the status updates they come back to are in the channel, in their language. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. The craft survives every tool: somebody still has to decide which meetings earn their hour, write the status by the set time, and read the decisions back before the room empties. What does not have to survive is the second job — reconstructing the record afterwards, by hand, in one language, for people who read others. ## FAQ **How can team productivity be improved?** By reducing what leaks the team's shared attention rather than by asking people to work harder. Three changes do most of it: keep only the meetings that make a decision and move information and status rounds into writing; have each person or team post one written status update in a fixed shape by a set time; and keep decisions, status and meeting recaps in one place the whole team can read later. Measure finished-versus-planned, hours in recurring meetings and repeated questions before and after. **What are the factors that affect team productivity?** The ones a lead can change in a month: how much of the week is spent in meetings that decide nothing; whether status is written once or asked for repeatedly; whether decisions and tasks are findable three weeks later; whether the people who need the record can read it in a language they work in; and whether the work planned for the week is small enough to finish. Skills, tools and motivation matter too, but they move slowly; attention leaks move in weeks. **How do you measure team productivity?** Count output, not activity: the items that reached done this week against the items planned on Monday. Then divide by the attention it took — hours in recurring meetings per person from the calendar, and the number of questions asked in a week that had already been answered. The direction of the three numbers over a month tells you whether a change worked; a single week's value tells you little. **Do fewer meetings improve team productivity?** Fewer meetings improve it when the removed meetings were doing a job that writing does better — reporting, informing, status rounds — and the remaining meetings end with their decisions written down. Cancelling a meeting whose decisions then get made in a thread that runs to Friday moves the cost rather than removing it. The test is what each meeting leaves behind: a decision with an owner stays; a list that was true for an hour goes to writing. **What is a written status update?** One message from each person or team, in the same shape every time, posted by a set time in one place: what was finished, what was not and why, decisions needed, what is blocked, and what will be finished next. It replaces the status round in meetings and the status question in direct messages, and because it is a message with an author and a time, it can be replied to under itself, searched later and read on a phone. **How often should a team send a status update?** Weekly for most teams, on a fixed day and hour; daily, in three lines per person, for work that changes by the day — support, delivery, a release week. The interval matters less than the fixed time and the fixed shape. A monthly update is a report, not a status: by the time it is read, the decisions it asks for are overdue. **How do you improve the productivity of a remote or distributed team?** The same three levers, with more weight on the second and third. A team across time zones cannot be in the same meeting at the same hour every day, so written status by a set time replaces the daily round, with a live call on a fixed cadence for blockers. A team across offices with different working languages needs the history in a place where each member reads it in their own language, or the office that did not sit in the meeting reconstructs the decision from a second-language document. The rules a distributed team agrees on — core hours, response times, which channel is for what — belong in a written [remote work policy](https://intermind.com/blog/remote-work-policy) that lives where the team reads. --- *Sources: [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Use huddles in Slack](https://slack.com/help/articles/4402059015315-Use-huddles-in-Slack){rel=""nofollow""}; [Slack — Meeting agenda template](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Each table cell names the month its fact was checked — the Teams recap page and the Zoom meeting-summary page checked August 2026, the rest checked October 2026. Vendors change plans, features and language lists over time; check their pages for the current state.* # How to join a video meeting from your computer: the link, camera and mic, your language — with or without an account (2026) - **Click the link, check camera and mic, join.** Chrome, Edge or Firefox, nothing to install; without an account you type your name and the host admits you. - **Pick your language in More.** You hear everyone in your language, in their own voice, subtitles one click away. The recap and history afterwards need a free account. - **InterMIND keeps the whole meeting in each member's language,** voice, chat and the recap. Guests join free by link, no account; you pay only for active members. If you searched "how to join a video meeting" with an InterMIND link in your inbox, the short answer is: click the link, check your camera and microphone on the pre-join screen, click **Join**. It works in the browser — Chrome, Edge or Firefox — with nothing to install, and you do not need an account: without one you type your name and join as a guest, and the host lets you in. This guide is the full version: the three steps, the one setting that matters, what a guest gets and what needs an account, the troubleshooting table, and — quoted from Google's and Microsoft's help pages, checked September 2026 — how Meet and Teams admit a participant without an account. ## A word on sound first A headset or earbuds with a microphone make you easier to hear — and easier to translate, because the room's translation works from what your microphone picks up. Laptop speakers and the built-in microphone work; they are just not the best. ## Join in three steps 1. **Click the link.** It looks like `https://intermind.com/abc-def-hij`. - **Signed in:** you land on the pre-join screen. - **Not signed in:** you land on the **Join Meeting** screen. Type your display name — and, if you like, pick a translation language (it defaults to your interface language) — and click **Join**. 2. **Pre-join.** Preview your camera, pick the microphone and the speakers, and start muted if you want. This screen shows the first time you join on a device and again whenever your camera, microphone or speaker setup has changed since; after that, later joins go straight into the meeting. 3. **Click Join.** Signed in, you are in the room. As a guest, a request goes to the host and you wait in the waiting room until they click **Admit**. Have a meeting ID instead of a link? On the **Meetings** page, click **Join Meeting**, paste the ID or the full URL, and continue from step 2. ## The setting that matters: your language In the meeting, open **More**, choose your translation language and enable translation. From then on you hear everyone in your language — in the speaker's own voice — and subtitles are one more click. Then you just talk, in your language; the others hear you in theirs. A guest can set the language on the Join Meeting screen before entering; a signed-in member's choice is remembered. ## With an account or without one A guest — a participant without an InterMIND account — gets the meeting itself: video and audio, live translation, subtitles, the in-meeting chat, reactions and hand raise. A temporary anonymous account is created for the session and cleaned up afterwards, and nothing is installed. What a guest does not get is everything that lives outside the single meeting: | | Signed-in member | Guest | | ---------------------------------------------- | ------------------------------------------- | --------------------------------- | | Join an ad-hoc meeting | Yes | Yes, once the host admits you | | Join a team channel's meeting | Yes | No — channels need a team account | | Live translation and subtitles | Yes | Yes | | Chat | In the meeting and in the channel's history | In the meeting only | | The recap and the meeting's history afterwards | Yes, in your language | No | | Create meetings, manage settings | Yes | No | The account is free, and it is what makes the part after the call reachable: the recap in your language, the channel's history, the next session of the same room. ## The host's side, and the five-minute rule When a guest asks to join, the host sees a notification — "*name* wants to join" — with **Admit** and **Deny**. Both sides see the result instantly. The host has to be in the meeting to admit anyone, and a request that gets no answer within five minutes is declined automatically; the guest can ask again. Several guests can knock at once; the host sees all pending requests. Members of the team that owns a channel join that channel's meeting directly, with no approval step — the channel's membership is the guest list. How a call is started from a channel is in the [guide to starting a call from a team chat](https://intermind.com/blog/how-to-start-a-call-from-a-team-chat). ## Troubleshooting | Issue | What to do | | -------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | | "Meeting not found" | Check the meeting ID or link | | Camera or microphone not working | Grant the browser permission for camera and microphone; the pre-join screen shows what it can see | | Stuck in the waiting room | The host has not approved the request yet — wait, or contact them; after five minutes the request expires and you can knock again | | "Access denied" | The host denied the request, or the link is a team channel's room and you are not a member of that team | Before a meeting that matters, the [test room](https://intermind.com/browser-test) checks your camera, microphone, speakers, screen sharing and connection on a meeting-shaped page with nobody in it — no account and no link needed. ## How Google Meet and Microsoft Teams admit a participant without an account Two documented maps, quoted, with the check date. Nothing here is an evaluation. | | Google Meet | Microsoft Teams | InterMIND | | ----------------------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------- | | Join without an account | "You can join a meeting without a Google Account, but the organizer or a participant needs to let you in" | "Join a meeting without an account": open the invite, "Continue on this browser" or "Join on the Teams app", "Join now" | Type a name on the Join Meeting screen; the host admits you | | Browser for a guest | Not stated on the joining page | "You can join Teams for web on Microsoft Edge or Google Chrome" | Chrome, Edge, Firefox | | The wait | Provide your name, "Click Ask to join"; a participant lets you in | "Wait for someone in the meeting to admit you. If no one admits you within 30 minutes, you'll be removed from the lobby" | Waiting room; a request unanswered for five minutes is declined and can be repeated | | How a guest is labelled | Not stated on the joining page | "Unverified" without an email, "Email verified" with a code, "External" with a Microsoft account | Guest | | What a guest gets | Not stated on the joining page | "People who are signed in will have access to more meeting features than those who aren't signed in" | The whole meeting, including translation and subtitles; the recap and history need an account | The rows are drawn from the two help pages listed in the footer. "Not stated" means the page did not state it at check time, not that the product lacks it. ## FAQ **Do I need an account to join an InterMIND meeting?** No. Click the link, type your name and join as a guest; the host admits you. An account is needed for team channels and for what comes after the call — the recap and the meeting's history in your language. **Do I need to install anything?** No. Joining works in the browser — Chrome, Edge or Firefox. The desktop and mobile apps are optional. **How do I hear the meeting in my language?** Open **More** in the meeting, choose your translation language and enable translation. You hear everyone in your language, in their own voice; subtitles are one more click. A guest can also pick the language on the Join Meeting screen. **Why am I waiting for approval?** Guests enter an ad-hoc meeting when the host clicks **Admit**. The host must be in the meeting; a request unanswered for five minutes is declined automatically, and you can ask again. **Can I test my camera and microphone before the meeting?** Yes. The pre-join screen previews your camera and lets you pick the microphone and speakers, and the test room at intermind.com/browser-test checks devices and connection without a meeting link. ## Try it - **[How to check your network and switch devices during a video call](https://intermind.com/blog/how-to-check-network-and-devices-during-a-video-call)** — network statistics for everyone, the device submenu, the test room. - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Joining a meeting](https://intermind.com/docs/meetings/join)** — link, meeting ID, guest steps, pre-join. - **[Guest access](https://intermind.com/docs/meetings/guest-access)** — what a guest gets and what needs an account. - **[Is InterMIND free for meeting participants?](https://intermind.com/blog/free-for-participants)** — who pays for what. *Sources: [Google Meet Help — Join a video meeting](https://support.google.com/meet/answer/9303069){rel=""nofollow""}, [Microsoft Support — Join a meeting without an account in Microsoft Teams](https://support.microsoft.com/en-us/office/join-a-meeting-without-a-teams-account-c6efc38f-4e03-4e79-b28f-e65a4c039508){rel=""nofollow""}. Vendors change their apps and documentation over time; check their pages for the current state. All facts checked September 2026.* # How to present to everyone in a video meeting — and scroll your shared tab without leaving the call (2026) - **Two things a shared screen usually cannot do.** Present to everyone puts one share onto every participant's main stage at once; a shared browser tab scrolls with the wheel over your own preview. - **One permission, tab shares only.** The browser asks once to allow scrolling of shared tabs, on desktop Chrome or Edge; viewers never touch your tab. - **InterMIND keeps the whole meeting in each member's language,** and the recap outlasts the share. Guests join free by link, no account; you pay only for active members. "Can you scroll down a bit?" is the sentence a shared screen produces most often. If you searched "how to present in a video meeting so everyone sees the same thing", the short answer for InterMIND is two things: **Present to everyone** puts the share on your main stage onto everyone's main stage at once, and when you share a browser tab you scroll it with the mouse wheel over your own share preview — from inside the meeting, without switching to that tab. This guide explains both, the browser permission behind the second one, and what viewers keep. ## Present to everyone: one main stage for the room Every participant's stage is their own: each person clicks tiles to move them between the main area and the sidebar and arranges the room the way they like. As long as one thing is shared, that share is everyone's main by default. **Present to everyone** exists for the moment there is more than one — two people sharing at once, or a screen share next to a shared document, note or recap — and each participant's main area may show a different one. 1. **Put it on your main stage.** Your screen, a shared document, a recap — whatever should be in the middle of everyone's screen. 2. **Click Present to everyone.** The button sits on the share in your main area. It puts that share onto every participant's main stage at once, and a person who joins later lands on it too. 3. **Present something else the same way.** Move the next share to your main stage and click again. Participants keep their own stage afterwards — the button moves the room, it does not lock it. Any participant can present, not only the host. A recap presented this way renders the full session on stage — the summary and the transcript tabs — and a timestamp clicked in the summary opens the transcript in place, for everyone. ## Scroll your shared tab without leaving the call When you share a **browser tab**, the wheel over your own share preview scrolls the page in that tab. You stay on the meeting screen, the room watches the page move, and you never switch windows to scroll down. It works while your preview is in **Zoom to fit**; in **Original size** the wheel pans the enlarged frame locally instead. This runs on a browser capability the presenter's browser has to allow once: the first wheel shows a prompt for **"Scrolling & zooming of shared tabs"**. If the browser blocked it, you see a notice — allow it in the site permissions, then share again. Only a tab share offers it, on a desktop Chromium browser such as Chrome or Edge; sharing a window or the entire screen does not. ## What viewers keep - **Their own zoom.** Every viewer switches the share between **Zoom to fit** and **Original size** and pans the enlarged frame — without changing what anyone else sees. - **The pointer.** The laser pointer lands on the same spot on every display, whatever a viewer's zoom. - **The presenter mode you picked.** How your camera sits with the content — **Content only**, **Standout** or **Side by side** — is the presenter's choice, and everyone sees the layout you picked. - **Nothing inside your tab.** Viewers watch the page; they do not scroll it, click links or type. The tab stays yours. ## What stays after the call The presented share disappears when it stops; the recap does not. After every transcribed meeting the signed-in participants get the summary and the full transcript, each reading the summary in their own language. A moderator can also start a server recording into the team's storage. The full rules are in the [screen sharing documentation](https://intermind.com/docs/meetings/screen-sharing). ## FAQ **How do I make everyone see the same thing in a meeting?** Put it on your main stage — a share, a document, a recap — and click **Present to everyone**. It goes onto every participant's main stage at once, late joiners included. **When does the Present to everyone button appear?** When the room has more than one thing shared at the same time, so participants may be looking at different ones. With a single share there is nothing to choose — it is everyone's main already. **Can participants scroll my shared screen themselves?** No. Viewers zoom and pan their own copy of the share; the page inside your tab moves only when you scroll it. What is new is that you scroll it from the meeting screen, over your own preview, without switching to the tab. **Why doesn't the wheel scroll my tab?** Your browser blocked the capability, or the share is a window or the whole screen. Allow "Scrolling & zooming of shared tabs" in the site permissions and share the tab again; it works on desktop Chrome and Edge. **Does a late joiner see what I am presenting?** Yes. A participant who joins after you clicked Present to everyone lands on the presented share. ## Try it - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Screen sharing and recording](https://intermind.com/docs/meetings/screen-sharing)** — sharing, presenter modes, both recordings. - **[How to share your screen in a video meeting](https://intermind.com/blog/how-to-share-your-screen-in-a-video-meeting)** — the basics, the laser pointer, from a phone. *Sources: [InterMIND docs — Screen Sharing & Recording](https://intermind.com/docs/meetings/screen-sharing){rel=""nofollow""}, [MDN — CaptureController.forwardWheel (Captured Surface Control)](https://developer.mozilla.org/en-US/docs/Web/API/CaptureController/forwardWheel){rel=""nofollow""}. Browser support for scrolling a captured tab changes with releases; check the MDN page for the current state. All facts checked September 2026.* # How to run an audio-only call in a video meeting: the voice stage, one link to copy, and the recap afterwards (2026) - **Any meeting becomes one in two clicks.** Move every tile to the sidebar and the stage empties into a voice stage with shortcuts and a Copy Link button. - **Nothing else changes.** Everyone still hears each other in their own language, the chat stays open, the recap arrives afterwards. On a phone, the app keeps the call alive behind other apps. - **InterMIND keeps the whole meeting in each member's language,** with or without faces. Guests join free by link, no account; you pay only for active members. A call at a desk, a call on a walk, a call where the slides matter and the faces do not: if you searched "audio-only call" the short answer for InterMIND is that any meeting becomes one in two clicks. Move the tiles off the stage, and the stage empties into a **voice stage** — no grid, a quiet panel, the room still fully alive. This guide is the rest: how to get there and back, what the empty stage offers, what a translated audio call does that a phone call cannot, and what the phone app does for a call that has to survive other apps. ## Empty the stage Every participant's stage is their own. Clicking a video tile moves it between the main stage and the sidebar; move **every** tile to the sidebar and the stage empties. What appears instead is a getting-started panel: shortcut reminders for translation, layout, chat and devices, and a **Copy Link** button — the meeting's permanent link, ready to paste to the person who is late. To bring the tiles back, click anywhere on the background or press **Alt + L** (Option + L on a Mac): the layout resets to its defaults. Nothing else changes. Everyone still hears you; you still hear everyone, each in your own language; the chat sidebar is one key away (**Alt + H**); the microphone toggles with **Alt + M**. Your own camera can be off the whole time — start muted and with the camera off on the pre-join screen, and the room is an audio room from the first second. ## What an audio call does here that a phone call does not - **Everyone in their own language.** The room translates each voice for each listener as they speak; a two-language call is two languages, one per ear. Subtitles are one click away for the part you want to read. - **The chat is in the room.** A link, a file, a note dropped into the sidebar reaches everyone, in their language, and stays in the channel's history if the call is a channel's. - **The recap comes afterwards.** After every transcribed meeting the signed-in participants get the summary and the full transcript, each reading the summary in their own language — an audio call is transcribed like any other. - **Guests join by link.** Someone outside the team joins by the same link with a name, no account; the host admits them. ## On a phone: a call that survives other apps On a phone the audio call is what the InterMIND app is for. Its foreground service keeps the call running when you switch to another app or lock the screen, and push notifications reach you between calls. In the mobile browser a call works too; it is the app that keeps it alive in the background. The differences are in the [apps documentation](https://intermind.com/docs/getting-started/apps). ## Idle, and coming back Thirty minutes without a mouse or keyboard and InterMIND marks you as away: your microphone is muted and a notice tells you why. You are not removed — listening to a translated conversation without speaking is an ordinary way to be in a call — and any key or mouse movement clears the away state. Coming back does not unmute you; you unmute when you choose to speak. ## FAQ **Can I use InterMIND for an audio-only call?** Yes. Join with the camera off, move the tiles to the sidebar, and the stage empties into a voice stage. Everything else — translation for each listener, chat, the recap — works as in any meeting. **How do I get the video grid back?** Click anywhere on the background of the empty stage, or press Alt + L (Option + L on a Mac). **Do the others need to speak my language?** No. Each participant hears the others in their own language, in the speaker's own voice, and subtitles are one click away. **Does an audio call get a recap?** Yes. After every transcribed meeting the signed-in participants get the summary and the full transcript, each reading the summary in their own language. **Will the call drop if I switch apps on my phone?** Not in the InterMIND app: its foreground service keeps the call running in the background and when the screen locks. ## Try it - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Meeting controls](https://intermind.com/docs/meetings/controls)** — the stage, the shortcuts, and every other control. - **[How to start a call from a team chat](https://intermind.com/blog/how-to-start-a-call-from-a-team-chat)** — one click from the channel, the chat stays with you. # How to run an effective meeting: before, during, after — and the channel that keeps what was decided (2026) - **An effective meeting ends with its outcomes written down.** One purpose sentence, a list run in time boxes, a close that reads every decision and owner back. - **Most of the work is outside the call.** The agenda the day before and the recap the same day are what people use later. - **InterMIND keeps the whole meeting in each member's language,** agenda, chat and recap, next to Teams, Zoom or Meet rather than instead of them. Guests join free by link, no account; you pay only for active members. An effective meeting is one that produces what it was called for — a decision, a plan, a shared piece of information — and leaves that result where the people who need it will find it. Everything else about running meetings well follows from that sentence: the purpose has to be known before the call, the call has to be run so the purpose is reached inside the time, and the result has to be written down before the room empties. This guide is in three parts, because a meeting is. **Before** is where most of the result is decided; **during** is a short stretch of facilitation that is easier than it looks once the list exists; **after** is the recap, and the five minutes at the end of the call that write it. Then the mechanics: a running sheet to copy, where the record of a meeting lives in the tools your team already uses, and how a meeting that runs in a channel keeps what was decided. ## What makes a meeting effective — three tests A meeting passed if it survives three questions, asked a week later: 1. **Did it produce what it was called for?** The purpose sentence from the invitation, compared with the recap. "Discuss the roadmap" cannot fail this test, which is why it is not a purpose. "Decide which two features ship in November" can. 2. **Could everyone who had to act find out what to do without having been there?** Each action with a name and a date, each decision in a sentence, readable by the person who was on leave or who joined the project on Tuesday. 3. **Did it cost what it was supposed to?** Thirty minutes booked and thirty minutes used, by the people who needed to be there. A meeting that runs over, or that has nine people for a decision between two of them, has paid more than its result was worth. The three stages below each serve one of these tests. Before serves the first, during the third, and the last five minutes plus the recap serve the second. ## Before: the four decisions that make the meeting Most of what makes a meeting effective is settled before anyone joins. Four decisions, in order: **Whether to hold it.** Write the purpose in one sentence that names the result — a decision, a plan, a piece of information that needs the same room to receive it. If the sentence is "update everyone on X", it is a message in the channel, not a meeting. If it is "get everyone's input on X", ask for the input in writing first and hold the meeting for what the writing could not settle. **Who is in it.** The people who decide, the people who will do the work that follows, and the people who hold a fact nobody else does. Everyone else reads the recap. A meeting for a decision between two people with seven observers is seven people's hour spent on watching. **The list.** The agenda: the items in order, each with an owner, a time box in minutes, and the outcome it needs — decision, information or discussion. Collect items in writing the day before, in the channel where the team already talks, and send the list with the invitation, not instead of it. The format, a template and five filled-in examples are in the [meeting agenda template](https://intermind.com/blog/meeting-agenda-template) guide; this post assumes you have one. **What to read first.** Anything that must be read before, not during. A pre-read linked from the agenda saves the ten minutes at the start of the meeting that are otherwise spent reading it aloud. If nobody will read it, it goes into the information slot of the meeting and the meeting gets longer — an honest trade, as long as it is made on purpose. ## During: how to run the room The call itself is a short job if the list exists: open, run the list, keep the time, close. Three roles make it work, and in a small team one person often holds two of them. - **The facilitator** owns the list, not the content: opens each item, holds the time box, says the outcome aloud before moving on. The facilitator is not the most senior person in the room; a chair who is also the main decider spends the meeting arguing with themselves about when to stop. - **The notes** are written during, not after. One person writes the outcome of each item as it is read back — or, where the tool does it, checks that it was caught. - **The timekeeper** says "five minutes left on this item" once per item. In a team of five the facilitator does this; above ten, it is a separate pair of eyes. **Open with the purpose, not with the weather.** The first minute: the purpose sentence, the number of items, the end time, and who takes notes. People who know what the meeting is for and when it ends behave differently from people who are waiting to find out. **Run the list, not the clock.** For each item the owner frames it in one minute — the question, the options — and the room works it inside the time box. The facilitator has one job per item: before moving on, say the outcome aloud. "So we're recording: decided, two languages, Lena owns the brief by the 12th." Reading the outcome back turns a conversation into a record while the people who had it are still in the room, and it catches the misunderstanding that would otherwise surface in next week's meeting. **Park what runs over.** An item that is not done when its minutes are is not extended; it is parked with a next step and a date — a smaller meeting, a written proposal, a decision by the owner alone. The parking lot is read out at the close and goes on the next agenda. The exception is the decision item that is one sentence from done; the facilitator asks the room for three more minutes and takes them from the information items, never from the close. **Ground rules, if your team needs them written.** Most teams run well on three: one conversation at a time, the owner speaks first on their item, and the outcome is said aloud before the next item. Cameras, mute and hand-raise are a matter of the team's own habit; a rule that nobody enforces is not a rule. ## The last five minutes The close is the part most meetings skip, and it is the part that produces the recap. Reserve five minutes for it on every agenda, and run them the same way every time: 1. **Read the outcomes back, item by item.** Each one gets one of three states — decided, open, or deferred to a date. A decision is read in a full sentence so the room hears what it agreed to; an open item gets the name of the person who moves it forward. 2. **Read every action with its owner and its day.** "Priya — interview slots to the channel — by Thursday." No owner, no action; an action the room cannot assign is an open item, not a task. 3. **Say what reaches every member's inbox, and when.** The recap, the same day. Members who were not in the room get the same record as those who were; a guest who joined by link without an account hears the meeting live and gets no record afterwards, so if a guest has an action, it is written next to a member who follows it up. 4. **Name the next meeting, or say there is none.** For a recurring meeting, the parking lot becomes the first items of the next agenda, and the open actions are the first thing checked. Then end on time. Ending a meeting five minutes early because the list is done is a result the room notices; ending five minutes late because the close was squeezed is the thing it remembers. ## After: the recap the same day The recap is the agenda with the outcomes filled in — three words per item plus the actions — and if the last five minutes were run, it already exists in the notes. Two rules decide whether it gets used: **Same day, to everyone invited.** Not to those who attended: to everyone the invitation went to. The person who missed the meeting is the one the recap exists for. **Where the next meeting will find it.** A recap in one person's notes is a recap the team does not have. It goes where the agenda for the next meeting will be drafted — the channel, the calendar event, the project's document — so that "what did we decide on item 3 three weeks ago" is a search, not a question to the room. The fuller, formal version of the same record is covered in [how to write meeting minutes](https://intermind.com/blog/how-to-write-meeting-minutes); the short form that most teams send is in [the meeting recap guide](https://intermind.com/blog/meeting-recap). Follow-through is the recap's second job. Open actions from the last recap are the first thing the next meeting checks — done, not done with a reason, or not discussed — and an action that is "not done" three meetings in a row is a decision the team has not made yet, not a task. ## A running sheet you can copy The facilitator's one page: the agenda with the close built in, filled during the meeting. Paste it into a note in the channel, a document or a canvas. > **\[Team] — \[Meeting name] — \[date]**:br**Purpose:** \[one sentence — what this meeting produces] :br**Facilitator:** \[name] · **Notes:** \[name or "the recap"] · **Ends:** \[time] :br**Pre-reads:** \[link], \[link] > > **Opening (1 min):** purpose read, \[N] items, end time, who takes notes. > > **1. \[Item]** — \[owner] — \[minutes] — *decision*:br > Outcome: \[decided / open — who moves it / deferred to date] > > **2. \[Item]** — \[owner] — \[minutes] — *discussion*:br > Outcome: \[what was heard; what happens next] > > **3. \[Item]** — \[owner] — \[minutes] — *information*:br > Outcome: \[noted; questions parked] > > **Parking lot:** \[raised, not on the list — carried to the next agenda] > > **Close (5 min)**:br > Outcomes read back: \[item 1 — state], \[item 2 — state], \[item 3 — state] :br > Actions: \[name] — \[task] — by \[date]; \[name] — \[task] — by \[date] :br > Recap to every member today; next meeting \[date] or none. The sheet works for any length of meeting; the time boxes change, the close does not. For the agendas themselves, from the daily stand-up to the board meeting, see [meeting agenda examples](https://intermind.com/blog/meeting-agenda-examples). ## Where the record of a meeting lives in the tools you already use Each platform has a place for the agenda and a place for what the meeting left behind, and each stops at a different point. Documented behaviour only, from the vendors' own pages; the month each page was checked is in the *Sources* footer. | Platform | Before: where the list is written | During: what the room sees | After: what stays, and for whom | | -------------------- | ------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | *Add an agenda* in the meeting's Details when scheduling | *Notes* in the meeting controls — a Loop document any attendee or organizer can edit, tasks assigned by tagging; external attendees cannot access or edit it | A recap with recording, transcript, shared files and notes for scheduled meetings that were recorded or transcribed; AI summary and notes require Teams Premium or a Microsoft 365 Copilot license; "not currently available for ad-hoc events" | | **Zoom Workplace** | AI Companion generates an agenda when the meeting is scheduled (setting enabled, desktop app 6.5.10 or later) | The agenda is shared and edited in Zoom Canvas | An AI Companion summary — quick recap, summary, next steps — on Pro and above, emailed; participants receive it when the host shares it; "unauthenticated users will not receive an email summary"; only the host can edit it | | **Google Workspace** | The Calendar event's description; *Take notes for me* switched on in Calendar for eligible editions | The meeting; Gemini captures notes when switched on | A Google Doc with summary, decisions and next steps, emailed to the organizer and attached to the event; "this feature supports one language at a time" | | **Slack** | A canvas from the meeting-agenda template, in the channel | The canvas, edited by whoever types | The canvas stays in the channel; what was said in the call is not in it unless someone types it | Two things are the same across the four. The record is written in the language the meeting was held in — Google states it outright, Zoom and Teams document a summary of the spoken transcript — and it reaches the people the host or an admin chose, in one copy. A reader who works in another language reads that copy as a second-language document or asks a colleague. ## How the meeting runs in a channel InterMIND is a communication space where a meeting lives in a channel, so the three stages have one home. The agenda is collected the day before as replies in the channel's chat, or lands there by email — every channel can have its own address, and a message sent to it arrives as a regular message with the sender named and attachments kept. During the call the running sheet, posted as a note, goes on everyone's screen next to the video tiles with *Share to conference*: the facilitator edits it live while the room watches, and every participant reads it in their own language, with the original a toggle away. The chat is translated per reader the same way — each member types in their own language and reads the others in theirs. When the call ends, the recap is written from the meeting itself: a summary, the points marked agreed, open or disputed, the action items with owners, each line keeping its timestamp. It arrives by email, as a message in the channel and as a link in the calendar event, and every signed-in member reads it **in their own language** — the record is translated per reader, not written once in the language the room happened to use. Any member can edit it, every edit keeps author and revision history, and the channel keeps the recap of every past session, so the close of three weeks ago is one click away. In an organization with team status pages on, the open action items of earlier sessions are judged when the next recap is written — done, not done with the reason in the words of the meeting, or left open when nobody brought them up — with the verdicts on the organization's status page rather than in the recap, and at the start of the next session Mia names the open items and their owners, so the parking lot is spoken about rather than lost. Team status pages are a preview feature: an organization's admin switches them on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). A guest joins by link, without an account and at no cost — from a phone, in the browser — and hears the meeting live in their own language. There is no record for a guest afterwards: the account is free, and it is what makes the record reachable. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing); members who go quiet keep their access at no cost. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. Running a meeting well is a craft that survives every tool: somebody still has to decide what the meeting is for, hold the time, and read the outcomes back. What does not have to survive is the second job — typing the record up by hand after the call, in one language, for people who read others. ## FAQ **How do you run an effective meeting?** Decide the purpose in one sentence and invite only the people who decide, do or know; send an agenda the day before with an owner, a time box and an outcome per item; open with the purpose and the end time; run the list inside the time boxes and say each outcome aloud before moving on; reserve the last five minutes to read every decision and action back; publish the recap the same day to everyone invited. **What makes a meeting effective?** Three tests, a week later: it produced what it was called for; everyone who has to act can find out what to do without having been there; and it cost the time and people it was supposed to. A meeting that passes the first two but ran an hour over for nine people has still failed the third. **How do you start a meeting?** With the purpose, not with small talk: read the purpose sentence, say how many items there are, name the end time and who takes notes. The whole opening takes a minute. Then open item one by handing it to its owner. **How do you end a meeting?** In the last five minutes, read each item back as decided, open or deferred to a date; read every action with an owner and a day; say that the recap goes out today and where it will live; name the next meeting or say there is none. Then stop on time — and if the list is done early, stop early. **What are the ground rules for an effective meeting?** The three most teams need: one conversation at a time; the owner speaks first on their item; the outcome is said aloud before the next item starts. Rules about cameras, mute or hand-raise are a team's own habit and only count if someone enforces them. **How long should a meeting be?** As long as its list: the time boxes should add up to the booking minus five minutes for the close. Three to five items fit in thirty minutes, five to seven in an hour. If the list needs more, either several items are information that belongs in a message, or it is two meetings. **What are the 4 P's of effective meetings?** A common planning mnemonic: purpose, people, process and product (or payoff). In practice: the purpose sentence, the invitee list, the order and time boxes, and the outcome the meeting must leave behind. Some versions add a fifth P, preparation — the pre-reads. --- *Sources: [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""}; [Zoom — Generating meeting agenda with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0081706){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Meeting agenda template (canvas)](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Microsoft's notes page, the Zoom agenda page and the Google and Slack pages checked October 2026; the Teams recap page and the Zoom meeting-summary page checked August 2026. Vendors change plans, features and language lists over time; check their pages for the current state.* # How to schedule a meeting from Google Calendar or Outlook: one click, the link is already inside (2026) - **Connect once, then one click.** The calendar half of New meeting creates the room and opens your calendar with the event pre-filled: title, join link, recap link. - **The link is permanent.** The same room keeps its chat and every recap week after week, and a date changed in the calendar moves the row. - **InterMIND keeps the whole meeting in each member's language,** next to Google Calendar or Outlook rather than instead of them. Guests join free by link, no account; you pay only for active members. If you searched "how to schedule a meeting" with a calendar invite in mind, the short answer for InterMIND is: connect your calendar once, then click the calendar half of **New meeting** — the room is created without entering it, and your calendar opens with the event already filled in: the title, the join link, the recap link. Add the people and the date, send. This guide is the full version: the one-time setup, the two ways a meeting gets onto the calendar, what "the link is permanent" changes, what someone outside the team does with the invite, and — quoted from Google's and Microsoft's help pages, checked September 2026 — how Meet and Teams schedule the same meeting. ## Once: connect the calendar 1. Open **Integrations** from the sidebar. 2. In the **Calendar Integration** card, click **Connect** next to **Google Calendar** or **Microsoft Outlook Calendar**, and sign in with that account. 3. The card shows the connected account's email. With both calendars connected, click **Make default** on the one you want scheduled meetings to use. There is no provider picker on the Meetings page itself — the default set here is the calendar that opens. ## Schedule a new meeting 1. On the **Meetings** page, the **New meeting** button is a split button. The main half creates a meeting and takes you straight into it. **Click the calendar half** — the meeting is created *without* entering it, and your calendar opens in a new tab with the event pre-filled: the title, the join link, and the link to the meeting's recap. 2. **Add the people, pick the date** — and, for a regular meeting, the recurrence — right there in the calendar. 3. **Send.** Everyone gets the link in the invite. The meeting row on the Meetings page picks up the date from your calendar and follows any later change: move the event, and the row moves. Once the event is observed, the same calendar button opens it for editing. A scheduled meeting shows a live countdown for thirty minutes before it starts, and **Now** while it is in its window. ## Put a meeting that already met on the calendar Any meeting can be added to the calendar — including one that has already happened. Click the calendar button on the meeting's row: the calendar opens with the event pre-filled the same way, and you pick the date and the recurrence. This is what the permanent link is for. A one-off room can become the weekly one without losing anything: the chat and every recap stay with the meeting, week after week, because it is the same room, not a new meeting each time. Rename the row if you want your own title; by default the list names the meeting after its participants. ## Who gets what from the invite - **Members of your team** click the link in the invite and land on the pre-join screen. - **Someone outside the team** joins by the same link as a guest — no account needed. They type their name, and the host admits them. The step-by-step, and what a guest gets, is in the [guide to joining a meeting](https://intermind.com/blog/how-to-join-a-video-meeting-from-your-computer). - **Everyone** hears the meeting in their own language, in the speaker's own voice, and the signed-in participants get the recap in theirs afterwards — the recap link in the calendar event points at it. Need the room right now rather than next week? The field next to **New meeting** accepts a contact's name or email; pick one or more people and the button becomes **Meet now** — it creates the meeting, sends the invites by email (plus a push notification on mobile) and puts you in the room. Capacity follows the host's plan: 50 participants on Basic, 100 on Pro, 300 on Business, 1,500 on Enterprise. ## How Google Meet and Microsoft Teams schedule the same meeting Two documented maps, quoted, with the check date. Nothing here is an evaluation. | | Google Meet | Microsoft Teams | InterMIND | | ------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- | | Where you schedule | Google Calendar: "Create", "Event", "Add guests", "Save" | Teams calendar: "Select a timeslot on the calendar or select New. Add meeting details and attendees. Turn on the Teams meeting toggle. Select Save" | The calendar half of **New meeting**, or the calendar button on any meeting's row — opens Google Calendar or Outlook | | The link in the event | When creating the Calendar event, you can "add a video meeting link" | "Teams lets you invite people to a meeting via a meeting link"; the page does not state that the link is added to the invitation automatically | The join link and the recap link are pre-filled in the event | | The other calendar | — | "When you schedule a meeting in Teams, it'll automatically appear in your Outlook calendar, and vice versa" | Meeting rows follow the connected calendar's dates | | People outside the organization | "Guests can forward the meeting link"; "if an uninvited person tries to join, a meeting participant from your organization must accept their request" | "Type their full email address" | Join by the same link as guests; the host admits them | | Recurring meetings | "Recurring meetings keep the same settings as the first meeting" | Not stated on the scheduling page | The link is permanent: the same room keeps its chat and every recap | | Limits stated | "If you're a Google Workspace Essentials user, you can't schedule a meeting in Google Calendar" | "Up to 1,000 invitees can join and participate"; "up to 10,000 invitees can join as view-only attendees" | 50 to 1,500 participants by the host's plan | The rows are drawn from the two help pages listed in the footer. "Not stated" means the page did not state it at check time, not that the product lacks it. ## FAQ **How do I schedule an InterMIND meeting in Google Calendar or Outlook?** Connect the calendar once in **Integrations → Calendar Integration**. Then click the calendar half of **New meeting**: the room is created and your calendar opens with the event pre-filled — title, join link, recap link. Add the people and the date, send. **Can I make a meeting that already happened a recurring one?** Yes. Click the calendar button on the meeting's row, pick the date and the recurrence. The link is permanent, so the room keeps its chat and every recap. **What happens if I move the event in my calendar?** The meeting row on the Meetings page follows the calendar's date. If the calendar is disconnected, rows keep the date from the last sync until you reconnect. **Can I use both Google Calendar and Outlook?** Yes. Connect both in Integrations and click **Make default** on the one scheduled meetings should use. **Does someone outside my team need an account to join a scheduled meeting?** No. They join by the same link as a guest, type their name, and the host admits them. An account is needed for the recap and the meeting's history afterwards. ## Try it - **[How to hand over a meeting or a channel to another host](https://intermind.com/blog/how-to-hand-over-a-meeting-or-channel-to-another-host)** — mid-call, or when the creator leaves the company. - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Starting a meeting](https://intermind.com/docs/meetings/start)** — the split button, Meet now, scheduling, the Meetings list. - **[Calendar settings](https://intermind.com/docs/settings/calendar)** — connecting Google Calendar and Outlook, the default calendar. - **[Calendar sync](https://intermind.com/features/calendar)** — what two-way sync gives you day to day. *Sources: [Google Meet Help — Start or schedule a Google Meet video meeting](https://support.google.com/meet/answer/9302870){rel=""nofollow""}, [Microsoft Support — Schedule a meeting in Microsoft Teams](https://support.microsoft.com/en-us/office/schedule-a-meeting-in-microsoft-teams-943507a9-8583-4c58-b5d2-8ec8265e04e5){rel=""nofollow""}. Vendors change their apps and documentation over time; check their pages for the current state. All facts checked September 2026.* # How to see who uses your translation minutes and storage — and get an email before you hit the limit (2026) - **Metered by the meeting host.** Voice minutes, chat words and translated documents count against the plan of whoever created the meeting, over a rolling 30-day window; storage is one team pool. - **The meeting never stops.** At the limit translation pauses while video and chat continue; an email arrives first, and View details shows which meeting used what. - **InterMIND keeps the whole meeting in each member's language,** at no cost to the listener. Guests join free by link, no account; you pay only for active members. A plan with an allowance raises one question in the first month: who is using it. If you searched "usage limits" for a meeting tool, the short answer for InterMIND is that every allowance is metered per **meeting host** — the person who created the meeting pays for its translation, whoever turned it on — and the **Billing** page shows each meter over a rolling 30-day window. This guide is the rest: what each meter counts, what happens at the limit, which emails arrive before it, and how the window refills. ## Four meters, one page Open **Billing** in the sidebar. Under the plan status — tier, trial or paid, next billing date — four meters: | Meter | What it counts | Whose usage | Window | | ------------------------ | ----------------------------------------------------------------------------------------------------------------- | ----------- | --------------- | | **Voice translation** | Minutes of live voice translation in meetings you created | The host's | Rolling 30 days | | **Text translation** | Words of chat translation for participants in meetings you created (a cap on Basic only; unlimited on paid plans) | The host's | Rolling 30 days | | **Document translation** | Distinct files translated; re-translating the same file into more languages does not count again | The host's | Rolling 30 days | | **Storage** | Every file, recording and upload of the whole team | The team's | Current total | Each meter is a bar with the exact numbers and three colours: normal under 80 %, warning from 80 %, red at 100 %. Only active translation time counts — pausing translation stops the meter — and a listener's choice never costs the listener: minutes spent translating in a meeting you created count against your plan, not theirs. That is the host-framing economics of the product: the host provides the room, every participant gets it in their language at no cost to them. ## Who used it Click **View details** on the Billing page for the **Usage details** view: voice translation listed by meeting, host and who triggered it, with the minutes used; text translation by meeting and words; document translation by file and uploader; storage by file and size. A team sees which meetings consumed the minutes — the weekly customer call, the daily standup, the one-off workshop — rather than one anonymous total. Storage is one pool for the team; the [team storage](https://intermind.com/docs/users/storage) page lists the files and recordings behind it. ## The emails, before the limit InterMIND emails you when you approach the **storage** limit — triggered by recording events, since recordings are what fills a pool fastest — and the first time you reach the **translation-minute** limit. The email says which allowance and where to look, so a host learns about the limit before the meeting where it matters. ## What happens at the limit - **Voice translation.** First a warning that you are approaching the limit; at the limit your translation language locks, and live translation pauses until usage falls below the limit. **The meeting itself continues** — video, chat and every other feature keep working. - **Text translation.** On Basic, at 10K words new messages are still delivered, just not translated. On every paid plan it is unlimited. - **Document translation.** Pro 10, Business 30, Enterprise 100 distinct files per 30 days; Basic shows "Not on this plan". - **Storage.** At the limit new uploads are refused; existing files stay available. Before a server recording starts, InterMIND checks the host's team storage and refuses the recording with an explanation if the team is at capacity. ## How the window refills The 30-day window is rolling: a session from 31 days ago falls out of it, and the available time grows by that much. A team that runs out every month either upgrades — Business and Enterprise have unlimited voice translation — or waits for older usage to roll off. The [pricing page](https://intermind.com/pricing) has the live allowances per plan; the [usage documentation](https://intermind.com/docs/billing/usage) has every rule. ## FAQ **Who pays for translation in a meeting — the host or the listener?** The host. Minutes of voice translation in any meeting you created count against your plan, whichever participant turned translation on. Listeners pay nothing. **How do I see which meetings used our translation minutes?** Click View details on the Billing page: voice translation is listed by meeting, host and who triggered it, with the minutes used over the last 30 days. **Do I get warned before we hit the limit?** Yes. A meter turns yellow from 80 %, a warning notification appears as you approach the limit, and an email arrives when you approach the storage limit and the first time you reach the translation-minute limit. **What happens to the meeting when translation minutes run out?** Nothing to the meeting — video, chat and everything else continue. Live translation pauses until usage falls below the limit or the plan is upgraded. **Does storage count per person?** No. Storage is one pool for the whole team: every member's files, recordings and uploads count toward the same limit. ## Try it - **[Usage and invoices](https://intermind.com/docs/billing/usage)** — every meter, every rule, the invoices. - **[Pricing](https://intermind.com/pricing)** — the live allowances per plan. - **[Is InterMIND free for meeting participants?](https://intermind.com/blog/free-for-participants)** — who pays for what. # How to send meeting recaps to your CRM, help desk or spreadsheet: Zapier, a webhook, or the API (2026) - **Four ways in.** A recap copy to an inbound email address, Zapier with the Meeting Recap Ready trigger, a signed webhook, or the API with an OpenAPI contract. - **The payload carries one language.** The summary arrives in the host's language, named in the payload; the linked recap page reads in each signed-in participant's own. - **InterMIND keeps the whole meeting in each member's language,** and the recap lands where the team works. Guests join free by link, no account; you pay only for active members. The recap of a customer call is only useful where the next person will look for it: on the deal in the CRM, on the ticket in the help desk, in the row of the sheet the team already keeps. If you searched "send meeting notes to HubSpot automatically" or "Zapier meeting recap", the short answer for InterMIND is: connect it to Zapier once with an API key, and the **Meeting Recap Ready** trigger fires for every meeting you hosted the moment its summary exists. This guide is the full version — the no-code way, the webhook, the API, what each of them carries, and the way that needs no integration at all. One property of every recap first, because it changes what lands in the CRM: the summary arrives in the language of the reader, and each participant reads it in theirs. The payload below carries the summary in one language, the host's, with the language named in the payload. ## Four ways in | Way | For whom | What you set up | | ------------------------- | -------------------------------------- | --------------------------------------------------------------------------------------------------- | | **Recap copy by email** | Anyone; no integration | Add the tool's inbound address as a recap copy recipient on the meeting or channel | | **Zapier** | No code | One API key, then Zaps on the trigger and the action | | **Webhook `recap.ready`** | A developer, or Make / n8n / Pipedream | One `POST /webhooks` subscription with a public `https://` URL | | **The API** | A developer, an AI agent | A personal key, a dozen endpoints (meetings, recaps, transcripts, channels, documents), OpenAPI 3.1 | All four are available on every registered account. A guest cannot create keys. ## The way that needs no integration: a recap copy Most CRMs, help desks and trackers have an inbound email address that turns a message into a note or a ticket. Add that address as a **recap copy recipient** on a meeting or a channel and the summary is emailed there after every session — up to ten addresses per host, each confirmed once by a test email, applied to all your meetings or to one channel or meeting. The details are in the [recap documentation](https://intermind.com/docs/meetings/recap). If that is enough for your tool, stop here. ## Zapier: the trigger and the action 1. **Create a key.** Open **Integrations**, find the **API keys** card, click **Create key**, label it "Zapier" and copy the key. It starts with `imk_` and is shown once — InterMIND stores only a hash. Up to ten keys per account; revoke one from the same card at any time. 2. **Connect.** In Zapier, add the **InterMIND** app to a Zap and paste the key when asked. The connection is labelled with your account email. 3. **Trigger: Meeting Recap Ready.** Fires once per finished meeting you hosted, as soon as the summary exists. Fields: meeting title and link, recap link, transcript link, the summary in Markdown, the summary language, start and end time, participants with name and email, the host. 4. **Action: Create Meeting Link.** Creates an ad-hoc meeting you own and returns its URL — put it in a CRM deal, a support ticket or a calendar invite. Anyone who opens the link knocks, and you admit them in the room. Typical Zaps: recap → new note on the HubSpot deal; recap → internal comment on the Zendesk ticket; recap → row in Google Sheets; new Pipedrive deal → meeting link written back to the deal. The same integration works from Make, n8n or Pipedream through their generic webhook and HTTP modules, using the webhook and the API below. ## The webhook: `recap.ready` Subscribe once: ```http POST https://intermind.com/api/v1/webhooks Authorization: Bearer imk_… Content-Type: application/json { "target_url": "https://example.com/hooks/intermind", "event": "recap.ready" } ``` The answer is `201` with the subscription's `id` and a `secret`. From then on, the moment a recap for a meeting **you hosted** is finalised with a non-empty summary, InterMIND sends one `POST` per meeting session to the target URL with these headers: | Header | Value | | ----------------------- | ------------------------------------------------------------------------ | | `X-InterMIND-Event` | `recap.ready` | | `X-InterMIND-Delivery` | Unique id of the event (`.`) — deduplicate on it | | `X-InterMIND-Signature` | `sha256=` | | `User-Agent` | `InterMIND-Webhooks/1` | The body carries the meeting (id, title, url, type), the recap (url, transcript url, the summary in Markdown, its language), the session's start and end, the participants with name and email, and the host. The full example is in the [API documentation](https://intermind.com/docs/integrations/api-zapier). Delivery rules, so nothing is silently lost: your endpoint answers `2xx` within 8 seconds; a network error, a `5xx` or a `429` is retried once immediately; a `410` or a `404` deletes the subscription; any other failure is logged and the event is not resent — the recap email and the recap page remain the durable record. The `target_url` must be `https://` and publicly reachable; private network addresses are refused. Twenty subscriptions per account. ## The API: the endpoints and a contract Base URL `https://intermind.com/api/v1`, JSON in and out, the key as a bearer token. Keys work only on these endpoints; they never grant access to the web application's own API. | Method | Path | Purpose | | ------------------------- | ---------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `GET` | `/me` | Who owns the key: id, email, name | | `POST` | `/meetings` | Create an ad-hoc meeting link; optional `{ "title": "…" }`; returns `201` with id, url, title | | `GET` | `/recaps?limit=3` | Your newest recaps (1–10), newest first, in the webhook payload shape | | `GET` / `POST` / `DELETE` | `/webhooks`, `/webhooks/{id}` | List, subscribe, unsubscribe | | `GET` | `/meetings`, `/meetings/{id}/transcript`, `/recaps/search`, `/channels`, `/channels/{id}/messages`, `/documents` | Since September 2026: your meetings, a transcript by speaker, a phrase search over your recaps, your channels and their chat, the documents shared there — keys created earlier need re-creating to open these | | `POST` | `/meetings` with `starts_at` + `time_zone`, `/channels/{id}/messages` | Schedule a meeting into your connected calendar; post a chat message as you | The machine-readable contract — OpenAPI 3.1 for Make, n8n, Pipedream and AI agents — is at `https://intermind.com/api/v1/openapi.json`. An AI assistant that speaks MCP (Claude, ChatGPT, Copilot, Gemini) can do all of this — meetings, recaps, transcripts, channels — without the key at all — that path is the [MCP guide](https://intermind.com/blog/mcp-servers-for-meeting-tools). ## What lands, and in whose language The summary in the payload is one text in one language — the host's summary language, named in the `recap.language` field. The recap page linked from the payload is what each participant opens, and there every signed-in participant reads the summary in their own language. So the CRM note is the host's version; the link on it opens each reader's. Recap and transcript links open for meeting participants who are signed in. A guest of the meeting gets neither the link nor the email — the account is what makes the part after the call reachable. ## FAQ **Can I get meeting summaries into HubSpot or Zendesk without an integration?** Yes. Add the tool's inbound email address as a recap copy recipient on the meeting or channel — the summary is emailed there after every session, no key and no Zap. **How do I connect InterMIND to Zapier?** Create an API key in Integrations → API keys, add the InterMIND app to a Zap and paste the key. Use the Meeting Recap Ready trigger and the Create Meeting Link action. **Does the webhook fire for meetings I only attended?** No. `recap.ready` is sent for meetings you hosted, once per session, when the summary is non-empty. **What if my endpoint is down when the recap is ready?** A network error, a `5xx` or a `429` is retried once immediately. If that fails, the event is logged and not resent; the recap email and the recap page remain the record, and `GET /recaps` returns the newest ten on demand. **Is the webhook signed?** Yes. Every delivery carries `X-InterMIND-Signature: sha256=` and a unique `X-InterMIND-Delivery` id to deduplicate on. ## Try it - **[How to get a copy of every meeting recap in your CRM by email](https://intermind.com/blog/how-to-get-a-copy-of-every-meeting-recap-in-your-crm-by-email)** — the no-integration route in detail: the field, the confirmation, the address book. - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[API and Zapier](https://intermind.com/docs/integrations/api-zapier)** — the full payload, every endpoint, the limits. - **[Meeting recap: what you get after the call](https://intermind.com/blog/meeting-recap)** — where the recap lands and who receives it. *Sources: [InterMIND API contract, OpenAPI 3.1](https://intermind.com/api/v1/openapi.json){rel=""nofollow""}. Checked September 2026.* # How to share a file, photo or link into your team chat from any app on iPhone, Android or Mac (2026) - **It is in the share sheet.** Tap Share on iPhone or Android and pick InterMIND, or use the Mac's Share menu; choose your Inbox or a channel. - **A file becomes a message.** Files up to 25 MB arrive as messages, a document is summarized on its own, and a channel keeps what lands in it. - **InterMIND keeps the whole space in each member's language,** so a document shared from a phone is read by every channel member in theirs. You pay only for active members. The photo of the whiteboard is in the camera roll, the contract is in Mail, the article is in the browser — and the team chat is a fourth app. If you searched "share to team chat from another app", the short answer for InterMIND is: it is in the share sheet. On iPhone and Android, tap **Share** in any app and pick InterMIND; on a Mac, use the system **Share** menu. Then choose the destination — your own Inbox, or a channel — and it lands there as a message. This guide is the rest: what each platform shares, what happens to the file once it lands, and where the Inbox comes from. ## From a phone: the share sheet 1. In any app, tap **Share** and pick **InterMIND** from the sheet. Text, links, images, video and files are accepted. 2. The **Forward to InterMIND** screen opens with the destination list: your **Inbox**, or any channel you belong to. Tap one. 3. It is sent. Several files go out as individual messages; a file over 25 MB is skipped, and the screen says how many. The iOS app adds itself to the iPhone's share sheet through its Share Extension; the Android app registers in Android's share sheet. Both need the app installed — the phone's browser cannot receive a share. ## From a Mac: the Share menu With the desktop app installed, InterMIND appears in the macOS system **Share** menu — in Finder, in Preview, in any app with a Share button. Pick it, choose the Inbox or a channel, and the file goes in. On Windows, and in the browser on any platform, the equivalent is to paste or to drop the file onto the app window: a file dropped anywhere on the window uploads to the chat, and a collapsed sidebar opens during the drag. ## What happens once it lands - **A document is summarized on its own.** The text is extracted on your device, and an AI summary appears on the file card — the point, the decisions, the open questions — and each member of the channel reads that summary in their own language. Opening the file shows the summary first and the preview one step behind. - **Text and links are messages.** Every member of the channel reads the text in their own language, whatever language it was shared in. - **It goes into the channel's history.** Files shared in a channel stay in its history; they count against the team's shared storage — 1 GB on Basic, 30 GB on Pro, 1 TB on Business, 5 TB on Enterprise. ## Where the Inbox comes from The **Inbox** is your personal channel. It appears in the channel list the first time something arrives in it — a share from the phone, a message forwarded to yourself, or a Telegram message relayed by the InterMIND bot. From the Inbox you route things on to your channels, or keep them: it is the quickest way to save a link or dictate a note for later. The [chat overview](https://intermind.com/docs/chat) describes the three chat types. ## FAQ **How do I send a photo from my iPhone to a team channel?** Open the photo, tap Share, pick InterMIND, then tap the channel. It arrives as a message that every member sees. **Can I share from Android?** Yes. InterMIND is in Android's share sheet; text and files from any app go to your Inbox or a channel. Files up to 25 MB each are sent as individual messages. **Does it work on a Mac?** Yes, with the desktop app installed: InterMIND is in the macOS Share menu. On Windows and in the browser, paste or drop the file onto the app window. **What happens to a PDF I share?** It is summarized automatically — the summary appears on the file card, readable by each member in their own language — and stored in the channel's history against the team's storage. **Is there a size limit?** 25 MB per file. Larger files are skipped, and the share screen tells you how many were. ## Try it - **[How to get a summary of every document shared in a team chat](https://intermind.com/blog/how-to-get-a-summary-of-every-document-shared-in-a-team-chat)** — what happens to the PDF once it lands. - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Desktop and mobile apps](https://intermind.com/docs/getting-started/apps)** — what each app adds, including sharing from other apps. - **[File sharing](https://intermind.com/docs/chat/files)** — formats, storage, what files do in a channel. - **[Voice notes in a team channel](https://intermind.com/blog/voice-notes-in-a-team-channel)** — the other way to put something into a channel from a phone. *Sources: [InterMIND — Desktop and mobile apps](https://intermind.com/docs/getting-started/apps){rel=""nofollow""}. Checked September 2026.* # How to share your phone screen in a video meeting from iPhone or Android (2026) - **Start sharing, allow capture, done.** In the iOS or Android app, start sharing and confirm the system's screen-capture permission; the room sees your phone as the main display. - **The apps share, the mobile browser joins.** On the receiving side a phone pinches to zoom, turns to landscape and sees the presenter's laser pointer in the same place. - **InterMIND keeps the whole meeting in each member's language,** what you say over the share included. Guests join free by link, no account; you pay only for active members. If you searched "share iPhone screen in a meeting" or "screen share from phone", the short answer for InterMIND is: in the iOS or Android app, start sharing, allow the system's screen capture, and the room sees your phone screen as the main display — the same way a laptop share works. This guide is the rest: the steps on each platform, what the others see, what a phone can and cannot do while sharing, what a phone does when someone else shares, and — quoted from Google's and Microsoft's help pages, checked September 2026 — what Meet and Teams state about the phone app. ## Share the phone screen 1. **Join the meeting in the app** — the InterMIND app for iOS (App Store) or Android (Google Play or Samsung Galaxy Store, or Huawei AppGallery on phones without Google services; Android 8 or later). Sharing the phone's screen is a feature of the apps; the mobile browser joins the meeting. 2. **Start sharing** from the meeting controls. 3. **Allow screen capture.** Android asks for its screen-capture permission; iOS asks to start the screen broadcast. Confirm, and the share begins. 4. **Stop** from the same control, or from the system's own indicator, and your camera is back. The room sees your phone screen as the main display; your camera moves to a small tile, exactly as with a laptop share. Everything you show — a document, a photo, an app — is seen by every participant, in every language in the room, because what you *say* over it is translated for each of them as you speak. ## What a phone does when someone else shares - **Pinch to zoom.** A shared screen on a phone can be pinched to zoom into the part you need, and viewed in landscape. - **The laser pointer lands on you.** When a presenter on a laptop draws the pointer, the trail is stored relative to the shared video, not to their monitor, so it lands on the same spot on your phone. Drawing the pointer yourself is a web and desktop feature today. - **Presenter modes follow you.** If the presenter picked **Side by side**, a narrow phone screen moves their camera under the content instead of squeezing it. ## What stays after the call The share itself disappears the moment it stops. What was said over it does not: after every transcribed InterMIND meeting, the signed-in participants get the recap — the summary and the full transcript — and each reads the summary in their own language. A moderator can also start a server recording into the team's storage; the phone app joins the meeting that is being recorded like any other participant. ## Where the phone apps stop The InterMIND apps are optional — the meeting itself is identical in the browser and in the apps. What the apps add is around the meeting window: a call that survives switching apps (a foreground service on the phone), push notifications, sharing into InterMIND from other apps, and the phone screen share described here. The full comparison is in the [apps documentation](https://intermind.com/docs/getting-started/apps). ## What Google Meet and Microsoft Teams state about the phone app Two documented maps, quoted, with the check date. Nothing here is an evaluation. | | Google Meet | Microsoft Teams | InterMIND | | -------------------------- | --------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------- | | Sharing from the phone app | The presenting help page carries "Android" and "iPhone & iPad" tabs; the documented steps on it are the computer ones | Mobile sharing documented: "Share PowerPoint, Share photo, Share video, Share screen, Share Whiteboard" | iOS and Android apps share the phone screen | | Audio with the share | "If you present a Chrome tab, it shares that tab's audio by default" (computer) | "Select Share audio to stream audio from your device" (computer) | A browser tab brings its audio (computer); the phone shares its screen | | Pointing at the content | Laser pointer not mentioned; annotation tools documented | Laser pointer not mentioned; "Select Annotate" documented | The presenter's laser pointer lands on the phone in the same place | The rows are drawn from the two help pages listed in the footer. "Not mentioned" means the page did not mention it at check time, not that the product lacks it. ## FAQ **Can I share my iPhone screen in an InterMIND meeting?** Yes, from the iOS app: start sharing in the meeting and confirm the system's broadcast sheet. The room sees your phone screen as the main display. **Can I share my Android screen?** Yes, from the Android app, using Android's screen-capture permission. Files and text can also be shared into a channel from any Android app through the share sheet — that is a different feature, described in the [guide to sharing from any app](https://intermind.com/blog/how-to-share-a-file-into-your-team-chat-from-any-app). **Can I share my screen from the phone's browser?** Joining works in the mobile browser; sharing the phone's screen is a feature of the iOS and Android apps. **Can I zoom into a screen someone else shares?** Yes. Pinch to zoom on the phone, and turn it to landscape for a wider view. **Does the laser pointer work on a phone?** You see everyone else's trails live, in the right place for your screen size. Drawing the pointer is a web and desktop feature today. ## Try it - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Desktop and mobile apps](https://intermind.com/docs/getting-started/apps)** — what the apps add to the browser. - **[How to share your screen in a video meeting](https://intermind.com/blog/how-to-share-your-screen-in-a-video-meeting)** — screen, window or tab from a computer, presenter modes, the laser pointer. *Sources: [Google Meet Help — Present during a video meeting](https://support.google.com/meet/answer/9308856){rel=""nofollow""}, [Microsoft Support — Present content in Microsoft Teams meetings](https://support.microsoft.com/en-us/teams/meetings/present-content-in-microsoft-teams-meetings){rel=""nofollow""}. Vendors change their apps and documentation over time; check their pages for the current state. All facts checked September 2026.* # How to share your screen in a video meeting: screen, window or tab, from a phone, with a laser pointer (2026) - **Click Share screen, pick, Share.** The entire screen, one window, or a browser tab that brings its audio. The laser pointer lands on the same spot on every device. - **The share disappears, the words stay.** Several participants can share at once, with a permission the host controls; signed-in participants get the recap in their own language. - **InterMIND keeps the whole meeting in each member's language,** whatever you say over your slides. Guests join free by link, no account; you pay only for active members. If you searched "how to share your screen" the short answer is: click **Share screen** in the control bar, pick what to show — the entire screen, one window, or a single browser tab — and click **Share**. That is the whole procedure in InterMIND, in the browser, with nothing to install. Everything else in this guide is what happens next: what the room sees, how you point at things, how it works from a phone, what stays after the call, and where the same job stops in Google Meet and Microsoft Teams — quoted from their own documentation, checked September 2026. The room can be in any mix of languages. That is a property of every InterMIND meeting, not a setting of screen sharing: whatever you say over your slides, each participant hears in their own language, and it is in the recap afterwards in theirs. ## Share your screen in three steps 1. **Click Share screen** in the meeting control bar. On a narrow window the button moves into the **More** menu. 2. **Pick what to show.**The browser opens its own picker with three choices: - **Entire screen** — everything visible on your display. - **Application window** — one application, nothing else. - **Browser tab** — one tab. A tab brings its audio along, which is what you want when you play a video or a recording. 3. **Click Share.** You are presenting. To stop, click **Stop screen sharing** — one click, your camera is back where it was. There is no extension and no plugin: sharing runs in the browser, on Chrome, Edge and Firefox. The desktop app adds a native picker and, on macOS, system audio for whole-screen shares. ## What everyone sees Participants see your shared screen as the main display; your camera moves to a smaller tile. Viewers keep their own zoom — **Zoom to fit** or **Original size** — because the content is never re-encoded on the way to them: it stays as sharp as what you captured. While you share, the arrow next to **Share** opens **Presenter mode** — how your camera sits with your content on everyone else's screen. You pick it once, and every participant sees the layout you chose, including the person who joins in the middle of your talk. | Mode | What everyone sees | | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------- | | **Content only** | Your content fills the stage; your camera stays in the filmstrip with everyone else. This is the default. | | **Standout** | Your camera floats over the content in the bottom-left corner. | | **Side by side** | The stage splits: content on the left, your camera on the right. On a narrow phone screen the camera moves under the content instead. | The mode needs your camera on; with the camera off, everyone stays on **Content only** until you turn it back on. Your camera is shown as it is — InterMIND does not cut you out of your background. ## Point at what you mean: the laser pointer "Third row, on the left" is how people point at a shared screen when the tool gives them nothing better. In InterMIND you hold the pointer over the shared view and draw. A comet trail follows your cursor; when you release, the whole stroke fades over a duration derived from how long you pressed — a deliberate circle lingers, a quick flick vanishes. The trail is streamed to the room and drawn relative to the shared video, not to your monitor. So the same point is marked on a phone, a laptop and an ultrawide — it lands on the right pixel for each viewer, whatever their screen size. Each person draws in their own colour. Drawing the pointer is a web and desktop feature today; on a phone you see everyone else's trails live, and you can share your own screen from the phone (next section). ## From a phone The iOS and Android apps share your phone screen the way the browser shares a laptop screen: start sharing in the app, and the room sees it as the main display. On the receiving side a shared screen on a phone can be pinched to zoom and viewed in landscape. The step-by-step, with the apps' own share sheets, is in the [apps documentation](https://intermind.com/docs/getting-started/apps). ## Several presenters, and who is allowed to share More than one participant can share at the same time; each share carries the presenter mode its presenter picked. Screen sharing is a per-participant permission the host controls — you can hand it to one presenter and take it back afterwards, or leave it open for the whole room. Guests join by the meeting link without an account and see the shared screen like everyone else. What they do not get is the part that comes after the call — the recap and the history go to signed-in members. ## What was said over the slides stays A screen share is the part of the meeting that disappears the moment you stop it. What was *said* over it does not. After every transcribed InterMIND meeting the signed-in participants get the recap — the AI summary and the full transcript — and each of them reads the summary in their own language. If you need the pixels as well, there are two recordings, both in the **More** menu: | Recording | Who can start it | Where the file goes | | -------------------- | --------------------------------------------- | --------------------------------------------------------- | | **Server recording** | Moderators (the host and promoted moderators) | The team's cloud storage, against the host's storage plan | | **Local recording** | Anyone whose browser supports screen capture | Downloaded to that person's device as `.webm` or `.mp4` | A local recording captures your microphone, the tab audio — other participants' voices and translations — and the screen content, and never touches team storage. The full rules, including storage limits per plan, are in the [screen sharing and recording documentation](https://intermind.com/docs/meetings/screen-sharing). ## Where the same job stops in Google Meet and Microsoft Teams Two documented maps, quoted, with the check date. Nothing here is an evaluation; a feature a vendor's page does not mention is recorded as exactly that. | | Google Meet | Microsoft Teams | InterMIND | | ----------------------- | ----------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------- | | What can be shared | "A tab, a specific window, or entire screen" | "Present your entire screen or a window"; PowerPoint Live, Excel Live, Whiteboard | Entire screen, a window, or a browser tab | | Audio with the share | "If you present a Chrome tab, it shares that tab's audio by default"; for a window or screen, "Also share system audio" | "Select Share audio to stream audio from your device … All sound from your computer, including notifications, will be audible" | A tab brings its audio; system audio on macOS via the desktop app | | From the phone app | The documented steps on the presenting page are the computer ones | Mobile sharing documented: "Share PowerPoint, Share photo, Share video, Share screen, Share Whiteboard" | iOS and Android apps share the phone screen | | Pointing at the content | Laser pointer not mentioned; "presenters and appointed co-annotators can use annotation tools" | Laser pointer not mentioned; "Select Annotate to lock what's on your screen while you and other people draw or add notes" | Laser pointer that lands on the same spot on every device, fades on release | | Several presenters | "A maximum of 10 simultaneous presentations in a meeting at a time" | Slide control can be given to "up to 20 people" | Several participants can share at once | | Who controls sharing | May be disabled by admin settings or host controls | "Only people with the ability to share their screen can be given slide control" | Per-participant permission the host controls | The rows are drawn from the two support pages listed in the footer; a row that says "not mentioned" means the page did not mention it at check time, not that the product lacks it. ## FAQ **How do I share my screen with audio?** Share a browser tab: a tab brings its audio along, so a video playing in that tab is heard by the room. For a whole-screen share, the desktop app on macOS adds system audio. **Can I share my screen from my phone?** Yes. The iOS and Android InterMIND apps share the phone screen, and the room sees it as the main display. Drawing the laser pointer is a web and desktop feature; on a phone you see other people's trails live. **Can two people share their screen at the same time?** Yes. Several participants can share at once, and each share carries the presenter mode its presenter chose. The host decides who may share — it is a per-participant permission. **Does everyone see the laser pointer in the same place?** Yes. Pointer positions are stored relative to the shared video frame rather than to your monitor, so the same point is marked on a phone, a laptop and an ultrawide. The stroke fades on its own when you release; a long press leaves a mark that lingers. **Do participants need an account to see my screen?** No. Guests join by the meeting link without an account and see the shared screen like everyone else. The recap and the meeting's history after the call go to signed-in members. **Is the shared screen recorded?** Only if someone records. A moderator can start a server recording into the team's storage; anyone whose browser supports screen capture can start a local recording that downloads to their own device. Without a recording, what stays is the recap: the summary and transcript of what was said, in each member's language. ## Try it - **[How to share your phone screen in a video meeting](https://intermind.com/blog/how-to-share-your-phone-screen-in-a-video-meeting)** — from iPhone or Android, pinch to zoom on the receiving side. - **[How to present to everyone and scroll your shared tab without leaving the call](https://intermind.com/blog/how-to-present-to-everyone-and-scroll-your-shared-tab-without-leaving-the-call)** — one share on every main stage, the tab scrolled from the meeting screen. - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Read the screen sharing docs](https://intermind.com/docs/meetings/screen-sharing)** — the step-by-step, presenter modes and both recordings. - **[Screen share and laser pointer](https://intermind.com/features/laser-pointer)** — how the pointer lands on every display. *Sources: [Google Meet Help — Present during a video meeting](https://support.google.com/meet/answer/9308856){rel=""nofollow""}, [Microsoft Support — Present content in Microsoft Teams meetings](https://support.microsoft.com/en-us/teams/meetings/present-content-in-microsoft-teams-meetings){rel=""nofollow""}. Vendors change their apps and documentation over time; check their pages for the current state. All facts checked September 2026.* # How to start a call from a team chat: one click, the chat stays with you, the recap comes back (2026) - **Click Join at the top of the chat.** Every InterMIND channel has its own room; the pre-join screen sets camera and mic, teammates join the same way, no approval. - **Members only.** The channel's membership is the guest list; a one-off outsider joins an ad-hoc meeting instead, by link, without an account. - **InterMIND keeps the whole conversation in each member's language,** the call, the sidebar chat and the recap posted back into the channel. Guests join free by link, no account; you pay only for active members. A chat thread getting long is the usual signal: five minutes of talking would beat fifty messages. If you searched "how to start a call from a chat", the short answer for InterMIND is that every channel already has its own meeting room — click **Join** at the top of the chat and you are on the pre-join screen. This guide is the rest: who can join and how, what happens to the chat while you talk, what comes back into the channel when you hang up, and — quoted from Slack's and Microsoft's own help pages, checked September 2026 — what a huddle and a Teams chat call do with the same job. If the thread was in two languages, the call is too: each of you hears the other in your own. That is a property of every InterMIND room, not a setting of the call. ## Start the call 1. **Open the channel.** Channels are the persistent team chats on the **Channels** page. 2. **Click Join** at the top of the chat. You land on the pre-join screen: preview your camera, pick the microphone and the speakers, start muted if you want. 3. **Click Join again.** You are in the channel's room. Teammates join the same way — the same **Join** button, no approval step. The room belongs to the channel: it is the same link every time, so a call on Monday and a call on Thursday are sessions of one room, not two meetings to find later. ## Who can join A channel meeting is for the members of the team that owns the channel. Someone who is not a member gets nothing at the meeting URL — there is no waiting room for a channel, because the channel's membership is the guest list. To bring an outside person in, add them to the channel: the member drawer searches your team, your contacts, the people you have met in meetings and your organization directory, and an external address gets a pending email invite. A registered user is added the moment they are invited; everyone else joins on sign-up via the emailed link. People you have met in a finished meeting are badged **Met before**; others outside your team are badged **External**. For a one-off call with someone who should not become a member of the channel, use an ad-hoc meeting instead: there, guests join by link without an account and the host admits them. How that works is in the [guide to joining a meeting](https://intermind.com/blog/how-to-join-a-video-meeting-from-your-computer). ## The chat stays with you The channel chat does not go away when the call starts: it is the same channel, in the meeting sidebar. Share a file, drop a note, paste a link — it goes into the channel's history, where it was going anyway. Two people typing in two languages keep reading each other's messages in their own; the call does not change that either. ## When you hang up, the recap comes back The recap is what makes a call from a channel different from a call *about* a channel. When the session ends, the recap posts back into the channel — the AI summary and the full transcript — and each member reads the summary in their own language. The thread continues where the call ended, with the decisions in it, for the people who were on the call and the ones who were not. The room's capacity follows the host's plan: 50 participants on Basic, 100 on Pro, 300 on Business, 1,500 on Enterprise. ## What a huddle and a Teams chat call do with the same job Two documented maps, quoted, with the check date. Nothing here is an evaluation; a fact a vendor's page does not state is recorded as exactly that. | | Slack huddles | Microsoft Teams (call from a chat) | InterMIND (call from a channel) | | ------------------------ | ----------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | | How it starts | "Click the headphones icon at the top of the conversation" | "Select Video call or Audio call to start a call" | **Join** at the top of the chat | | Who can be on it | Free plan: "a maximum of two participants"; paid plans: "up to 50 participants, but only 25 can enable video at a time" | "Up to 20 people can be on the same video call"; "If a group chat includes more than 20 people, calling buttons will be disabled" | The channel's members; 50 to 1,500 by the host's plan | | Screen sharing | "Up to two people in a huddle can share their screen at a time" | Not stated on the chat-call page | Several participants can share at once | | What stays afterwards | "A dedicated message thread to share notes, links, and files"; the canvas stays "from its tab at the top of the conversation" | "Entries for the calls will appear in your chat"; the calls "are private and won't appear in any team conversation" | The recap — summary and transcript — posts into the channel, in each member's language | | The chat during the call | A thread inside the huddle | The chat the call was started from | The channel itself, in the meeting sidebar | The rows are drawn from the two help pages listed in the footer. "Not stated" means the page did not state it at check time, not that the product lacks it. ## FAQ **How do I start a video call from a group chat?** Open the channel and click **Join** at the top of the chat. The pre-join screen lets you set camera and microphone before you enter; teammates join with the same button, no approval needed. **Can someone outside my team join the call from the channel?** Only as a member of the channel: add them from the member drawer, and an external address gets an email invite. For a one-off outside participant, create an ad-hoc meeting instead — guests join that by link without an account. **Does the chat keep working during the call?** Yes. The channel chat is in the meeting sidebar; files, notes and links posted there land in the channel's history like any other message. **What happens to the call afterwards?** The recap — the AI summary and the full transcript — posts into the channel when the session ends, and each member reads the summary in their own language. The room's link stays the same, so the next call is another session of the same room. **Do we need to speak the same language on the call?** No. Each participant hears the others in their own language, in the speaker's own voice, and reads the chat the same way — that is how every InterMIND room works. ## Try it - **[How to run an audio-only call in a video meeting](https://intermind.com/blog/how-to-run-an-audio-only-call-in-a-video-meeting)** — the voice stage, one key away. - **[How to add an external client or partner to a team chat channel](https://intermind.com/blog/how-to-add-an-external-client-to-a-team-chat-channel)** — by email, a member rather than a guest. - **[Try the live demo](https://intermind.com/demo)** — a real InterMIND meeting in the browser, no signup needed. - **[Channels and members](https://intermind.com/docs/chat/channels)** — the member drawer, invite links, email invites. - **[How to join a video meeting](https://intermind.com/blog/how-to-join-a-video-meeting-from-your-computer)** — the link, the pre-join screen, joining as a guest. - **[Meeting recap: what you get after the call](https://intermind.com/blog/meeting-recap)** — where the recap lands and who receives it. *Sources: [Slack Help Center — Use huddles in Slack](https://slack.com/help/articles/4402059015315-Use-huddles-in-Slack){rel=""nofollow""}, [Microsoft Support — Start a call from a chat in Microsoft Teams](https://support.microsoft.com/en-us/office/start-a-call-from-a-chat-in-microsoft-teams-f5138c9d-df4c-43d8-9cf6-53400c1a7798){rel=""nofollow""}. Vendors change their apps and documentation over time; check their pages for the current state. All facts checked September 2026.* # How to write meeting minutes: format, template, example — and who writes them now (2026) - **Minutes record outcomes, not words.** Attendance, agenda items, decisions and how they were reached, action items with owner and deadline; publish the same day. - **The format assumes one language.** Drafting is increasingly automated, but the record still arrives in the language the room ran in, not the reader's. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes and the recap with decisions and action items, translated per reader. Guests join free by link, no account; you pay only for active members. Meeting minutes are the official written record of a meeting: who was there, what was discussed, what was decided, and who is responsible for what by when. Unlike a transcript, minutes don't record every word — they record outcomes. Unlike a casual summary, they follow a recognizable format, and in boards, councils and associations they are usually the one document the organization is required to keep. This guide is the manual craft first — the format, a template you can copy, a filled-in example, what changes for a board meeting — and then the part the format itself never addresses: who writes the minutes in 2026, and in whose language they arrive when the people in the room don't share one. ## What meeting minutes are — and what they aren't Three documents get produced after meetings, and they answer different questions: | | What it records | Typical length | Who reads it | | -------------- | ----------------------------------------------------------------- | ---------------- | --------------------------------------- | | **Transcript** | Every word, in order | Pages | Almost nobody, searched occasionally | | **Minutes** | The official record: attendance, items, decisions, votes, actions | One to two pages | Members, auditors, whoever wasn't there | | **Recap** | Decisions, action items and open questions, in reading order | One screen | Everyone invited, the same day | Minutes sit in the middle: fuller than a [recap](https://intermind.com/blog/meeting-recap), far shorter than a transcript, and — in formal settings — the version with legal weight. If your meeting is a working call and nobody will ever audit it, the recap format is lighter and gets read more; we keep a separate guide for it. If your meeting has a chair, an agenda and anything resembling a vote, you want minutes. The working notes taken during the call itself — what to capture, and where they live afterwards — have [their own template](https://intermind.com/blog/meeting-notes-template). One thing they are not: a record of time. The word comes from the Latin *minuta* — "small" — as in *minuta scriptura*, notes taken in small writing, later transcribed formally. Minutes were always about compact notes, not about the clock. ## What to include: the standard format A usable set of meeting minutes carries eight elements. This is the skeleton behind nearly every template you'll find, from a project sync to a board book: 1. **Meeting name, date, time and place** (or the meeting link — "place" is a URL now). 2. **Attendance** — present, absent with apologies, and any guests. In formal meetings, note whether quorum was reached. 3. **Approval of the previous minutes** — formal bodies open by approving the last meeting's record, with corrections noted. 4. **Agenda items, in order** — one block per item, each with a short neutral summary of the discussion. Two or three sentences; positions, not a play-by-play. 5. **Decisions** — each decision stated in one sentence, with how it was reached ("agreed by consensus", "carried 5–2"). Decisions are the reason minutes exist; never bury them inside discussion text. 6. **Action items** — owner, task, deadline. One line each. An action item with no owner is a wish, not a record. How to write, assign and track them — and how the recap keeps the list between meetings — is in [the action items guide](https://intermind.com/blog/action-items). 7. **Next meeting** — date and time if set. 8. **Time of adjournment and who recorded the minutes.** What stays out: verbatim quotes (unless someone asks to be minuted), tone and emotion, opinions of the minute-taker, and anything said off the record. Minutes are neutral by construction — a reader should not be able to tell from the text whose side the writer was on. ## How to write them: before, during, after **Before the meeting, steal the structure.** Take the [agenda](https://intermind.com/blog/meeting-agenda-template) and turn it into your minutes skeleton: one heading per item, attendance list pre-filled from the invitation, previous minutes linked. Ninety percent of the formatting work happens before anyone speaks. If there's no agenda, that's the first finding to raise — minutes without an agenda become a chronology of whoever talked loudest. **During the meeting, write decisions, not dialogue.** The craft of taking minutes is aggressive filtering in real time: for each agenda item you need the positions raised (attributed only when it matters), the decision, and the actions. When a decision is made, read it back aloud — "so we're recording: X, agreed by all, Anna to deliver by the 15th" — and let the room correct it while everyone still remembers. That single habit removes most of the disputes that otherwise surface when the minutes circulate. **After the meeting, publish the same day.** Clean up the notes while context is fresh, get the chair's review if your process requires it, and send the minutes to everyone invited — including, especially, the people who missed the meeting. Then store them where the next meeting will find them: minutes that live in one person's inbox are minutes the organization doesn't have. ## A meeting minutes template > **\[Organization / team] — Minutes of \[meeting name]**:br**Date:** \[date] · **Time:** \[start]–\[end] · **Place:** \[room / meeting link] :br**Present:** \[names] · **Apologies:** \[names] · **Guests:** \[names] :br**Chair:** \[name] · **Minutes:** \[name] > > **1. Approval of previous minutes**:br > The minutes of \[date] were approved \[as circulated / with the following correction: …]. > > **2. \[Agenda item]**:br > \[Two–three sentence neutral summary of the discussion.] :br**Decision:** \[one sentence — what was decided and how: consensus / vote count]. :br**Action:** \[name] — \[task] — by \[date]. > > **3. \[Agenda item]**:br > \[Summary.] :br**Decision:** \[decision, or "deferred to \[date]"]. :br**Action:** \[name] — \[task] — by \[date]. > > **Next meeting:** \[date, time]. :br > The meeting was adjourned at \[time]. ## A filled-in example > **Aster GmbH — Minutes of the product council**:br**Date:** 28 August 2026 · **Time:** 14:00–14:50 · **Place:** meeting link :br**Present:** L. Ortega (chair), M. Bauer, K. Sato, P. Nowak (minutes) · **Apologies:** J. Lindqvist > > **1. Approval of previous minutes**:br > The minutes of 14 August were approved as circulated. > > **2. Q4 pricing revision**:br > Bauer presented the revised tiers; Sato raised the impact on annual renewals. The council agreed the revision should not apply to contracts signed before October. :br**Decision:** revised tiers adopted for new contracts from 1 October — carried 3–0. :br**Action:** M. Bauer — updated price list to sales — by 5 September. > > **3. Support coverage in Japanese**:br > Sato reported current response times. Discussion deferred pending the September hiring round. :br**Decision:** deferred to the next council. > > **Next meeting:** 11 September 2026, 14:00. :br > The meeting was adjourned at 14:50. Notice what the example doesn't contain: nobody's exact words, no adjectives, no atmosphere. Fifty minutes of meeting became fourteen lines that a person who wasn't there can act on — that's the entire job. ## Board minutes: what formality adds For a board, council or association, the same skeleton picks up legal duties, and the details vary by jurisdiction and by your own bylaws — check both. The additions are consistent across most rulebooks: record that notice was properly given and quorum reached; record **motions** verbatim — who moved, who seconded, and the vote tally, with abstentions and any recusals named; record dissent when a member asks for it. Approved minutes typically become the organization's official evidence of its decisions, which is why boards approve the previous meeting's minutes as their first item — the record itself needs a decision. The discipline that follows from legal weight is the same one that makes everyday minutes good: neutral language, decisions over dialogue, and nothing in the record you wouldn't want read back in two years. ## Who writes them now — and in whose language In 2026 the writing itself is increasingly automated: the meeting is transcribed, a model drafts the summary, and the minute-taker's job shifts from stenography to editing. What the automation has mostly not changed is the assumption underneath the format — that the meeting, and therefore its record, happens in one language. Run a meeting in English with a team that thinks in Portuguese, Polish and German, and the minutes arrive in English: accurate, official, and a second-language document for most of the people bound by it. We documented what each major platform actually keeps after a call, per vendor and with sources, in [the recap guide](https://intermind.com/blog/meeting-recap) — the shape is the same everywhere: one record, one language — and [how much of the meeting still exists in your language a week later](https://intermind.com/blog/the-meeting-a-week-later) is a question with a measured answer. We built InterMIND so that the record doesn't have that assumption. It's a communication space where the meeting runs in each participant's own language — voice, chat and notes — and when the call ends, the summary already exists: overview, points marked agreed, open or disputed, action items with owners, each line keeping its timestamp. Signed-in members get it by email, in the meeting's chat and in the calendar event, and every member reads it **in their own language** — the record is translated per reader, not written once in the room's loudest language. Any member can edit it, every edit keeps author and revision history, and a channel keeps the record of every past session. (A participant who joins as a guest without an account gets the fully translated meeting live, but no record afterwards — the account is free, and it's what makes the record reachable.) The summary runs on the AI gateway your organization selects, in an EU region, with zero data retention and no training on your content. Minutes as a craft survive the automation — somebody still has to decide what the meeting meant. What shouldn't survive is the idea that the official record of a multilingual room can only exist in one language. - **[Open a complete example](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours, timestamps included. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. When the minutes start as speech — a voice note recorded into the channel on the way back from the meeting — InterMIND transcribes it and separates the decisions and the action items on its own; the mechanics are in [voice notes in a team channel](https://intermind.com/blog/voice-notes-in-a-team-channel). ## FAQ **What are meeting minutes?** Meeting minutes are the official written record of a meeting: the date and attendance, the items discussed, the decisions made (with vote counts where votes were taken), and the action items with owners and deadlines. They record outcomes, not conversation — a reader who missed the meeting should be able to act on them without hearing what anyone said. **Why are they called "minutes"?** From the Latin *minuta*, "small" — *minuta scriptura* was the rough note taken in small writing during the proceedings, formalized afterwards. The name refers to compact notes, not to units of time. **What should be included in meeting minutes?** Eight things: meeting name/date/time/place; attendance (present, apologies, guests, quorum where relevant); approval of the previous minutes; each agenda item with a short neutral summary; decisions, stated in one sentence each with how they were reached; action items with owner and deadline; the next meeting's date; and adjournment time plus who recorded the minutes. **What should NOT be included in meeting minutes?** Verbatim dialogue, tone, emotion, the minute-taker's opinions, and off-the-record remarks. Attribute positions only where it matters or where a member asks to be minuted. Minutes are neutral: the text should not reveal whose side the writer was on. **What is the difference between meeting minutes and a meeting recap?** Minutes are the fuller, formal record — attendance, agenda items, decisions, votes, actions — and in formal bodies they carry legal weight after approval. A recap is a one-screen working summary (decisions, action items, open questions) sent the same day. For working calls a recap gets read more; for anything with a chair and votes, write minutes. We keep a [separate guide to recaps](https://intermind.com/blog/meeting-recap). **How detailed should meeting minutes be?** Detailed enough that an absent member can act on them; short enough that they get read. The working rule: two-three neutral sentences of discussion per agenda item, every decision in exactly one sentence, every action item on one line. A fifty-minute meeting should usually fit on one to two pages. **Who should take the minutes?** Formal bodies name a secretary or rotate the duty; in working meetings it's whoever is designated — ideally not the chair, who is busy running the discussion. In 2026 a growing share of the first draft is machine-written from the meeting itself, and the human role shifts to editing: verifying decisions, owners and dates before the record circulates. --- *Sources: [Merriam-Webster — "minute" (noun): "the official record of the proceedings of a meeting", from Latin minutus, "small"](https://www.merriam-webster.com/dictionary/minute){rel=""nofollow""}. Board-minute requirements vary by jurisdiction and bylaws — check yours. Checked September 2026.* # Inside the four translation pipelines that run InterMIND - **Four pipelines, not one engine.** Voice, chat, notes and documents each run on their own engine, latency budget and quality envelope, sharing only the picker. - **Different jobs, different engines.** Voice runs per target language in the room on our own engine in France; documents go to DeepL's Document API: 23 and 30 languages. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes and files, per-pair quality published monthly. Guests join free by link, no account; you pay only for active members. The old `/product/overview/how-it-works` page on mind.com is several major releases out of date. It describes a single "translation engine" the way most vendor pages do — one big arrow from "you speak" to "they hear." That picture was already a simplification two years ago. Today it is wrong. The truth is that InterMIND runs **four separate translation pipelines**, each solving a different problem with a different engine, a different latency budget, and a different quality envelope. They share a language picker. They do not share an engine. This is the updated answer to "how does it work." > **A companion piece:** [*"How many languages do you support?"*](https://intermind.com/blog/how-many-languages-do-you-support) covers what each pipeline *covers* (23 / 23 / 30 / 17). This post covers what each pipeline *does* — and why it is its own thing. --- ## Why "one engine for everything" is a lie A live meeting platform has at least four jobs to do at once, and they pull in incompatible directions: 1. **Real-time voice** — audio in, translated audio out while the speaker is still talking, every viewer in their own language. The hard constraint is latency. 2. **Real-time chat text** — short messages, fast, with edits and quotes and HTML structure preserved. 3. **Real-time shared notes** — character-by-character collaborative typing, with structural hierarchy (lists, headings, checkboxes) that has to survive translation. 4. **Asynchronous document files** — a 40-page PDF dropped into chat. No latency budget. The hard constraint is *fidelity* — formatting, tables, page numbers, font. You can build one giant LLM call that tries to do all four. We tried. It is bad at all four. The latency budget for voice means the model can't think; the fidelity budget for documents means the model has to. A chat edit needs a diff in the viewer's language; a 40-page PDF needs format preservation that no token-streaming model gives you. So we run four. Here is each one. --- ## Pipeline 1: Real-time voice translation **The problem:** A participant speaks French. Another participant joined in German, a third in Brazilian Portuguese, a fourth in Japanese. Each one needs to hear the speaker in their own language, in their own ear, with a delay short enough to keep eye contact possible. **The budget:** the listener must never wait for it. Once translated speech lags far enough that people start talking over it, the meeting drifts toward "let's just switch to English." ### How the audio actually moves ![Voice translation pipeline: the speaker's browser sends audio over WebRTC to our own engine — the Mind API media server at OVH, France — which runs ASR and translates into every target language present in the room; each viewer receives their own translated audio track, and the ws-server receives the transcript words for the recap.](https://intermind.com/blog/inside-the-translation-pipelines-voice.svg) A few things worth naming explicitly: - **ASR runs on the media server.** The speaker's audio travels over WebRTC to our own engine — the Mind API at OVH, France — and is recognized there, on the same server that carries the call; the browser only sends audio and receives the words back. No separate speech vendor and no extra hop before translation can start. (Chat voice notes are the exception: their speech-to-text runs on Azure AI Speech, the speech service of the default AI gateway.) - **Translation is not one fan-out.** The engine translates **per target language present in the room**, not per viewer: translation into a language starts when the first listener in it asks for a translated stream, three participants who picked German share one German translation, and nobody listening in Arabic means nothing is translated into Arabic. This is why a four-language meeting costs the same as a forty-language meeting up to the point of who actually showed up — we never translate to languages no participant is listening in. - **Synthesized speech is per-viewer.** Each participant receives their own translated audio track, mixed against the original speaker's video. They are not watching a master "translated meeting" — they are watching the *same meeting*, with their personal audio channel translated to their picked language. This is why two people in the same physical room can each plug in headphones and hear different languages. ### Why this matters when a meeting goes sideways In a 60-minute call with eight languages, things break in interesting ways: WebSockets drop, ASR temporarily mis-transcribes a proper noun, one participant's network gets jittery. The architecture above is what lets us isolate failures: one viewer's audio glitching does not affect the other seven, because the translation engine never produced "the translation" in the first place — it produced eight, in parallel, and only the affected one has to recover. The engine itself is ours, hosted on our own infrastructure. We do not route real-time voice through third-party general-purpose LLMs. The latency budget rules them out; the data-residency story rules them out for the regulated customers who actually care. > **What we publish about voice quality:** [/benchmark](https://intermind.com/benchmark) runs the production voice pipeline against [FLORES-200](https://github.com/facebookresearch/flores){rel=""nofollow""} sentences for every published language pair, monthly. The judge is named (Gemini 3.7 Flash primary, Claude Sonnet 5 fallback). The full distribution — median, p10, p90, min, max, sample size — is on the page. See [the methodology](https://intermind.com/benchmark/methodology) for what those numbers do and don't measure. --- ## Pipeline 2: Real-time chat translation **The problem:** Every chat message in the meeting, translated for every participant in their own language, as it is sent. Plus edits — and edits need to look like edits, not like re-translations. **The budget:** looser than voice. A chat message can take a beat to appear in another language without anyone caring. What people care about is whether the translation is *right* and whether edits make sense. ### What the chat pipeline actually does Each message goes through the same translation engine the voice pipeline uses — but with different pre- and post-processing: - **HTML structure is preserved.** Chat supports rich text (paragraphs, lists, quotes, bold, italic). We convert to plain text for the model, translate, then re-wrap the result in the original tags. The model never sees the HTML — it sees clean prose. - **Quotes are translated independently.** If you reply to a message and quote it, the `[QUOTE]…[/QUOTE]` block and the new content are translated as separate units, so the model can't confuse the two. - **Long messages get chunked.** We split on paragraph boundaries at 1,000 characters per chunk. Each chunk is its own translation call. We do *not* feed 4,000-character novels to the model in one shot — the failure modes (truncation, lost paragraphs, mid-sentence cut-offs) are too ugly. - **Translation is lazy.** We use an IntersectionObserver: a message is only translated when it scrolls into the viewer's viewport. Switching languages in a long-running channel used to replay every translation API call from the history. Now it doesn't. ### The interesting part: edits as diffs In v1.2 we changed how chat edits behave for viewers in another language. The old behavior was: someone edits a message, we re-translate the whole thing, you see a fresh paragraph and have to spot what moved. The new behavior: 1. The original message was already translated to your language. 2. When the sender edits, we re-translate the *new* version. 3. We compute the diff between **your previous translation** and **your new translation**, in your language. 4. We show that diff inline — same way Git shows you what changed. So when "review by Tuesday" becomes "review by Thursday" in English, your Spanish-reading colleague sees **martes → jueves** highlighted, not a re-translated paragraph they have to re-read. This required treating the chat pipeline as a *stateful* per-viewer cache, not a stateless translate-on-request endpoint. Documents and voice don't need this. Chat does. --- ## Pipeline 3: Real-time shared-notes translation **The problem:** The host opens a shared-notes pane and starts typing. Every participant sees the notes in their language, character-by-character, with the structure of the document — headings, nested lists, checklists, code blocks — intact. **The budget:** Same as chat, but with two extra constraints: - **The thing being translated changes mid-translation.** The host is still typing. A naive system that translates "the whole document" each keystroke produces flicker and burns the API budget. We translate at the granularity of the *changed unit*, not the whole document. - **Structure must survive.** If you ask a translation model to translate a markdown blob with three nested lists, you get back something that *looks* like the original but with subtly flattened hierarchy, renumbered items, or moved indentation. We do not let the model see the whole blob. ### How the notes pipeline differs from chat The structural preservation is the main thing. We translate **each list item independently** rather than as one document. The model sees: > "Compliance review — Q2 deliverables" — not: > "# Project plan\n## Quarter\n- Compliance review — Q2 deliverables\n- Vendor scoring\n - Tier 1 vendors..." The wrapping document — the `
    `, the headings, the indentation — is rebuilt on the client side using the same structure the original document had, with each leaf node swapped for its translation. The model never gets to "improve" the hierarchy. Notes also use the same per-viewer diff model as chat edits: if the host changes a line, viewers in other languages see the changed words highlighted, not a fresh paragraph. --- ## Pipeline 4: Asynchronous document translation **The problem:** Someone drops a 40-page PDF, a Word doc, a PowerPoint deck, or an Excel sheet into chat. Each participant can request a copy in their own language. The translated file must look like the original — same fonts, same tables, same page numbers, same headers, same charts in place. **The budget:** No real-time constraint. A minute is fine. Two minutes is fine. The constraint is **fidelity** — if the translated PDF doesn't look like the original, the recipient won't trust it. ### Why this pipeline does not share an engine with voice A general LLM, even a very good one, will hand you back a translated *text* of a document. It will not hand you back a translated *PDF* with the same layout. The model has no concept of "page break that has to line up with the source" or "table cell that has to keep its column width." For this surface we use the **DeepL Document API** directly. It is purpose-built for translating *files as files*, not *prose extracted from files*. DeepL handles: - PDF (with layout preservation) - DOCX, DOC - PPTX - XLSX The document is uploaded to DeepL's pipeline, translated server-side with formatting intact, and returned as the same format. We then upload the result to our object storage and surface it back in chat as a downloadable attachment. ### What this costs and why we don't hide it DeepL bills a minimum of 50,000 characters per document — roughly one US dollar per file on the Pro tier, regardless of whether the document is one page or thirty. We absorb that cost rather than charging per file; it shows up in the meeting's translation usage as **billed characters**, converted to word-units that match the way the rest of the product reports translation activity. We picked DeepL for this surface because translating *files as files* is exactly the job it was built for — we did not try to build a better one. The same is not true the other way around — DeepL does not run a live-voice pipeline of the kind we built for meetings. Different problems; different tools. The honest version of "what powers InterMIND translation" is "the right engine per pipeline" — not "our engine, everywhere." ### Languages this pipeline covers that voice does not The document pipeline reaches **30 languages**, vs. 23 for voice. The extras include: Bulgarian, Greek, Estonian, Indonesian, Lithuanian, Latvian, Slovak, Slovenian. (Arabic is also on this list, and it is one of the extras: it is withdrawn from the real-time picker while its voice quality is below our bar, and its per-pair scores stay public on [`/benchmark`](https://intermind.com/benchmark) — that number is what brings it back. The asymmetry runs the other way for Hindi — live on voice, not yet on files.) That asymmetry is real. It means a French participant in a meeting can request the contract PDF in Estonian even though they cannot listen to the meeting in Estonian. We flag it in the picker rather than smooth it over with a single number. The reasoning is in the [language-count post](https://intermind.com/blog/how-many-languages-do-you-support). --- ## Where the pipelines meet The four pipelines do not run in isolation. A meeting room is where they touch each other, and the seams matter: - **A chat message with a document attachment** triggers the chat pipeline for the text and the document pipeline for the file. The participant in another language sees the message translated immediately and the attachment translation arriving asynchronously as a downloadable. - **A shared note that quotes a transcript line** crosses notes ↔ voice. The transcript is what the voice pipeline produced for the sender's language; the note translation produces a per-viewer copy of that quote in everyone else's language, with its source attribution preserved. - **A transcript exported after the meeting** runs the chat-style text pipeline over the full conversation, producing a per-language file that participants can download. This is the same code path as chat translation, just batched. The language picker is one piece of UI. The infrastructure underneath is four pipelines, talking to each other. --- ## What we deliberately do not try - **No "unified translation model."** We are not building one model that does voice, chat, notes, and documents. The latency vs. fidelity trade-off doesn't have a winner. We use the right engine per surface. - **No silent re-routing.** If the file pipeline can't translate to Hindi today, we don't quietly fall back to the voice engine and pretend it worked — the file picker flags the gap instead of hiding it. - **No "we translate to 200 languages."** Our engine emits 24. The live surfaces ship 23, documents 30 — and instead of one marketing-friendly number, the per-pair quality that has to stand in front of an auditor is published at [`/benchmark`](https://intermind.com/benchmark), weaker pairs included. --- ## Try it yourself - **[Try the live demo](https://intermind.com/demo)** — runs the live voice pipeline against your audio, in any of the 23 product languages. The same pipeline that scores [`/benchmark`](https://intermind.com/benchmark). - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month quality on real traffic. Every pair in the picker, strong or weak, deep-linkable. - **[Read the methodology](https://intermind.com/benchmark/methodology)** — what the numbers are, what they aren't, who the judge is. Four pipelines, four engines, one meeting room. That is the honest replacement for the old `how-it-works` page. — The Mind.com Team --- *Sources: [DeepL — supported languages](https://developers.deepl.com/docs/getting-started/supported-languages){rel=""nofollow""}, [DeepL — usage count and billing](https://support.deepl.com/hc/en-us/articles/360020685720-Usage-count-and-billing-in-DeepL-API){rel=""nofollow""} (the 50,000-character per-file minimum), [FLORES-200](https://github.com/facebookresearch/flores){rel=""nofollow""}; internal pipeline facts verified against the shipped code, checked August 2026.* # InterMIND for Slack: how it works — start a meeting with /intermind, get the recap back in the thread (2026) - **One slash command.** Type /intermind, the join link lands in the channel, and when the meeting ends the recap comes back as a reply in the thread. - **Five permissions, no reading of messages.** The app adds a command, posts messages and unfurls intermind.com links; no message sync, no calendar writes. - **InterMIND keeps the whole meeting in each member's language,** voice, chat and the recap, next to Slack rather than instead of it. Guests join free by link, no account; you pay only for active members. A team does not leave Slack in a day. It keeps the channels it has and tries a neighbouring tool on one job. The InterMIND app for Slack is built for that one job: the meeting. Type `/intermind` in a channel, the join link lands there; when the meeting is over, the recap comes back under the same message. Nobody has to open a second chat to find out what was decided. The short version: one slash command, five permissions, no reading of your messages, no message sync. ## What the command does | You type | What happens | | ------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `/intermind` | A meeting is created under your InterMIND account and the app posts the join link in the channel | | `/intermind Weekly sync` | The same, with a title | | `/intermind tomorrow 3pm Weekly sync` | The meeting is scheduled for that time; the join link is posted now, the meeting sits in your upcoming list, and the recap still comes back to the thread. Also `fri 15:00` and `2026-10-01 at 10:30` | | `/intermind timezone Europe/Berlin` | The time zone your scheduled times are read in — set once, from your browser's zone when you connect, or with this command | | `/intermind recaps here` | The recaps of **your** meetings — not only the ones started from Slack — go to this channel | | `/intermind recaps off` | Stops sending recaps to a channel | | `/intermind help` | Lists the commands, visible only to you | Anyone in the channel can open the link. A person without an InterMIND account joins as a guest and the host admits them — the same as with any InterMIND meeting link. In the meeting each participant speaks, hears and reads in the language they think in; that part happens in InterMIND, not in Slack. Scheduling from Slack does not write to your calendar: the join link and the time are in the channel, the meeting is in InterMIND, and **Add to calendar** on the meeting page puts it into Google or Microsoft Calendar when you want that. ## Where the recap goes - A meeting started with `/intermind` gets its recap as a **reply in the thread** of the message that started it. - Any other meeting you host goes to the channel you chose with `/intermind recaps here` — one channel per workspace, per person. - No channel chosen — nothing is sent to Slack. The Slack message carries the summary and an **Open the recap** link. The summary in Slack is written in the recap's language; the link opens the recap in InterMIND, where each reader gets it in their own language. The recap is produced only for a meeting that had speech to summarize — the same rule as for the recap email. In a private channel or a direct message the app can post only after it is invited (`/invite @InterMIND`). Until then the join link is still posted, and the recap arrives as a direct message from the app with a note saying why it is not in the channel. ## A pasted link becomes a card, and the app has a Home tab Paste an InterMIND meeting link or a recap link anywhere in Slack and the app replaces it with a card: the title, the host, the scheduled time when there is one, a **Join the meeting** button. A recap link becomes a card with the title and an **Open the recap** button — the recap's text reaches Slack only through the thread or the channel you chose. The card shows no more than the meeting's join screen shows to anyone who opens the link. Click **InterMIND** under Apps in the Slack sidebar: the Home tab tells you whether your account is connected and where your recaps go, lists the commands, and has a **Start a meeting** button. The join link comes to you as a direct message, ready to share, and that meeting's recap comes back to the thread of the message. ## Installing it, and who the host is The app is added from InterMIND: **Integrations → Slack → Add to Slack**, pick the workspace, approve. The person who adds it is connected right away. Everyone else connects their own account the first time they use the command: Slack shows them — and only them — a **Connect your InterMIND account** link. It works for 10 minutes and opens a page that names the Slack user, the workspace and the InterMIND account before anything is connected. Accounts are never matched by email address: a meeting started from Slack is hosted by the account its sender connected, and by nobody else's. That makes the host question simple. The meeting is yours: your plan, your meeting list, your recap. The app is available on every InterMIND plan. ## What the app can and cannot see The app requests five Slack permissions: | Slack scope | Slack's description | Why the app needs it | | ------------------- | ------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------- | | `commands` | "Add shortcuts and slash commands that people can use" | The `/intermind` command | | `chat:write` | "Send messages as your Slack app" | The join link and the recap | | `chat:write.public` | "Send messages to channels your Slack app isn't a member of" | Posting in a public channel without being invited first | | `links:read` | "View URLs in messages" — limited to the domains the app registers | Receiving the links to intermind.com that are posted; the app registers only that domain and gets only those links, not the message around them | | `links:write` | "Show previews of URLs in messages" | Replacing such a link with a card | It requests no scope for reading messages, files, channel lists or the member list, so it cannot read them. Slack sends the app four things: the command you typed (with the channel it was typed in), a link to intermind.com when one is posted, the notice that someone opened its Home tab, and the notice that the app was removed. When the app is removed from a workspace, InterMIND deletes that workspace's token and every account connection made through it. A workspace that installed the app before link previews existed keeps working as before; the Slack card in Integrations shows **Update permissions** there, and the same approval flow adds the two link scopes. One thing to decide consciously: a recap posted to Slack is stored by Slack, under your Slack workspace's retention and data-location settings — not under InterMIND's. If a meeting's recap should stay inside InterMIND, do not start that meeting from Slack and keep `recaps here` off. ## What it does not do - It does not sync messages between Slack channels and InterMIND channels, in either direction. - It does not write to your calendar; a meeting scheduled from Slack is added to Google or Microsoft Calendar from the meeting page, with **Add to calendar**. - It is not in the Slack Marketplace yet; it is installed from InterMIND Integrations. - Moving a workspace's history over is a separate path: the standard Slack export imports as InterMIND channels — see [Moving from Slack](https://intermind.com/migrate-from-slack). ## FAQ **How do I start a video meeting from a Slack channel?** With the InterMIND app installed, type `/intermind` in the channel — optionally followed by a title. The app posts a join link there; anyone in the channel can open it, and the person who typed the command is the host. **Can a meeting recap be posted to Slack automatically?** Yes. A meeting started with `/intermind` gets its recap as a reply in the thread of the join message. For all your other meetings, type `/intermind recaps here` in the channel that should receive them. **Does the InterMIND app read my Slack messages?** No. It requests `commands`, `chat:write` and `chat:write.public` — scopes for adding a command and posting messages — plus `links:read` and `links:write`, which give it the links to intermind.com that are posted and let it replace them with a card. It requests no scope that reads messages, files or members. **Can I schedule a meeting from Slack?** Yes. Start the command with a day and a time: `/intermind tomorrow 3pm Weekly sync`, `/intermind fri 15:00`, `/intermind 2026-10-01 at 10:30 Planning`. The join link and the time are posted in the channel at once, the meeting appears in your upcoming list, and the recap comes back to the same thread. Times are read in the time zone saved with your connection; `/intermind timezone Europe/Berlin` changes it. **Do my teammates need InterMIND accounts?** To start a meeting from Slack — yes, each person connects their own account once, because the meeting is hosted by that account. To join a meeting — no: they can join as guests and the host admits them. **Does it work in private channels and direct messages?** The command works everywhere. Posting the recap into a private channel needs the app invited there (`/invite @InterMIND`); otherwise the recap comes to you as a direct message from the app. **Which InterMIND plan includes the Slack app?** Every plan. The meeting itself follows the limits of the host's plan. **How do I remove it?****Disconnect** in InterMIND Integrations removes your own connection. A workspace admin removes the app in Slack; InterMIND then deletes the workspace's token and all connections made through it. ## Try it - **[Add InterMIND to Slack](https://intermind.com/slack)** — sign in, then Integrations → Slack → Add to Slack. - **[Read the Slack app docs](https://intermind.com/docs/integrations/slack)** — commands, permissions, where the recap goes. - **[Try the live demo](https://intermind.com/demo)** — what a meeting feels like before you start one from Slack. *Sources: Slack developer docs — [`commands` scope](https://docs.slack.dev/reference/scopes/commands){rel=""nofollow""}, [`chat:write` scope](https://docs.slack.dev/reference/scopes/chat.write){rel=""nofollow""}, [`chat:write.public` scope](https://docs.slack.dev/reference/scopes/chat.write.public){rel=""nofollow""}, [`links:read` scope](https://docs.slack.dev/reference/scopes/links.read){rel=""nofollow""}, [`links:write` scope](https://docs.slack.dev/reference/scopes/links.write){rel=""nofollow""}, [slash commands](https://docs.slack.dev/interactivity/implementing-slash-commands){rel=""nofollow""}, [unfurling links](https://docs.slack.dev/messaging/unfurling-links-in-messages){rel=""nofollow""}, [App Home](https://docs.slack.dev/surfaces/app-home){rel=""nofollow""}; [InterMIND — Slack](https://intermind.com/docs/integrations/slack){rel=""nofollow""}. Checked September 2026.* # The Meeting Room That Doesn't Switch to English - **Nobody in the room has to switch.** v1.2 made everything around the voice multilingual per viewer: chat edits as diffs in your language, notes line by line, documents inline. - **A dated record.** The numbers are those of May 2026: 21 live languages then, Arabic, Turkish and Hindi disabled; the current per-surface counts are in the language post. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes and the recap. Guests join free by link, no account; you pay only for active members. You schedule a cross-border meeting. People join from three time zones. Within ninety seconds someone says **"let's keep this in English so we're all on the same page"** — and you watch the most senior people in the room go quiet. That switch is a tax. On time, on confidence, on what actually gets decided. We've spent the last six weeks rebuilding InterMIND around the principle that **no one in the room should have to switch.** Not for the conversation. Not for the chat. Not for the notes you're typing live. Not for the edit history you'll review tomorrow. Here's what shifted. --- ## 1. Per-Viewer Everything, Not Just Voice Live voice translation has always been the headline — 21 languages, live, every participant picks their own language at the start of the call. v1.2 makes everything **around** the voice multilingual too, and keeps it in sync, per viewer, in real time. (For why "21" and not the bigger numbers other surfaces show, see [the breakdown](https://intermind.com/blog/how-many-languages-do-you-support).) ### Chat: every edit shows you what changed, in your language Every message in chat is translated as it's typed. The change in v1.2: when someone edits a message, we don't throw out their previous translation and serve you a fresh one. We compute the diff **between the previous translated text and the new translated text**, in your language — and show it inline. So when your colleague edits "we should review by Tuesday" to "we should review by Thursday," your Spanish reviewer doesn't see a re-translated paragraph and guess what moved. They see *martes → jueves*, highlighted. Same precision as a Git diff, but rendered in whichever of the 21 languages they read. If the edit changes only formatting — bold, italic, list markers — we re-translate anyway, because format-only edits are often where meaning shifts (a comma becomes a clause break). And the previous translation stays on screen while the new one streams in, so you never look at blank space waiting for the API to come back. ### Notes: live, character-by-character, per language The host opens the shared-note pane during the meeting and starts typing. Every participant sees the note in their language, character-by-character, as it is typed. Edit a line and viewers get a per-language diff — same model as chat edits. We also rewrote note translation to **translate list items individually instead of the whole document**. A nested checklist in English doesn't preserve its structure if you translate the markdown blob — the model flattens the hierarchy. Translating each `
  • ` independently keeps the indentation, the numbering, and the inline formatting intact in every language. ### Attachments: documents inside chat speak the room Drop a Google Doc, OneDrive link, or PDF into chat. v1.2 renders them inline: - **Linked docs** — title, preview, domain badge, no raw URL bleeding through. Editable docs open in a new tab with the right locale hint (`hl=`), so a Brazilian Portuguese reader doesn't land in an English Docs UI. - **Image uploads** — thumbnail on upload, intrinsic-grid responsive layout in the message bubble so images don't blow out at narrow widths. - **Three-tier document access** — *edit*, *view*, or *no-access* — with auto-share when permissions allow. Participants without Drive access still see a clean read-only preview, not a "permission denied" page. ### Lazy translation: faster, cheaper, less noisy We used to translate every message in your history when you switched languages. For long-running team channels that meant replaying hours of API calls for messages you'd never scroll back to. v1.2 uses an IntersectionObserver: translations happen on demand, when a message enters the viewport. Switching languages mid-meeting is now instant. We also stop chat-list polling immediately on 401, which silenced a runaway error stream you would never have noticed but we did. ### Voice transcription: sanitized before render Transcription text is sanitized before rendering — no HTML injection through a creative pronunciation. It sounds obvious. It also wasn't true two months ago. --- ## 2. The Note Editor Caught Up With the Conversation Notes and chat messages share a rich editor with: - **Slash menu** for headings, lists, code blocks - **AI Improve** transforms — pick a paragraph, rewrite for tone, expand, summarize, fix grammar — directly in the editor, no copy-paste round trip - **@-mentions** wired into participant data: type `@` and you see the live participant list - **Emoji picker** that doesn't drop out of position on narrow widths - **Image upload** straight into the message body AI Improve transforms run as single-chain inserts with no output-token cap (we hit that ceiling more than once during testing). Output is converted from markdown to HTML via `marked`, so the editor never shows you a raw `### Heading` artifact. A shared note can be opened in a new tab — useful when the meeting is on one monitor and the document needs a full second screen. Sidebar resize no longer gets stuck behind the iframe. --- ## 3. The Meeting Room Finally Has the Boring Parts Right A translation feature is meaningless if the meeting room around it doesn't hold up. v1.2 closes a long list of gaps you only notice when they fail. | Capability | What it does | Why it matters | | -------------------------------- | --------------------------------------------------------------------------- | ------------------------------------------------------------ | | **Host-only permissions** | Mic, camera, screenshare, chat — gated per participant from More → Settings | Moderation surface stops being a free-for-all | | **Conference guide modal** | Keyboard shortcuts and button explanations in one panel | New users find features without a tour | | **Note sharing on stage** | Pin a note next to your camera overlay; camera stays visible | Walk through a doc without losing the room | | **Two-mode read receipts** | *Present* (currently watching) vs *returned* (saw it later) | Beats the binary "delivered" lie | | **Pre-join deferred approval** | Guests see an approval-pending screen before they appear | No surprise joins, no awkward expulsions | | **Ad-hoc copy-link nudge** | Host joins alone? Toast asks if they want to copy the link | Closes the "am I the only one here, was the link sent?" loop | | **Raise-hand fix** | The button works again | It was broken; now it isn't | | **Forced dark theme in meeting** | Dark only while the meeting room is mounted | Less brightness whiplash mid-call | | **1-hour Basic cap** | Free meetings end at 60 min — more headroom than Zoom Free's 40 | Honest pricing surface | Translation runs full quality on every plan, including Free. --- ## 4. Teams That Don't Fight the Tool We rewrote the role and seat model from scratch on a strict **1-user-1-org** invariant. No lazy team creation. No ghost orgs. Owners cancel subscriptions; they don't get asked to transfer to nowhere. | Role | Scope | | ---------- | ---------------------------------------------------- | | **Owner** | Billing, domain management, every action below | | **Admin** | Invite, role changes, license grants — no billing | | **Member** | Meetings, chat, their own profile | | **Solo** | Personal contacts, personal meetings — no team scope | Licenses are assignable per seat, Zoom-style. Bulk operations from the Users table — make admin, make member, grant license, revoke license — apply across selection with a clear warning when only part of the bulk action will fit available seats. License switching is optimistic, no spinner waiting for the server. If you grant a seat and the next click would exceed the plan, a contextual **Buy more licenses** CTA appears exactly where you'd next try to grant one. Domain Management is gated to Business+ and clearly labeled, not silently hidden. Pending invitations clean themselves up. Self-service is real: members can't accidentally delete themselves, can't grant themselves admin, can't bulk-action their own row. Owners see Owner-only UI; members don't see it at all. The guest-access flow now lives outside the team boundary entirely. Hosts can approve a guest into the meeting without adding them to the team; the host's personal contacts get a separate *Add to contacts* option from the participants sidebar. --- ## 5. Honest Cuts, Honest Numbers A release post is also a chance to be straight about what didn't make it. **We disabled Arabic, Turkish, and Hindi for live voice/chat/notes during the alpha cycle.** Translation quality for those three didn't meet our bar at the time. We'd rather ship languages that work than pad the count with footnotes. (Update: Turkish and Hindi have since returned to the live picker; Arabic returned in July 2026 and was withdrawn again in August 2026 while the engine is below the bar in both directions — voice/chat/notes is 23 languages today, with per-pair quality published on [`/benchmark`](https://intermind.com/benchmark) instead of hidden behind the count. See [the full per-surface breakdown](https://intermind.com/blog/how-many-languages-do-you-support).) The picker names for Spanish, Portuguese, and Chinese now disambiguate region and script, because nobody should have to guess whether "Chinese" means simplified or traditional. **We retired `staging.intermind.com`.** `main` is the only long-lived branch. Production deploys are manual. CI on push to `main` runs lint + unit + integration on a Vercel preview and stops there — we don't auto-promote, which means we don't ship to prod by accident either. **We migrated the translation server from Amsterdam to Paris.** Measurable latency improvement for European users, with retry logic added in the same pass to absorb upstream provider blips. **We collapsed two Sentry projects into one** and split by environment tag. Two projects sounded organized; in practice it doubled the dashboards we had to check before believing anything. **Replay session sampling went down** because the previous rate was burning the entire org quota. The 4xx HTTP errors fall out of capture for the same reason — most were not actionable. We publish a **[public benchmark](https://intermind.com/benchmark)** with translation latency, quality scores, and the methodology. The methodology page includes a disclosure: before 2026-04-23, our chat harness was mis-counting some translation events, which inflated reported latency. We found it, fixed it, kept the bad numbers in the historical chart, and labeled them. That's the kind of disclosure that should be expected from anyone publishing a benchmark. In production we run **hourly synthetic E2E checks** through Checkly — full chat round-trip and full voice round-trip, including an LLM-scored translation-quality assertion — plus **Web Vitals monitoring** via Sentry Metric Alerts on every public page. When something breaks, we know within minutes, not the next morning. --- ## 6. Eight Use Cases — Try Before You Sign Up Telling people "we translate" doesn't land. We built eight use-case pages with animated demos for the scenarios that actually drive cross-border meeting need: 1. **Regulated multilingual meetings** — CAPA reviews, inspection prep, multi-site quality calls. The audit trail is multilingual end-to-end. 2. **Cross-border sales calls** — close in the buyer's language, keep your team's notes in yours. 3. **Multi-site engineering reviews** — design walkthroughs across plants where the technical vocabulary is the hard part, not the small talk. 4. **Remote technical interviews** — assess the engineer, not their English. 5. **Multilingual customer support** — every ticket conversation, in every language, with one rep. 6. **Language tutoring** — instructor speaks naturally; learner gets dual-language subtitles and chat. 7. **Online events and webinars** — one host, many language tracks, no relay interpreters. 8. **Remote consulting** — billable hours that don't get spent translating jargon. The [/use-case](https://intermind.com/use-case) listing page has the full set with CSS-animated demos. The [/demo](https://intermind.com/demo) route lets you experience translation against a scripted conversation — no account, no sign-up. --- ## What Else Shipped Compact list, for completeness: - **Site-wide localization** for ES / PT / RU / ZH with locale-prefix routing and `hreflang` on every public route - **Auto-translate i18n on commit** — we edit `en.json`, the other four locales are translated and re-staged in the same pre-commit hook (Gemini Flash → Sonnet fallback) - **Single translation-language override** — interface language and translation language used to be two settings that diverged; now they're one - **Bug reports with attachments** — on-demand screenshot, conference-button context, email delivery with a Sentry thread ID - **In-app reply to bug reports** — when we reply to your Sentry issue, the message lands back in your feed via an `@reply` convention - **G2 social proof carousel** with curated reviews on the landing page - **Sitemap + robots.txt** generation for SEO; redirected stray legacy URLs - **In-app docs with AI chat** — full knowledge base injected, search, walkable from [/docs](https://intermind.com/docs) - **Adaptive default page** — sidebar reorders based on which area you actually use --- ## Free Still Works The free-for-everyone alpha ran through June 2026; billing is now active. The Basic plan stays free forever — live voice and chat translation included, with a 1-hour meeting cap and no credit card. If you're going to test InterMIND for your team, every paid plan starts with a 14-day trial — you get the full Business experience without paying for it. → [Try the demo](https://intermind.com/demo) — no sign-up → [Create a free account](https://intermind.com/login) — 30 seconds → [See the use cases](https://intermind.com/use-case) — find your scenario — The Mind.com Team **Your team doesn't switch to English in the hallway. The meeting shouldn't make them switch either.** --- *Sources: [Zoom — plans and pricing](https://zoom.us/pricing){rel=""nofollow""} (Basic plan 40-minute meeting cap), checked August 2026. This is a release post — product numbers reflect v1.2 as shipped in May 2026; the current per-surface language counts are in [How many languages do you support?](https://intermind.com/blog/how-many-languages-do-you-support).* # The Language Barrier Ends Here - **Launched as a public alpha, free until June.** Pick a language in a call and hear everyone in your own: 21 languages with subtitles, chat translated as you type, guests in with host approval. - **A dated record.** The numbers and the self-description are those of 1 March 2026, not today's product; what InterMIND is now is on the home page. - **InterMIND keeps the whole meeting in each member's language,** voice, chat and the recap. Guests join free by link, no account; you pay only for active members. *A dated record. This is the alpha announcement as published on 1 March 2026; the numbers and the self-description below are that day's, not today's product. What InterMIND is now is on the [home page](https://intermind.com).* You spend years learning a language. You still can't close a deal in Mandarin. You still need an interpreter for the Tokyo call. You still lose nuance in every cross-border conversation. **What if you didn't have to?** Today we're launching the public alpha of InterMIND — and giving it away for free until June 2026. --- ## Why InterMIND Exists We stopped memorizing phone numbers when smartphones made it unnecessary. We abandoned manual calculations when calculators became ubiquitous. We no longer memorize directions since GPS navigation emerged. Language learning is one of the last inefficient allocations of human cognitive potential. The average person spends 600–1,000 hours to reach basic proficiency in a new language. Fluency requires 2,000+ hours. These are hours that could be invested in your actual expertise. **We believe language shouldn't determine who you can work with.** Geography shouldn't limit your ambitions. Culture shouldn't be a competitive disadvantage. InterMIND eliminates the need to spend years mastering foreign languages for practical communication — just as calculators eliminated mental arithmetic. Learn more about [our mission](https://mind.com/resources/company/about){rel=""nofollow""}. --- ## Not Translation. Not Interpretation. Something New. InterMIND is **conversational telepathy** — you think in English, they hear perfect Mandarin. They respond in Japanese, you understand every nuance. It preserves your voice, your tone, your personality — in any language. It captures context, cultural subtext, business intent. Unlike traditional translation tools that convert words, InterMIND **interprets meaning**, adapts tone, and facilitates seamless multilingual dialogue as if the language barrier didn't exist. > Speak naturally. Be understood perfectly. Close more deals. **How it works:** your speech is recognized, cleaned up (removing filler words, correcting errors), translated with context and cultural awareness, and synthesized back into natural speech — all in under 3 seconds, matching the speed of professional simultaneous interpreters. Learn more about [the technology behind InterMIND](https://mind.com/product/overview/how-it-works){rel=""nofollow""}. --- ## What You Get Today ### Speak and Listen in Your Language Join a video call, pick your language, start talking. Everyone hears the conversation in their native language — **21 languages**, live, with subtitles. No plugins, no setup, no interpreters. ([Why "21" and not "24" or "30"](https://intermind.com/blog/how-many-languages-do-you-support).) Chat messages are translated too — automatically, as you type, before you even hit send. ### HD Video Meetings — No Compromises InterMIND is a full video conferencing platform, not a translation add-on. HD video, screen sharing, cloud recording, laser pointer, reactions, hand raise — everything you'd expect, with translation built into the core. Create ad-hoc meetings with shareable links. Invite guests without requiring them to sign up — they get in with just a name, with host approval. ### Team Chat That Breaks Language Walls Persistent channels with every message auto-translated. See the original and translation side by side. Share files up to 500 MB with link previews. Real-time delivery via WebSocket — no refreshing, no waiting. ### Enterprise-Ready from Day One Google Workspace SSO with domain-based auto-join. Microsoft directory integration. Passwordless email sign-in. Role-based access control and bulk invitations. Export your data anytime. Built-in docs with search and AI chat assistant at [/docs](https://intermind.com/docs). --- ## Free During Alpha — No Credit Card Required Every feature. Every plan tier. Zero cost until June 2026. We're building InterMIND in the open and we need your feedback. During the alpha period, all users get unrestricted access to the full platform. See [pricing and plans](https://intermind.com/pricing) for what comes after the trial. --- ## Roadmap | Milestone | Date | What to expect | | ------------------------------- | ----------------- | ------------------------------------------------------- | | **v1.0.0-alpha** (this release) | March 1, 2026 | Full platform — free for all users | | **Extended trial** | Until June 2026 | No charges, no credit card needed | | **v1.0.0-beta** (paid) | June 2026 | Billing activated, new features based on alpha feedback | | **v1.0.0** (GA) | September 1, 2026 | General availability — stable, production-ready release | --- ## Get Started in 30 Seconds 1. **Try the demo** — no sign-up required: [/demo](https://intermind.com/demo) 2. **Create a free account**: [/login](https://intermind.com/login) 3. **Start your first translated meeting** Have feedback? Use the in-app bug report (with screenshot capture) or reach out via support chat. We're not building a translator. **We're building a bridge between worlds.** — The Mind.com Team **Stop pretending you understood that meeting.** Everyone speaks their language. Everyone understands. Instantly. # Interpretation vs translation: what's the difference — and every type of interpretation explained (2026) - **Interpreters talk, translators write.** Interpretation converts spoken or signed language live, while the communication happens; translation converts written text after it exists, with time to revise. - **The type follows the situation.** Simultaneous for conferences and working meetings, consecutive for medical and legal appointments, an accredited human wherever the interpretation is the legal record. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes and documents in the call, per-pair quality published. Guests join free by link, no account; you pay only for active members. **Interpretation is the conversion of spoken (or signed) language into another language, live, while the communication is happening. Translation is the conversion of written text from one language to another, done after the text exists.** The American Translators Association compresses it into one line: [translators do the writing, interpreters do the talking](https://www.atanet.org/client-assistance/translator-vs-interpreter/){rel=""nofollow""}. The two words get used interchangeably in everyday speech — "we need a translator for the meeting" almost always means *interpreter* — but they name different professions, different skills, different tools, and different buying decisions. This guide gives you the working definitions, a side-by-side comparison, every type of interpretation with the situations each one fits, and where AI now sits in the picture. --- ## What is interpretation? **Interpretation is real-time language conversion of speech.** An interpreter listens to a speaker in one language and renders the meaning — not the word-for-word text — in another language, either while the speaker is still talking (simultaneous) or in the pauses between their sentences (consecutive). The output is ephemeral: it exists in the moment, for the people in the room or on the call, and is gone when the meeting ends. Because it happens live, interpretation allows no second draft. The interpreter carries everything — vocabulary, tone, cultural context, the speaker's intent — in working memory, at the speaker's pace. That is why the United Nations, where sessions run in [six official languages rendered simultaneously into the other five](https://www.un.org/dgacm/en/content/interpretation){rel=""nofollow""}, treats conference interpreting as one of the most demanding language professions, and why professional simultaneous interpreters [work in pairs and swap roughly every 30 minutes](https://akjournals.com/abstract/journals/084/9/2/article-p261.xml){rel=""nofollow""}. ## What is translation? **Translation is the conversion of written text.** A translator works on a document that already exists — a contract, a website, a subtitle file, a medical record — and produces a new written document in the target language. The work happens after the fact, with time to research terminology, consult reference material, use translation-memory tools, and revise. The output is durable: a text that can be reviewed, certified, and reused. That review step is the practical dividing line. A translated contract can be checked word by word before anyone signs it. An interpreted negotiation cannot — which is why the two professions certify differently and price differently, and why "can I get it in writing?" is a translation question even when the meeting itself was interpreted. ## Interpretation vs translation: the difference at a glance | | Interpretation | Translation | | ------------------- | ----------------------------------------------- | ----------------------------------------- | | **Medium** | Spoken or signed language | Written text | | **When it happens** | Live, in real time | After the source text exists | | **Direction** | Often both ways in one session | Usually one way per assignment | | **Deliverable** | Ephemeral — heard, then gone | Durable — a document you can review | | **Time to work** | Seconds (simultaneous) to a pause (consecutive) | Hours to weeks, with revision | | **Tools** | Booth/console, receivers, or a platform | CAT tools, translation memory, glossaries | | **Fidelity target** | Meaning and intent, at speaking pace | Full accuracy, reviewable word by word | | **Typical pricing** | Per interpreter, per day or hour | Per word or per page | Two consequences follow directly from the table. First, the skills barely overlap: an outstanding contract translator may be unable to interpret a meeting, and vice versa — hiring one to do the other's job is a category error, not a compromise. Second, machine assistance entered the two fields at different speeds: machine translation of text has decades of history, while machine *interpretation* — live speech, both directions, at conversation pace — only became practical recently. We cover that shift [below](https://intermind.com/#ai-interpretation). ## Types of interpretation "Types of interpretation" mixes two independent axes that are worth separating: the **mode** (how the interpreting itself is timed and delivered to the listener) and the **delivery format** (where the interpreter is and how the audio reaches you). ### The modes | Mode | How it works | Typical setting | | -------------------------- | --------------------------------------------------------------------------------------------------- | ------------------------------------------------------------- | | **Simultaneous** | Interpreter renders the speech while the speaker is still talking; listeners hear it seconds behind | Conferences, multilingual meetings, broadcasts, the UN | | **Consecutive** | Speaker pauses every few sentences; interpreter renders the segment | Medical consultations, depositions, site visits, interviews | | **Whispered (chuchotage)** | Simultaneous interpretation whispered directly to one or two listeners, no equipment | A delegate or executive in a room running in another language | | **Liaison (bilateral)** | Interpreter alternates between both languages in a back-and-forth exchange | Negotiations, escorted visits, small two-party meetings | | **Sight translation** | A written document read aloud in another language on the spot | Forms and letters inside a medical or legal appointment | **Simultaneous interpretation** is the mode that scales: the meeting runs at full speed, any number of languages can run in parallel (one channel per language), and listeners choose their channel. Its historical cost — soundproof booths, two interpreters per language, day rates — is what made it an event-day service rather than an everyday one. We wrote a full plain-language guide to it: [Simultaneous interpretation: what it is, how it works, and when AI can do it](https://intermind.com/blog/simultaneous-interpretation-guide). **Consecutive interpretation** trades time for simplicity: no equipment, but the meeting takes roughly twice as long, because everything is said twice. It shines where precision per sentence matters more than pace — a diagnosis, a sworn statement, a contract clause read aloud. **Whispered and liaison** interpretation are small-scale variants of the two modes above — worth knowing by name because agencies quote them separately, but nearly every real decision reduces to *simultaneous vs consecutive*. ### The delivery formats | Format | What it is | What it changes | | ----------------------------- | ----------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | | **On-site** | Interpreter physically present (booth or beside the listener) | The traditional baseline: highest setup cost, hardware in the room | | **OPI — over-the-phone** | Interpreter joins by phone, on demand | Minutes-based pricing, audio only, no visual context | | **VRI — video remote** | Interpreter joins by video call | Adds visual context (critical for sign language); common in hospitals | | **RSI — remote simultaneous** | Interpreters work from a hub or home via a platform; audio streams to each listener's device | Removes booths, receivers, and travel from simultaneous interpreting | | **AI interpretation** | A speech pipeline (recognition → translation → synthesis) interprets continuously, per listener | Removes the booking and the per-day rate; interpretation becomes a software feature | The formats are a cost story. On-site simultaneous is the most expensive configuration in language services: per interpreter, per language, per day, plus equipment. OPI and VRI made *consecutive* interpretation available on demand — a hospital doesn't schedule a Tagalog interpreter for a possible emergency; it dials one. RSI did the same restructuring for *simultaneous*: the interpreters are still professionals at day rates, but the booth, the receivers, and the travel are gone. And AI interpretation removes the remaining constraint — the booking itself — which changes *which meetings get interpreted at all*. The weekly sync between Berlin, São Paulo, and Tokyo was never going to book two interpreters per language pair; with AI it doesn't have to. ## Which type do you need? Match the situation, not the terminology: - **A conference, summit, or multilingual event** → simultaneous. Human (on-site or RSI) for headline stakes and budget to match; AI for the sessions, breakouts, and events that a booth budget would exclude. What that looks like in practice: [events and conferences](https://intermind.com/use-case/events). - **A medical appointment or patient conversation** → consecutive, usually via VRI or OPI on demand; in several jurisdictions qualified interpreters in healthcare are a legal requirement, not a courtesy. For multilingual telehealth and staff meetings, AI interpretation covers the everyday layer: [healthcare](https://intermind.com/use-case/healthcare). - **A working meeting, webinar, or recurring cross-border call** → this is the space human interpretation never reached (nobody books a booth for a stand-up) and where [AI simultaneous interpretation](https://intermind.com/features/simultaneous-interpretation) is the native fit: every participant picks a language, the meeting runs at full speed. - **A court hearing, sworn deposition, or certified proceeding** → an accredited human interpreter, full stop. Where the interpretation *is* the legal record, machine output doesn't qualify — and vendors claiming otherwise should worry you. - **A document — contract, report, website, patent** → that's translation, not interpretation. Different professional, different certification, priced per word. (If the document comes up *inside* a live meeting, that's the one place the two jobs meet — see below.) []{#ai-interpretation} ## Where AI fits: machine interpretation AI entered translation and interpretation asymmetrically. Machine translation of text is decades old and everywhere. Machine **interpretation** — live speech in, live speech out, both directions, at conversation pace — became practical only when speech recognition, machine translation, and voice synthesis each got fast enough to chain at conversation pace. We build one of these systems, so here is the honest shape of the category rather than a pitch: - **What AI interpretation does today:** continuous simultaneous interpretation of a meeting, per listener, with no booking and no per-day rate. In InterMIND's case that is 23 languages of live voice, with each speaker's **own voice** preserved via zero-shot synthesis rather than one synthetic narrator ([how that works](https://intermind.com/blog/own-voice-translation)) — plus the parts of a meeting a human interpreter was never asked to cover: chat messages, shared notes, and documents dropped into the call, translated inline. - **What to demand from any vendor, ours included:** published per-language-pair quality, not a language count. "Supports 60 languages" says nothing about *your* DE↔EN. Ours is measured monthly on FLORES-200 and published in full at [/benchmark](https://intermind.com/benchmark) — or [run the live demo](https://intermind.com/demo) and judge with your own ears. - **What AI interpretation does not do:** replace accredited interpreters in certified settings. Courts, treaty negotiations, and sworn proceedings belong to humans. AI's territory is the enormous space below that bar — the meetings that never got interpretation because booths and day rates priced them out. The major meeting platforms sit at intermediate points: Zoom and Teams offer [interpretation](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0064768){rel=""nofollow""} [channels](https://support.microsoft.com/en-us/office/use-language-interpretation-in-microsoft-teams-meetings-b9fdde0f-1896-48ba-8540-efc99f5f4b2e){rel=""nofollow""} for human interpreters you source and pay yourself, all three offer translated captions on qualifying plans, and Google Meet ships [Gemini speech translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""} on qualifying plans. If you're comparing tools rather than learning the category, the buyer's guide does that comparison with sources: [best AI translation tools for conferences and meetings](https://intermind.com/blog/best-ai-conference-translation-tools). --- ## FAQ **What is the difference between interpretation and translation?** Interpretation converts spoken (or signed) language live, while the communication happens; translation converts written text, after the text exists. An interpreter works in real time with no revision pass; a translator works on a document with time to research and revise. They are separate professions with separate certifications. **What are the main types of interpretation?** By mode: simultaneous (rendered while the speaker talks), consecutive (rendered in the speaker's pauses), whispered/chuchotage (simultaneous, whispered to one or two listeners), and liaison (back-and-forth in small exchanges). By delivery: on-site, over-the-phone (OPI), video remote (VRI), remote simultaneous (RSI), and AI interpretation. **What is simultaneous interpretation?** Interpretation delivered in parallel with the speaker — listeners hear their language a few seconds behind, and the meeting never pauses for translation. It's how the UN runs sessions in six languages and how multilingual conferences keep one agenda. Full guide: [simultaneous interpretation explained](https://intermind.com/blog/simultaneous-interpretation-guide). **Is an interpreter the same as a translator?** No. An interpreter works with live speech; a translator works with written text. The skills barely overlap — one profession trains working memory and real-time delivery, the other trains research, writing, and revision. Someone who does both exists, but each role is hired, certified, and priced separately. **Which is harder, interpretation or translation?** They are hard differently. Interpretation compresses everything into real time — no dictionary, no second draft, meaning rendered at the speaker's pace, which is why simultaneous interpreters work in pairs and rotate every \~30 minutes. Translation demands a different rigor: full accuracy on a text that will be reviewed word by word, sometimes certified and legally binding. **Can AI do interpretation?** For everyday meetings, webinars, and events — yes: AI systems now interpret live speech continuously, per listener, in both directions. Quality varies by vendor and language pair, so verify rather than assume: check published per-pair benchmarks ([ours is here](https://intermind.com/benchmark)) or [hear it live in the demo](https://intermind.com/demo). For certified settings — courts, sworn proceedings — accredited human interpreters remain the only qualifying option. **Do Zoom, Teams, or Google Meet include interpretation?** Partially. Zoom and Teams provide interpretation channels for human interpreters you hire yourself, and all three platforms offer translated captions on qualifying plans; Meet additionally ships Gemini speech translation on qualifying plans. None of it is turnkey full-meeting interpretation — the per-platform breakdowns are here: [Zoom](https://intermind.com/blog/zoom-live-translation), [Teams](https://intermind.com/blog/teams-live-translation), [Meet](https://intermind.com/blog/google-meet-live-translation). --- ## See the difference, live Definitions explain the category; hearing it settles it. - **[Run the live demo](https://intermind.com/demo)** — hear live speech interpreted into another language on the production pipeline — no signup needed. - **[Read the benchmark](https://intermind.com/benchmark)** — per-language-pair quality, measured monthly, published in full. - **[AI simultaneous interpretation, in detail](https://intermind.com/features/simultaneous-interpretation)** — how live interpretation works inside an InterMIND meeting. - Picking who does it: [human interpreter, RSI platform, or AI](https://intermind.com/blog/simultandolmetscher) — and what each costs and covers for a meeting, in [simultaneous translation: booth, RSI, or AI](https://intermind.com/blog/traduction-simultanee). — The Mind.com Team --- *Sources: [ATA — Translator vs. Interpreter](https://www.atanet.org/client-assistance/translator-vs-interpreter/){rel=""nofollow""}, [United Nations DGACM — Interpretation](https://www.un.org/dgacm/en/content/interpretation){rel=""nofollow""}, [Chmiel — Boothmates forever? On teamwork in a simultaneous interpreting booth](https://akjournals.com/abstract/journals/084/9/2/article-p261.xml){rel=""nofollow""} (two interpreters per booth, \~30-minute turns), [Zoom — Using language interpretation in meetings and webinars](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0064768){rel=""nofollow""}, [Microsoft Teams — Use language interpretation in meetings](https://support.microsoft.com/en-us/office/use-language-interpretation-in-microsoft-teams-meetings-b9fdde0f-1896-48ba-8540-efc99f5f4b2e){rel=""nofollow""}, [Google Meet — Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, checked August 2026. Vendors change plans and language lists over time — check their pages for the current state.* # Is your meeting confidential? - **Only if three questions have checkable answers.** Who processes your words besides the people in the room, what remains afterwards and who decides, and whose laws apply. - **Our answers are published, hop by hop.** Translation on our own engine in France, the recap on the AI gateway your organization selects in the EU, with zero data retention. - **InterMIND keeps the whole meeting in each member's language,** voice, chat and the recap, every sub-processor named. Guests join free by link, no account; you pay only for active members. People say things in meetings they would never put in an email. Salary bands. A candid read on a partner. The negotiation floor. Legal strategy. That's what meetings are *for* — the medium where you can still think out loud. Which makes it odd how rarely anyone asks where all that thinking-out-loud actually goes. The words leave your mouth, become audio, hit a server, possibly feed a model, possibly become a transcript, possibly get retained under a policy you agreed to by clicking "join." "Confidential" on a vendor homepage tells you nothing about any of that. We put the word on our homepage too. So here's what we think it should be required to mean — three questions concrete enough to check, and our answer to each. Not because you should trust the answers, but because every one of them is verifiable, which is the only kind of confidentiality claim worth making. ## Question 1: Who processes your words, besides the people in the room? A translated meeting is, unavoidably, a processed meeting. Speech becomes text, text becomes another language, an AI writes the recap. The confidentiality question isn't *whether* machines touch your words — it's **which machines, run by whom, under what terms**. Our answer: voice and chat translation run on **our own engine, on dedicated servers in France** — not routed through generic third-party translation APIs, so your negotiation doesn't transit a consumer service. The AI features that do use an external model (the recap, document summaries, the writing assistant, Ask AI) run on **the AI gateway your organization selects, in an EU region** — Azure OpenAI in the EU Data Zone by default, Vertex AI EU or Amazon Bedrock Frankfurt by choice, or your own endpoint — with zero data retention and no training on customer content: your meeting content is processed for the feature, not stored by the provider. The vendors behind the hosted gateways are US companies operating EU regions, stated plainly on our trust page. Document translation goes through exactly one named sub-processor (DeepL's Document API, for file-format support), disclosed on our sub-processor list rather than "available on request." The checkable part: every vendor that touches meeting data is [named on the page, with what it does and where it's domiciled](https://intermind.com/features/security). ## Question 2: What remains afterwards — and who decides? A meeting leaves traces: chat history, files, recaps, sometimes a recording. Confidentiality isn't the absence of a record (a record in your language is half the product's value — [we've argued it's the half the industry forgets](https://intermind.com/blog/the-meeting-a-week-later)). It's **the record being yours**: - **Recording is a host decision.** It's available when the host turns it on — not a default, not a vendor's background process. - **Retention is yours to end.** Data is kept until you or your team owner delete it — the criterion is written in the privacy policy, not implied. - **Deletion actually deletes.** Erasing an account cascades across the database and sweeps every storage blob, recordings included. We audited our own codebase to make sure the cascade runs — and [published what we found and fixed](https://intermind.com/blog/gdpr-audit-what-we-closed). ## Question 3: Whose laws apply to the room? Where data lives decides who can compel it and which rules protect it. For a bakery's stand-up, academic. For a bank, a clinic, a bidder in a public tender — the first question procurement asks. Our answer: **EU at every runtime hop.** The translation engine runs in France, meeting orchestration in Paris, the database in Frankfurt; storage and analytics are EU-resident too. That's a jurisdiction you can name in a compliance review, not a region-of-convenience that shifts with the vendor's load balancer. ## The quieter half: data never collected One more property, easy to miss: **your guests join by link, with no account.** No sign-up means no profile, no address book upload, no identity graph of everyone who ever attended your meetings. The least exposed data is the data that was never collected — and it's also just [how hospitality should work](https://intermind.com/blog/give-every-guest-their-language). ## Make any vendor answer the same three questions Take this list into your next procurement call — it works on us too: 1. Which companies process meeting content, and is the list published? 2. Does any AI feature retain meeting content after processing? Under what terms — marketing copy, or contract? 3. In which jurisdictions does meeting data live, hop by hop? 4. Who can start a recording, and can participants tell? 5. When a customer deletes data, what proves the deletion ran — policy text, or an audited cascade? If the answers arrive quickly and specifically, you're talking to a vendor who expected the questions. Our full set — DPA with a 72-hour breach window, sub-processor list, uptime terms, the GDPR audit — lives at [Privacy & Security](https://intermind.com/features/security), one click deep, where procurement can get properly bored. ## Check it yourself - **[Read the security page](https://intermind.com/features/security)** — infrastructure, encryption, sub-processors, DPA, the audit. - **[See where the AI features run](https://intermind.com/blog/meeting-ai-on-your-own-cloud-gateway)** — the hyperscaler gateway your organization already uses, and the per-organization off switch. - **[Try the live demo](https://intermind.com/demo)** — no signup required, which is itself a data-collection answer. - **[How a meeting actually runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs)** — the infrastructure map, hop by hop, for the technically curious. --- ## FAQ **Is a video meeting confidential by default?** No platform can promise that as a default — it depends on who processes the audio, what's retained afterwards, and where the data lives. Those are answerable questions: ask for the sub-processor list, the AI retention terms, and the jurisdiction of each hop. A vendor with real answers publishes them. **Does live translation mean an AI is listening to my meeting?** Yes — translation is processing, there's no way around that. What differs between vendors is which machines process it and what they keep. In InterMIND, voice and chat translation run on our own engine on dedicated EU servers, and the recap AI runs on the gateway your organization selects, in an EU region, with zero data retention and no training on customer content. **Who can record an InterMIND meeting?** Recording is controlled by the host — it's available when the host enables it, never a background default. Access controls cover who can join, present and record. **What happens to meeting data when I delete my account?** Deletion cascades across the database and sweeps every storage blob, recordings included. Retention until that moment is under your control — data is kept until you or your team owner delete it, per the published policy. **Where is InterMIND meeting data processed?** In the EU at every runtime hop: translation engine on our own infrastructure in France, meeting orchestration in Paris, database in Frankfurt, EU-resident storage and analytics. Document translation uses one named EU-disclosed sub-processor (DeepL), listed publicly. --- *Sources: [DeepL — data security](https://www.deepl.com/en/pro-data-security){rel=""nofollow""}, checked August 2026. InterMIND claims in this post are documented on [Privacy & Security](https://intermind.com/features/security) — infrastructure, sub-processor list, DPA and the GDPR audit report — and in [the audit write-up](https://intermind.com/blog/gdpr-audit-what-we-closed).* # Where Microsoft Teams and Google Meet store your transcript, recording and summary — and how to keep them after the call - **Not with the recording.** Teams keeps transcript, recording and AI recap in three places with three permission lists; Meet, one transcript file per start. - **Moving one does not move the others.** Microsoft documents that captions aren't fully supported once a recording is moved; past translated transcripts aren't stored. - **InterMIND keeps the whole meeting in each member's language,** summary, transcript and recording on one link, next to Teams or Meet rather than instead of them. Guests join free by link, no account; you pay only for active members. *Where did Teams put the transcript?* is what people type into a search box the day after a meeting, and the honest answer is: not where the recording went. The tooling did its job — a transcript with names and time stamps, a summary, action items with owners. Then you filed the recording somewhere sensible, a SharePoint library or a shared drive, and the rest of it didn't come along. Or a colleague on Linux, in another tenant, or on the phone dial-in, opens the link and sees nothing. Nobody made a mistake. On the major platforms **a meeting does not produce one artifact, it produces three or four**, each with its own storage location, its own permission list, its own expiry policy and — for the AI summary — its own license. "Preserving the meeting" means preserving all of them, in place, with the right people still attached. This post is the documented map: where each vendor puts each artifact, who can still open it afterwards, what breaks when it moves, and what the alternative looks like when the meeting is a place rather than a folder of files. Vendor facts are from their own help pages, checked September 2026; links are in the footer. ## Microsoft Teams: four objects, four rulebooks **The recording.** For meetings and events, "the recording saves to the organizer's OneDrive, even if the organizer didn't attend the meeting or event." For channel meetings it goes somewhere else entirely — "the recording is stored in the SharePoint Teams site documentation library in a folder named `Recordings`." For 1:1 and group calls it lands in the OneDrive of whoever pressed Record. **The transcript.** A separate object in a separate place: "Teams live transcripts for meetings with recording and/or transcription are stored in the meeting organizer's OneDrive for Business. The transcript can be accessed through the meeting chat and Recap tab in Teams until a meeting organizer deletes the transcript." When the call is over, "the transcript is immediately available in the meeting event on the calendar. By default, meeting organizers and co-organizers can download it as a `.docx` or `.vtt` file." **The AI recap.** Also separate, and licensed separately: intelligent recap is listed by Microsoft under "Teams Premium and Microsoft Copilot", where "licensing and the transcription policy control this feature. Users with a Teams Premium or Microsoft Copilot license automatically have access to this feature." **And this is the sentence that explains the missing captions:** > Closed captions aren't fully supported if the Teams meeting recording is moved or copied from its original location in OneDrive or SharePoint. That is Microsoft's own admin documentation. The captions shown during playback are "available during playback if transcription was turned on at the time of recording" — they are bound to the recording where it was born, not carried inside the video file. Move the file, and you have moved one of the four objects. ### Who can still open it Microsoft publishes the after-the-meeting access matrix for transcripts. Condensed, and quoting the cells: | Participant | View transcript after meeting | Download transcript after meeting | | ----------------------------- | ----------------------------- | -------------------------------------------------------------- | | Organizer | Yes | Yes | | Person from same organization | Yes | "No, but organizers can configure who can download on Stream." | | Person from another tenant | No | No | | Anonymous | No | No | Microsoft adds: "People who call into a meeting can't view the transcript." For recordings the ownership rule is stated just as plainly — "the meeting organizer automatically owns the recording. By default, only meeting organizers and co-organizers can download or delete the recording," and "for now, guests and external attendees can view the recording only if it's explicitly shared with them." ### What expires, and what was never captured Expiry is an admin setting, not a property of the file: "your admin settings determine a recording's expiration," and the admin surface for it is documented as "manage when recordings and transcripts expire for your organization." An owner whose recording expires "will get an email when it expires. At that point, they'll have up to 90 days to recover it from the recycle bin." Some of the meeting is never in the recording at all. Microsoft lists what meeting recordings won't capture: "more than four peoples' video streams at once," "whiteboards and annotations," "shared notes," "content shared by app," and "videos or animations embedded in PowerPoint Live presentations." And on the reader's language, Microsoft is explicit twice over: live translated transcription "is available as part of Teams Premium," and "past translated transcripts aren't stored. Only the original transcript is stored." Changing the spoken language changes it for the room — "when you change the spoken language setting, the transcript and caption language will change for everyone." ### The client question The situation that starts most of these threads is not really about storage. Microsoft's client availability table lists Windows ✅, macOS ✅, **Linux ❌ — "Teams is no longer supported on Linux"** — and Web ✅, "supported in Microsoft Edge, Chrome, Firefox, Safari." A team that is mostly on Linux is a team on the web client, and the artifacts above still live in one person's OneDrive. ## Google Meet: a file per start, in the host's Drive Google's transcripts documentation is equally concrete. "Meeting transcripts are saved in the meeting organizer's Google Drive in the `Google Meet` folder," in per-meeting sub-folders, and "you get a separate transcript file each time you start Transcripts" — stop and restart during a call and you have two files. Distribution is by email plus a calendar attachment: after the meeting "an automated email with a link to the meeting transcript is sent to: the host, any co-hosts, the person who turned on Transcripts." The transcript "is also attached to the meeting's Google Calendar event. All invitees in the host's organization can open the attachment," except that "if there are more than 200 invitees in the host's organization, the transcript is only available to the host, co-hosts, and the person who turned on Transcripts in the meeting." Two limits worth writing down before you rely on it. Scope: "only the spoken words in a meeting are included in the transcripts. To get a transcript of chat messages, record your video meeting." Language: "meeting transcripts are available in: English, French, German, Italian, Japanese, Korean, Portuguese, Spanish" — eight. And access is device-shaped: "you can only use the Transcripts feature on a computer, laptop, or Android device." Transcripts are a premium feature, listed for Business Standard, Business Plus, Enterprise Starter, Enterprise Standard, Enterprise Plus, Teaching and Learning Upgrade, Education Plus and Workspace Individual. ## What it looks like when the meeting is a place InterMIND was built the other way round: the meeting is an event inside a space that outlives it, so the artifacts are not files to be filed. Everything below is how the product works today. **One page, one permanent link.** After a transcribed meeting, the recap is a single page holding the summary, the full speaker-by-speaker transcript, and the recording when the session was recorded. The recap link is permanent and serves every session of the meeting: a channel that has met twelve times has twelve session cards on one page, each with its own Summary and Transcript tabs. There is nothing to move, because there is no file to move. **Access is identity, not file permissions.** Recaps are members-only: opening the link requires signing in, and only meeting members — the host and the people who participated — get access. Forwarding the link to someone who wasn't there does not grant access. This is the same rule for the transcript and the recording, because they are views of one thing rather than three objects with three sharing dialogs. It also has an honest edge: someone who joined as an unauthenticated guest has no account for the recap to belong to, so post-meeting artifacts go to signed-in members. **The summary has a shape.** It is not a paragraph. The recap carries an overview, key takeaways, topic sections, negotiated points each marked **agreed / open / disputed** with who stated them and when, action items with the owner attached, and open questions that were raised and never resolved — each anchored to the moment in the transcript it came from. **It can be corrected, and the correction is auditable.** Meeting members can edit the AI summary directly on the recap page. Every edit creates a revision, and version history shows the AI original and each edit as a word-level diff with author and timestamp. The recap message in chat updates to match. **Every member reads it in their own language.** When the meeting is finalized, the summary *and the transcript* are translated into every participant's language right then, so each person opens their own version instantly rather than waiting on a translation. That covers 23 languages for voice, chat and notes. The transcript is generated in the speakers' original languages, and the translated copy is stored rather than rendered once and thrown away. **It arrives where people already are.** The recap link goes out by email; a recap message is posted to the channel chat; the meeting's calendar event carries the link. Hosts can also add confirmed BCC addresses — a CRM or tracker inbound mailbox, up to ten, on every plan. **You can take the whole thing with you.** Settings → **Backup & Restore** exports all your chats as a ZIP: chat messages, transcription records, files, images and conference recordings. It is available on every plan, including the free Basic tier, and restore puts selected chats back with their metadata — pins, reactions, translations, file names and types. Deletion is symmetrical and explicit: the host can delete a session's summary, transcript, recording and their translations, permanently. **Any operating system.** It is a web app; a Linux desktop is a browser like any other, and there are native mobile and desktop apps for people who want them. Two honest limits. Channels keep the recap of every past session; **ad-hoc meetings keep only the latest session's recap**, mirroring how their chat history is purged after each call — if you want the archive, meet in a channel. And InterMIND has no live transcription feature: the persistent trace of what was said is the post-meeting transcript and recap, not a word-for-word live feed. ## Side by side Documented facts from each vendor's own help pages, checked September 2026. Where a page doesn't state something, the cell says so. | | InterMIND | Microsoft Teams | Google Meet | | --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Where the transcript lives | on the meeting's recap page, one permanent link, alongside summary and recording | organizer's OneDrive for Business; reachable from meeting chat and the Recap tab "until a meeting organizer deletes the transcript" | organizer's Google Drive, `Google Meet` folder; a separate file per start; also attached to the Calendar event | | Who can open it afterwards | signed-in meeting members — host and participants | organizer yes; same organization yes; another tenant no; anonymous no; dial-in callers can't view it | host, co-hosts and whoever started it by email; all invitees in the host's organization via the Calendar attachment (host/co-hosts/starter only above 200 invitees) | | Download | Backup & Restore ZIP of all your chats — messages, transcriptions, files, images, recordings — on every plan | `.docx` or `.vtt`, organizers and co-organizers by default; same-org "no, but organizers can configure who can download on Stream" | not stated in the transcripts article | | If the recording is moved | nothing to move — one link, one page | "Closed captions aren't fully supported if the Teams meeting recording is moved or copied from its original location in OneDrive or SharePoint" | not stated in the transcripts article | | Summary with decisions and action items | included on every plan; overview, takeaways, points marked agreed/open/disputed, action items with owners, open questions | intelligent recap — "users with a Teams Premium or Microsoft Copilot license automatically have access to this feature" | not stated in the transcripts article | | Correcting the summary | members edit it in place; every edit is a revision with a word-level diff, author and timestamp | not stated | not stated | | Expiry | kept until the host deletes it; channels keep every session, ad-hoc meetings keep the latest | "Your admin settings determine a recording's expiration"; admins manage when recordings and transcripts expire | not stated in the transcripts article | | Reader's language | summary and transcript translated into every participant's language when the meeting ends; 23 languages | "Past translated transcripts aren't stored. Only the original transcript is stored"; live translated transcription is Teams Premium | transcripts available in eight languages | | Where it runs | web app in any browser, plus mobile and desktop apps | Windows and macOS apps; "Teams is no longer supported on Linux"; web in Edge, Chrome, Firefox, Safari | Transcripts: "a computer, laptop, or Android device" | The middle and right columns are not oversights. They follow from treating meeting output as files: a file has one home, one owner and one ACL, and the summary that describes it is a fourth thing bought separately. The left column follows from treating meeting output as the contents of a room the team keeps. ## If you're staying on your current stack Four things worth doing this week, all from the documentation above: 1. **Find out who owns the artifacts.** On Teams that is the organizer's OneDrive, or the channel's SharePoint library for channel meetings; on Meet, the organizer's Drive. Ask what happens to those meetings when that person changes role or leaves. 2. **Check the expiry policy before you need the file.** Teams expiry is an admin setting; the recycle-bin window after expiry is 90 days. That is a question for your admin, not a setting on the video. 3. **Leave the recording where it was created.** Moving or copying it is exactly the step Microsoft documents as breaking caption support. 4. **Download the transcript for anything you'll need later** — `.docx` or `.vtt` on Teams, by default only if you're the organizer or a co-organizer. People from another tenant can't view it afterwards at all, so anything cross-company has to be shared deliberately. If most of the meeting's readers can't open the record — wrong tenant, wrong license, wrong client, wrong language — the archive exists for one person. > Related: if your team reads recaps from an AI assistant rather than an app, see [which meeting tools expose an MCP server, and what each one lets the assistant do](https://intermind.com/blog/mcp-servers-for-meeting-tools). ## FAQ **Where are Microsoft Teams meeting transcripts saved?** In the meeting organizer's OneDrive for Business. Microsoft states that transcripts for meetings with recording and/or transcription "are stored in the meeting organizer's OneDrive for Business" and can be reached "through the meeting chat and Recap tab in Teams until a meeting organizer deletes the transcript." Recordings are stored separately — the organizer's OneDrive for regular meetings, the channel's SharePoint site in a `Recordings` folder for channel meetings (checked September 2026). **Why did the captions or transcript disappear after I moved the Teams recording?** Because the caption track is tied to the recording's original location rather than travelling inside the video file. Microsoft's admin documentation states: "Closed captions aren't fully supported if the Teams meeting recording is moved or copied from its original location in OneDrive or SharePoint" (checked September 2026). The transcript itself is a separate object and stays where it was, reachable from the meeting chat and Recap tab. **Can someone from another company read a Teams meeting transcript after the meeting?** No, per Microsoft's access matrix: a person from another tenant can view the real-time transcription during the meeting but not view or download the transcript afterwards, and anonymous participants can do neither. People who dial into a meeting can't view the transcript at all. Someone from the same organization can view it after the meeting but can't download it by default (checked September 2026). **Do Teams meeting recordings and transcripts expire?** Expiration is controlled by your organization's admin settings — Microsoft documents an admin control to "manage when recordings and transcripts expire for your organization," and the expiry date on an individual recording can be changed, or removed, by someone with edit permission. If a recording does expire, its owner is emailed and has up to 90 days to recover it from the recycle bin (checked September 2026). **Where does Google Meet save the transcript, and who can open it?** In the meeting organizer's Google Drive, in the `Google Meet` folder, with a separate file each time transcription is started. A link is emailed to the host, co-hosts and the person who turned Transcripts on, and the transcript is attached to the Google Calendar event, which all invitees in the host's organization can open — above 200 invitees in the host's organization it is limited to the host, co-hosts and the person who started it (checked September 2026). **Can I use Microsoft Teams on Linux?** Not as a desktop app. Microsoft's client availability table lists Linux as unavailable with the note "Teams is no longer supported on Linux," and lists the web client as supported in Microsoft Edge, Chrome, Firefox and Safari (checked September 2026). InterMIND is a web app, so a Linux desktop is a supported desktop. **Can my team read the summary and the transcript in their own languages?** In InterMIND, yes — when a meeting is finalized the summary and the transcript are translated into every participant's language at that moment, so each member opens their own, covering 23 languages for voice, chat and notes. Microsoft states the opposite for Teams: live translated transcription is part of Teams Premium, and "past translated transcripts aren't stored. Only the original transcript is stored." Google documents Meet transcripts in eight languages, in the language spoken (checked September 2026). **How long does an InterMIND recap stay available?** Until the host deletes it. A channel keeps the recap of every past session on the same permanent link; an ad-hoc meeting keeps only the latest session's recap, the same way its chat history is purged after each call. The host can delete a session's summary, transcript, recording and their translations, and that deletion is permanent. ## Try it - **[How to send meeting recaps to your CRM, help desk or spreadsheet](https://intermind.com/blog/how-to-send-meeting-recaps-to-your-crm-with-zapier-or-the-api)** — a recap copy by email, Zapier, a signed webhook, or the API. - **[Open the live demo](https://intermind.com/demo)** — a meeting in your language, no signup. - **[Start your first meeting](https://intermind.com/chats)** — guests join by link, each in their own language. - **[See what a recap looks like](https://intermind.com/examples/recap)** — summary, transcript, and the structure above on a real example. - **[Read the recap docs](https://intermind.com/docs/meetings/recap)** — access rules, editing, archive and BCC copies. - **[Back up your chats](https://intermind.com/docs/settings/data-export)** — what the ZIP contains and how restore works. If the language of the record is the part that bothers you rather than its filing, that argument is laid out separately in [how much of your meeting still exists in your language a week later](https://intermind.com/blog/the-meeting-a-week-later). *Sources: Microsoft Support — [Start, stop, and find meeting recordings in Microsoft Teams](https://support.microsoft.com/en-us/office/record-a-meeting-in-microsoft-teams-34dfbe7f-b07d-4a27-b4c6-de62f1348c24){rel=""nofollow""} and [View live transcription in Microsoft Teams meetings](https://support.microsoft.com/en-us/office/view-live-transcription-in-microsoft-teams-meetings-dc1a8f23-2e20-4684-885e-2152e06a4a8b){rel=""nofollow""}; Microsoft Learn — [Teams meeting recording and transcript storage and permissions in OneDrive and SharePoint](https://learn.microsoft.com/en-us/microsoftteams/tmr-meeting-recording-change){rel=""nofollow""}, [Overview - Recording and transcription for Teams meetings, events, and calls](https://learn.microsoft.com/en-us/microsoftteams/recording-transcription-overview){rel=""nofollow""} and [Overview of the Microsoft Teams client](https://learn.microsoft.com/en-us/microsoftteams/teams-client-desktop-admin){rel=""nofollow""}; Google Meet Help — [Use Transcripts with Google Meet](https://support.google.com/meet/answer/12849897){rel=""nofollow""}, checked September 2026.* # Linguee English–Portuguese: what it's actually for (and when you need a different tool) - **A corpus dictionary, not a translator.** Linguee shows how a word was actually translated in real sentences; paste a paragraph and you get dictionary entries. - **Three limits, all by design.** No running text, no documents, no voice: text is DeepL's or Google Translate's job, files a document translator's. - **InterMIND keeps the whole conversation in each member's language:** you speak Portuguese, they hear English, they answer and you hear Portuguese, across 23 languages. Guests join free by link, no account; you pay only for active members. People searching for the Linguee English–Portuguese translator usually want one of two things — and Linguee only does one of them well. If the question is *"how do I say **this word** in this context?"*, that is exactly the job Linguee was built for. If the task is *"translate this paragraph / this document / this conversation"*, it was never built for that — and insisting costs you time. This guide separates the two uses honestly: what Linguee does better than its competitors, where it stops, and which tool takes over from there. --- ## What Linguee is — and why it's good at it Linguee is a **corpus dictionary**: besides the word's translation, it shows dozens of real sentences — contracts, websites, published documents — where that word was actually translated by human translators, side by side with the original. It's from the same company that built DeepL; Linguee's corpus is part of what trained its sibling translator. That's what it does that a plain machine translator doesn't: **nuance**. Is "enforcement" *aplicação*, *execução* or *fiscalização* in Portuguese? Depends on context — and Linguee shows you the context, ten real examples of each option. A machine translator picks for you and hides the alternatives. Use Linguee when: - you're writing in the other language and want the *right* word, not just a translation; - you're learning and want to see a word alive in real sentences; - you need to check how a technical or legal term is actually translated in practice. --- ## Where Linguee stops Three limits, all by design — Linguee is a dictionary, not a translation engine: 1. **It doesn't translate running text.** Paste a paragraph and you don't get the paragraph back translated — you get dictionary entries. For text, its own maker points you at DeepL; Google Translate and others handle it too. 2. **It doesn't translate documents.** PDF, DOCX, slide deck — wrong category of tool. 3. **It has no voice.** No speaking and hearing a translation — not one sentence, let alone a conversation. None of these limits is a flaw. It becomes a problem only when we use the tool from the wrong step: Linguee answers *"which word?"*, not *"what did they say?"*. --- ## The right tool for each job | Job | Right tool | | ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------ | | A word or phrase, with nuance | **Linguee** (or Reverso Context, same model) | | A paragraph, an email, running text | DeepL, Google Translate | | A whole document (PDF, DOCX) | A document translator — InterMIND, for one, [translates files in the meeting across 30 languages](https://intermind.com/features/realtime-translation) | | A spoken phrase, face to face | A phone voice app ([the three kinds of voice translator](https://intermind.com/blog/tradutor-de-voz)) | | **A voice conversation — a call, a meeting, several people** | **Live meeting translation** — everyone speaks and hears their own language | The first row and the last are the two that get confused in practice. The ladder is always the same: word → text → voice → *conversation*. Each rung has its own tool, and the last one is the least known — which is why it gets its own section. --- ## The rung almost nobody knows: the conversation The typical Linguee English–Portuguese user is *working* between the two languages — a foreign client, a supplier, a distributed team, a job interview. Then the voice meeting arrives, and the dictionary can't join the call with you. That step has its own category — the [voice translator](https://intermind.com/blog/tradutor-de-voz) — and the version built for real conversations is live meeting translation. In InterMIND, the call itself is multilingual: you speak Portuguese, the other side hears English; they answer in English, you hear Portuguese — **at the same time, live, in any combination of 23 languages**, with no English anchoring. Per-language-pair quality is public, measured on real traffic, at [`/benchmark`](https://intermind.com/benchmark) — including the English ↔ Portuguese pair. And if what you like about Linguee is precisely that it *shows instead of promising*: [`/demo`](https://intermind.com/demo) does the same with voice — it plays a real meeting translated live, no signup needed. --- ## The verdict Linguee answers the question it chose to answer: *which word, in this context*. Keep it open in a tab — we do. Just don't ask it for what it never promised: running text is DeepL's or Google Translate's job; documents are a file translator's job; and a **conversation** — the meeting with the client who doesn't speak your language — is the job of [live meeting translation](https://intermind.com/blog/tradutor-de-voz). Word, text, voice, conversation. Four jobs, four tools — and now you know which is which. — The Mind.com Team --- *Sources: [Linguee — English–Portuguese dictionary](https://www.linguee.com/english-portuguese){rel=""nofollow""}, [DeepL Translator](https://www.deepl.com/en/translator){rel=""nofollow""} — Linguee and DeepL are built by the same company, and Linguee's own pages point to DeepL for running text; checked August 2026.* # Best MCP servers for meetings (2026): what Zoom, Teams, Fireflies, Otter, Granola and InterMIND expose to your AI assistant - **Most meeting MCP servers only read.** Search, transcript, summary; only Read AI, InterMIND, Fireflies and Microsoft Work IQ document tools that act. - **Check the plan gate first.** Otter, Read AI and InterMIND take any account; tl;dv needs Pro or higher, Zoom's connector a licensed Pro seat; Meet has none. - **InterMIND keeps the whole meeting in each member's language,** and its server lets your assistant read recaps, transcripts and channels and act as you. Guests join free by link, no account; you pay only for active members. A year ago "connect my meetings to my AI" meant copying a transcript into a chat window. Now most meeting tools ship a **Model Context Protocol (MCP) server**: a hosted endpoint your assistant signs into once, after which it can search your meetings, pull a transcript, read a summary — and, in a few cases, do something on your behalf — from the same conversation where it already works with your mail, CRM and tickets. The catch is that "has an MCP server" tells you almost nothing. One vendor's server exposes nineteen tools and another's exposes three. One lets any account connect, another requires a licence the team may not have. One returns a transcript, another returns a link to a recording. This guide compares the servers the way you would evaluate them: **what the assistant can do**, **who is allowed to connect**, **how you sign in**, and **where the server is listed** — using only what each vendor states in its own documentation, checked in September 2026. We make one of these ([InterMIND](https://intermind.com){rel=""nofollow""}); we say where it fits and where it does not. > New to the protocol? [MCP](https://modelcontextprotocol.io){rel=""nofollow""} is an open standard for giving AI assistants tools and data. A *remote* MCP server is one the vendor hosts at a URL; you add the URL to your assistant, sign in, and the assistant discovers the tools itself. --- ## The three questions that separate the servers ### 1. Can the assistant only read, or can it act? Almost every meeting MCP server is a **read layer over recordings**: search meetings, fetch a transcript, fetch a summary. That is useful — "what did we agree with Acme last week?" answered without opening another app — but it is a rear-view mirror. A smaller set of servers also lets the assistant **act**: create a meeting, share a report, post into a channel. If your workflow is "AI drafts the follow-up *and* books the next call", the second group is the one to look at. ### 2. Who is allowed to connect? The plan gate is where the surprises are. Some servers are documented as available to every account, some only to paid tiers, some only to users holding a specific AI licence on top of the seat. Since the person connecting is usually not the person paying, check this before you tell the team to try it. ### 3. Where does it run, and how do you sign in? Every server in this list is hosted by the vendor (remote, Streamable HTTP). The difference is sign-in: most use OAuth (you approve the connection in a browser and can revoke it), a few also accept an API key for tools that cannot run an OAuth flow (editors, CLIs). Whether the server appears in the [Claude Connectors Directory](https://claude.ai/directory){rel=""nofollow""} or the [official MCP Registry](https://registry.modelcontextprotocol.io){rel=""nofollow""} tells you how much setup the first-time user faces: a listed connector is one click; an unlisted one is a URL to paste. --- ## Side by side All facts from vendor documentation, checked September 2026; "n/d" = not documented on the pages we checked (sources at the end). | Tool | Server | Sign-in | Read | Act | Plan gate (documented) | Listed in | | ----------------------------------- | ----------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Zoom** (Zoom Meetings server) | `mcp.zoom.us` remote | OAuth 2.0 with PKCE, manual app registration | `search_meetings`, `get_meeting_assets` (summary, recording, whiteboards, docs), `get_recording_resource` (transcript, summary, next steps), `recordings_list` | No meeting-creation tool listed on the Zoom or Zoom Meetings server pages | Claude connector: licensed user on Workplace Pro or higher; AI Companion Smart Recording + Meeting Summary enabled; `recordings_list`: Pro or higher | Official MCP Registry (`io.github.zoom/*`); Claude directory search shows only a Community "Zoom Revenue Accelerator Connector" | | **Microsoft 365 / Teams** (Work IQ) | `agent365.svc.cloud.microsoft` remote; local `@microsoft/workiq` | Microsoft Entra ID (OAuth) | Work IQ: `fetch`, `ask`, `search_paths` over Graph paths; Teams server: chats, channels, messages | Teams server: `postMessage`, `createChat`, `postChannelMessage`; Work IQ: `create_entity`, `do_action` | Agent 365 page: Microsoft 365 Copilot licence; Work IQ overview: usage-based billing without a Copilot licence — two pages state different gates | Official MCP Registry (`com.microsoft/workiq-*`); Claude directory has an Anthropic-made "Microsoft 365" connector (mail, calendar, SharePoint, chat search) | | **Google Meet** | No Meet server documented; Workspace servers exist for Gmail, Drive, Docs, Sheets, Slides, Calendar, Chat, People | OAuth 2.0 | — | — | Google Workspace Developer Preview Program | Claude directory: Google Drive, Google Calendar; no Meet page | | **Fireflies** | `api.fireflies.ai/mcp` remote | OAuth; API key via Bearer header | 19 tools incl. `fireflies_search`, `fireflies_get_transcript`, `fireflies_get_summary`, `fireflies_get_active_meetings`, `fireflies_get_analytics` | `fireflies_share_meeting`, `fireflies_update_meeting_title`, `fireflies_move_meeting`, `fireflies_create_soundbite` | Any active account; rate limits apply to MCP: Free 50 requests/day, Pro 500/day, Business/Enterprise 60/min | Claude directory (Fireflies); Official MCP Registry (`ai.fireflies/fireflies`) | | **Otter.ai** | `mcp.otter.ai/mcp` remote | OAuth with granular permissions | `search` (meetings overview), `fetch` (full transcript), `get_user_info` | — | Pricing page shows the MCP row checked on Basic, Pro, Business and Enterprise | Claude directory (Otter.ai, made by Otter.ai); not found in the Official MCP Registry | | **Granola** | `mcp.granola.ai/mcp` remote | OAuth and Enterprise-Managed Authorization; no API key | `query_granola_meetings`, `list_meetings`, `get_meetings`, `get_meeting_transcript`, `list_meeting_folders`, `get_account_info` | — | Free: personal notes from the last 30 days; folders, search and transcript tools on paid plans; Enterprise scopes admin-configured | Claude directory (Granola); no official entry in the MCP Registry | | **tl;dv** | Hosted connector (Claude, ChatGPT); open-source local server | OAuth (connector); API key (local) | `search-meetings`, `get-meeting-metadata`, `get-meeting-notes`, `get-meeting-transcript`, `get-user-profile` | — | tl;dv Pro or higher (help centre); Business or Enterprise for the local server (GitHub) | Claude directory (tldv); not found in the MCP Registry | | **Fathom** | `api.fathom.ai/mcp` remote | Authorization prompt on first use; method not named | Tools not enumerated on vendor pages ("ask about your meetings") | — | n/d | Claude directory (Fathom); Official MCP Registry (`ai.fathom.api/mcp`); ChatGPT app | | **Read AI** | `api.read.ai/mcp` remote, open beta | OAuth 2.1; 10-minute access tokens, single-use refresh tokens; API keys planned | Get meeting by id, List meetings | Create meeting agent, Share meeting report | All users regardless of plan; workspace must have Downloads enabled; 100 requests/min/user | Claude directory (Read AI); not found in the MCP Registry | | **InterMIND** | `intermind.com/api/mcp` remote | OAuth 2.1 (sign in with InterMIND); API key for static-header clients | `list_recaps`, `search_recaps` (phrase over your recaps, snippet + links), `get_transcript` (Markdown by speaker, spoken language or your cached translation), `list_meetings`, `list_channels`, `get_channel_messages` (text as written + cached translation into your language), `list_documents` | `create_meeting_link`; `schedule_meeting` (a time in your connected Google/Microsoft calendar, with invitees); `post_channel_message` (as you, translated for every reader) | Every registered account, including free Basic; guests cannot connect apps; reading limited to meetings you attend | Claude directory (InterMIND, community connector); Official MCP Registry (`com.intermind/intermind`); ChatGPT and Microsoft 365 Copilot listings in review | Two rows deserve a note. **Google Meet** has no MCP server of its own as of September 2026: Google's Workspace MCP page lists Gmail, Drive, Docs, Sheets, Slides, Calendar, Chat and People, and the Meet developer page does not mention MCP. **Microsoft Teams** is reachable through Work IQ, but the documented Teams server is about chats, channels and messages; no transcript or recording tool is listed on that page, and the two Microsoft pages that describe licensing disagree with each other (a Copilot licence on one, usage-based billing on the other), so ask your admin which applies to your tenant. --- ## What each server does, in the vendor's words ### Zoom Zoom hosts several servers ("Zoom", "Zoom Meetings", "Zoom Docs", "Zoom Team Chat", "Zoom Tasks", "Zoom Whiteboard", "Zoom Revenue Accelerator"), all "over streamable HTTP". The Zoom Meetings server exposes `search_meetings` (returns "availability of transcripts, summaries, or recordings"), `get_meeting_assets` ("summary, cloud recording, whiteboards, Zoom Docs, and the agenda document"), `get_recording_resource` ("transcript, summary, next step, and the corresponding playback link") and `recordings_list`, which requires "a Pro or a higher plan" with Cloud Recording enabled. The workspace server adds `ask`, an agentic search that "requires either a ZoomMate license or a Custom AI Companion license". Sign-in is OAuth with PKCE, and "Zoom remote MCP servers only support manual client registration through app creation". The Claude connector requires "a Licensed user on a Zoom Workplace Pro, Pro Plus, Business, Business Plus, Enterprise, Enterprise Plus, or Enterprise Bundle account" and depends on AI Companion's Smart Recording and Meeting Summary being enabled. Neither server page lists a tool that creates or schedules a meeting. ### Microsoft 365 and Teams (Work IQ) Microsoft's Work IQ MCP "exposes Microsoft 365 intelligence capabilities to AI agents … through a single MCP endpoint", with per-workload servers for Mail, Calendar, Teams, SharePoint, OneDrive, Word and Copilot. Clients "automatically discover the authentication configuration through the `/.well-known/oauth-protected-resource` endpoint" (Entra ID). The generic server's tools are verbs over Graph paths: `fetch`, `ask`, `search_paths`, `create_entity`, `update_entity`, `do_action`, `call_function`. The Teams server's tools are chat- and channel-scoped (`listChats`, `listChatMessages`, `postMessage`, `createChat`, `listChannels`, `postChannelMessage`); meetings appear in the Work IQ overview as one of the unified signals, but no transcript tool is named on the pages we checked. Documented clients: Copilot Studio, Microsoft Foundry, and coding agents ("GitHub Copilot CLI, Claude Code, and VS Code"). Separately, the Claude directory carries a "Microsoft 365" connector made by Anthropic with mail, calendar, SharePoint and chat-message search. ### Google Meet and Workspace Google documents remote MCP servers for Gmail, Drive, Docs, Sheets, Slides, Calendar, Chat and People, "available as part of the Google Workspace Developer Preview Program", with OAuth 2.0. There is no Meet server on that page, no Meet entry in the Workspace release notes through September 2026, and the Meet developer landing page does not mention MCP. If you need Meet recordings in an assistant today, the vendor-documented route is Drive (where Meet stores them) rather than a Meet-specific server. ### Fireflies Fireflies runs a remote server at `api.fireflies.ai/mcp` that "uses OAuth with your Fireflies account" and also accepts an API key in a Bearer header. It is the widest tool surface in this list: nineteen tools covering search, transcripts, summaries, active meetings, analytics, sharing and revoking access, renaming and moving meetings, channels, soundbites, users, groups and contacts. The changelog states that the plan rate limits "also apply to the MCP server": 50 requests per day on Free, 500 per day on Pro, 60 per minute on Business and Enterprise. Documented clients: Claude, Claude Desktop, Devin, "OpenAI Connector, Cursor". ### Otter.ai Otter's remote server at `mcp.otter.ai/mcp` is "OAuth-authenticated with granular permissions. Your AI assistant can only access meetings you explicitly authorize." Three tools: `get_user_info`, `search` ("Search for meetings and get an overview") and `fetch` ("Retrieves a full speech transcript of a meeting or conversation"). The pricing page shows "MCP server integration for AI assistants" checked on all four tiers. Documented clients: Claude, ChatGPT, Cursor, Perplexity and "other MCP-compatible platforms via JSON configuration". ### Granola Granola's remote server at `mcp.granola.ai/mcp` supports "browser-based OAuth and Enterprise-Managed Authorization (EMA)"; "there is no API key or service account access method for MCP". Six tools: `query_granola_meetings`, `list_meetings`, `get_meetings`, `get_meeting_transcript` (paid), `list_meeting_folders` (paid), `get_account_info`, with a rate limit of "around 100 requests per minute". Free accounts get "personal notes from the last 30 days"; Enterprise scopes are admin-configured, and "if neither scope is enabled, members cannot use Granola MCP". ### tl;dv tl;dv offers a hosted connector in the Claude and ChatGPT marketplaces (OAuth) and an open-source local server keyed by `TLDV_API_KEY`. The connector's tools are `search-meetings`, `get-meeting-metadata`, `get-meeting-notes`, `get-meeting-transcript` and `get-user-profile`. The help centre requires a tl;dv "Pro Plan (or higher)" plus a paid Claude or ChatGPT plan; the GitHub README of the local server states "A Business or Enterprise tl;dv account is required." ### Fathom Fathom "now offers an official MCP (Model Context Protocol) server" at `api.fathom.ai/mcp`, with an official Claude connector (for teams, "an owner must first enable the connector"), a ChatGPT app, and a Claude Code recipe via `mcp-remote`. The vendor pages describe the experience ("ask Claude about your meetings") without enumerating the tools, and an unauthenticated tools request answers 401. Plan requirements are not stated on the MCP pages. ### Read AI Read AI's remote server at `api.read.ai/mcp` is "currently available as an open beta release" with "OAuth 2.1 (sign in using your Read AI account)"; "access tokens expire after 10 minutes, and refresh tokens are single-use". Four tools: get meeting by id, list meetings, **create meeting agent**, **share meeting report** — one of the two servers in this list with documented actions beyond reading. It is "available to all users regardless of plan or workspace", provided the workspace has the Downloads option enabled, with a limit of 100 requests per minute per user. ### InterMIND InterMIND's remote server at `intermind.com/api/mcp` exposes ten tools. Reading: `list_recaps` (newest recaps with the summary in Markdown and links to the recap and transcript pages), `search_recaps` (a phrase over the current summaries of meetings you attend, with a snippet around the match), `get_transcript` (the transcript grouped by speaker, in the spoken language or your cached translation, cut at a limit with a link to the full page), `list_meetings` (recent or upcoming), `list_channels`, `get_channel_messages` (the text as written plus, when the room already translated it, the text in your language) and `list_documents` (uploads and linked Drive / OneDrive files). Acting: `create_meeting_link` creates an ad-hoc meeting you own and returns its URL; `schedule_meeting` creates one at a local time and writes it to your connected Google or Microsoft calendar with the invitees (without a connected calendar the link still works but carries no time); `post_channel_message` writes into a channel as you, and every member reads it in their own language. Sign-in is OAuth 2.1 — the assistant opens an InterMIND page listing what it will be able to do, the connection appears in **Settings → API keys** under the assistant's name, where you can revoke it — or a static API key for clients that take a header (Claude Code, Cursor, Gemini CLI, Copilot Studio). It is available on every registered account, including the free Basic plan; guests cannot connect apps. It is listed in the [Claude Connectors Directory](https://claude.ai/directory/connectors/intermind){rel=""nofollow""} and in the [official MCP Registry](https://registry.modelcontextprotocol.io/v0.1/servers/com.intermind%2Fintermind/versions/latest){rel=""nofollow""}, and works with any MCP client. Every participant takes part in the meeting in their own language, so the assistant does not need to know which language the call was in. **Honest limits.** Reading stops at the meetings you host or attend; a meeting you are not in answers "not found". Recap search is a substring match over the current summary, not semantic search. The transcript comes back in the language it was spoken unless the room already translated it for you. The assistant cannot join a meeting, speak in it, or change your settings, and a connection made before September 2026 keeps only the two original rights (meeting links, recaps) until you reconnect. ## How to read the table for your own case - **You want the assistant to prepare the next call, not just summarise the last one.** Look at the "Act" column: Read AI (create meeting agent, share report), InterMIND (create or schedule a meeting, post to a channel), Fireflies (share, rename, move, soundbites), Microsoft Work IQ (post messages, create entities). Zoom, Otter, Granola and tl;dv document read tools only. - **The team is on free or mixed plans.** Otter, Read AI and InterMIND document the server as available on every tier; Fireflies allows Free with 50 requests per day; Granola's Free tier excludes transcripts and folders; Zoom's Claude connector needs a licensed Pro-or-higher seat plus AI Companion; tl;dv needs Pro or higher. - **Your assistant is Copilot.** Microsoft's own route is Work IQ; third-party servers connect through Copilot Studio's MCP tool with OAuth or a header. InterMIND and Granola document Copilot explicitly. - **Your assistant is an editor or CLI without a browser flow.** Fireflies, tl;dv (local) and InterMIND accept an API key; Granola documents no key method; Zoom requires a registered OAuth app. - **You need the transcript itself, not a link.** Otter (`fetch`), Fireflies (`fireflies_get_transcript`), Granola (`get_meeting_transcript`, paid), tl;dv (`get-meeting-transcript`), Zoom (`get_recording_resource`) return transcript content; InterMIND (`get_transcript`) returns the transcript by speaker, cut at a limit with a link to the full page. --- ## Connect InterMIND to your assistant - **Claude:** open the [InterMIND connector](https://claude.ai/directory/connectors/intermind){rel=""nofollow""}, click **Connect**, allow the connection on the InterMIND page. - **ChatGPT:** Settings → Apps & Connectors → Developer mode → Create a connector with `https://intermind.com/api/mcp` and OAuth. - **Claude Code:** `claude mcp add --transport http intermind https://intermind.com/api/mcp`, then `/mcp` to sign in. - **Copilot Studio, Cursor, Gemini, Windsurf, VS Code:** add a remote MCP server with the same URL; OAuth where the client supports it, otherwise a key from Settings → API keys. Then ask: *"Create an InterMIND meeting link for tomorrow's call with Acme and put it in the deal."* or *"What did we agree with Acme last week? Check my InterMIND recaps."* Full setup notes per client: [AI assistants (MCP)](https://intermind.com/docs/integrations/mcp). - **[Try the live demo](https://intermind.com/demo)** — a meeting in your language, no account needed. - **[Read the MCP docs](https://intermind.com/docs/integrations/mcp)** — tools, sign-in, security and privacy. - **[See the public API](https://intermind.com/docs/integrations/api-zapier)** — the endpoints the MCP server calls. --- ## FAQ **What is an MCP server for meetings?** A hosted endpoint, published by a meeting or note-taking tool, that an AI assistant (Claude, ChatGPT, Copilot, Gemini, Cursor) can sign into and call as tools: search your meetings, fetch a transcript or summary, and in some cases create a meeting or share a report. It uses the Model Context Protocol, an open standard, so the same server works in any assistant that supports remote MCP. **Does Zoom have an MCP server?** Yes. Zoom hosts several remote servers on `mcp.zoom.us` (Zoom, Zoom Meetings, Docs, Team Chat, Tasks, Whiteboard, Revenue Accelerator) with OAuth and manual app registration. The Zoom Meetings server exposes `search_meetings`, `get_meeting_assets`, `get_recording_resource` and `recordings_list`. The Claude connector requires a licensed user on Workplace Pro or higher with AI Companion Smart Recording and Meeting Summary enabled (checked September 2026). **Does Microsoft Teams have an MCP server?** Through Work IQ, yes: Microsoft documents a Teams server for chats, channels and messages, plus a general Work IQ server that queries mail, meetings, documents and Teams messages over Graph paths, authenticated with Entra ID. No transcript tool is named on the Teams server page. Microsoft's pages state different licensing gates (a Microsoft 365 Copilot licence on one, usage-based billing on another), so confirm with your admin. **Does Google Meet have an MCP server?** Not as of September 2026. Google's Workspace MCP page lists Gmail, Drive, Docs, Sheets, Slides, Calendar, Chat and People servers under the Developer Preview Program; Meet is not among them, and the Meet developer page does not mention MCP. **Do Fireflies and Otter have MCP servers?** Both do. Fireflies: `api.fireflies.ai/mcp`, OAuth or API key, nineteen tools, plan rate limits apply (Free 50 requests/day). Otter: `mcp.otter.ai/mcp`, OAuth with granular permissions, three tools (`search`, `fetch` for the full transcript, `get_user_info`), shown as included on every pricing tier. **Which meeting MCP servers let the assistant do more than read?** From vendor documentation: Read AI (create meeting agent, share meeting report), InterMIND (create meeting link, schedule a meeting in the calendar, post a channel message), Fireflies (share meeting, revoke access, rename, move, create soundbite) and Microsoft Work IQ (post messages, create chats, create and update entities). Zoom, Otter, Granola, tl;dv and Fathom document read tools only on the pages we checked. **Do I need a paid plan to use a meeting MCP server?** It depends on the vendor. Otter, Read AI and InterMIND document availability on every account. Fireflies allows Free with 50 requests per day. Granola's Free tier covers personal notes from the last 30 days without transcripts. tl;dv requires Pro or higher. Zoom's Claude connector requires a licensed Pro-or-higher seat with AI Companion. Microsoft's pages disagree with each other about Work IQ. **Can my assistant create a meeting link with InterMIND?** Yes. `create_meeting_link` creates a meeting you own and returns its URL; put it in a calendar invite, a deal or a ticket, and admit people when they knock. `schedule_meeting` does the same at a given time and writes the event to your connected calendar. The assistant acts as you: it can also read recaps, transcripts and channels of meetings you attend and post in your channels, but it cannot join a meeting, speak in it, or change settings. **Which assistants can connect to InterMIND?** Any MCP client: Claude (listed in the Connectors Directory), ChatGPT (Developer mode), Claude Code, Cursor, Windsurf, VS Code, Microsoft 365 Copilot via Copilot Studio, Gemini, Le Chat, Perplexity and agent SDKs. OAuth where the client supports it, otherwise an API key. **In which language does the assistant get the meeting back?** Vendor MCP pages we checked do not document the language of the returned content. In InterMIND every participant takes part in their own language, and the recap the assistant reads is the one the connected account sees. **Is a meeting MCP server safe to connect?** Every server here uses OAuth (Zoom, Microsoft, Google, Otter, Granola, Read AI, InterMIND) or OAuth plus an optional key (Fireflies, tl;dv). Look for three things in the documentation: the scope the assistant gets (Zoom lists per-tool scopes; Otter states "only access meetings you explicitly authorize"), how to revoke (InterMIND: Settings → API keys; Read AI: 10-minute access tokens), and whether the server can act, not just read — an acting server deserves a narrower grant. --- *Sources: vendor documentation checked September 2026 — Zoom ([MCP overview](https://developers.zoom.us/docs/mcp/){rel=""nofollow""}, [Zoom Meetings server](https://developers.zoom.us/docs/mcp/zoom-meetings-mcp-server/){rel=""nofollow""}, [Zoom server](https://developers.zoom.us/docs/mcp/zoom/){rel=""nofollow""}, [connect guide](https://developers.zoom.us/docs/mcp/servers/connect-to-zoom-mcp-servers/){rel=""nofollow""}, [Claude connector](https://developers.zoom.us/docs/mcp/plug-ins-and-connectors/claude-connector/){rel=""nofollow""}); Microsoft ([Work IQ MCP overview](https://learn.microsoft.com/en-us/microsoft-365/copilot/extensibility/work-iq/mcp/overview){rel=""nofollow""}, [tool reference](https://learn.microsoft.com/en-us/microsoft-365/copilot/extensibility/work-iq/mcp/tool-reference){rel=""nofollow""}, [Agent 365 tooling servers](https://learn.microsoft.com/en-us/microsoft-agent-365/tooling-servers-overview){rel=""nofollow""}, [Teams tools](https://learn.microsoft.com/en-us/microsoft-copilot-studio/mcp-teams-tools){rel=""nofollow""}, [Work IQ](https://learn.microsoft.com/en-us/microsoft-365/copilot/extensibility/work-iq/){rel=""nofollow""}); Google ([Workspace MCP servers](https://developers.google.com/workspace/guides/configure-mcp-servers){rel=""nofollow""}, [release notes](https://developers.google.com/workspace/release-notes){rel=""nofollow""}, [Meet API](https://developers.google.com/workspace/meet){rel=""nofollow""}); Fireflies ([MCP configuration](https://docs.fireflies.ai/getting-started/mcp-configuration){rel=""nofollow""}, [tools](https://docs.fireflies.ai/mcp-tools/overview){rel=""nofollow""}); Otter ([MCP Server](https://help.otter.ai/hc/en-us/articles/35287607569687-Otter-MCP-Server){rel=""nofollow""}, [pricing](https://otter.ai/pricing){rel=""nofollow""}); Granola ([MCP](https://docs.granola.ai/help-center/sharing/integrations/mcp){rel=""nofollow""}); tl;dv ([MCP](https://intercom.help/tldv/en/articles/15322415-mcp){rel=""nofollow""}, [local server](https://github.com/tldv-public/tldv-mcp-server){rel=""nofollow""}); Fathom ([MCP docs](https://developers.fathom.ai/mcp-docs){rel=""nofollow""}); Read AI ([MCP Server](https://support.read.ai/hc/en-us/articles/49381158409491-MCP-Server){rel=""nofollow""}, [API and MCP overview](https://support.read.ai/hc/en-us/articles/49379985941523-Read-AI-API-and-MCP-Overview){rel=""nofollow""}); [Claude Connectors Directory](https://claude.ai/directory){rel=""nofollow""}; [official MCP Registry](https://registry.modelcontextprotocol.io/v0.1/servers?search=zoom){rel=""nofollow""}; InterMIND ([AI assistants (MCP)](https://intermind.com/docs/integrations/mcp)).* # Meet in the side panel: the InterMIND Chrome extension is live - **It is in the Chrome Web Store.** It docks InterMIND in Chrome's side panel beside the tab you present: call, chat and participants in view, the tab keeps focus. - **Chromium only, and the picker stays.** By our measurement, not a documented guarantee, a tab share omits the panel; a full-screen share captures it. - **InterMIND keeps the whole meeting in each member's language,** voice, chat and the recap, beside the tab you are editing. Guests join free by link, no account; you pay only for active members. The InterMIND Chrome extension is published: **[InterMIND — Meet in the side panel](https://chromewebstore.google.com/detail/bapkchcgnleolmemfdagdigikmgngihb){rel=""nofollow""}** in the Chrome Web Store. It does one thing. It puts the meeting in Chrome's side panel, beside the tab you are presenting, instead of in a window that competes with it. The tab keeps focus and full width — you type in it, you edit it, you share it — while the call, the chat and the participants stay readable next to it. The long version of why that matters is a separate post: [How do you see the room while you're presenting?](https://intermind.com/blog/present-and-edit-at-the-same-time) — the trade every existing fix makes (an overlay covers your content; a second monitor still drops the roster when slides go full screen), and the structural reason a browser side panel is not in that trade. This one is the short version: what shipped, and how to use it. ## What it is A Manifest V3 extension that renders the InterMIND web app inside Chrome's side panel. Chrome documents the Side Panel API as a way for an extension to "host content in the browser's side panel alongside the main content of a webpage" (checked August 2026). The panel belongs to the browser frame rather than to the tab, so switching tabs does not close it and typing into the page does not push it behind anything. What the package asks for, and why: | Permission | What it is for | | ------------------------------ | ----------------------------------------------------------------------------- | | `sidePanel` | The product surface itself — the app renders in the panel | | `storage` | Panel preferences, stored locally; nothing is transmitted | | `scripting` | The sign-in handoff below, scoped to the login tab the extension opens itself | | Host access to `intermind.com` | The panel embeds the InterMIND web app and uses your existing session there | The extension executes only packaged code — no remote code. What it renders is the intermind.com website in an iframe, which is ordinary web content, not extension code. The extension itself collects nothing; account and meeting data is handled by intermind.com under its [privacy policy](https://intermind.com/privacy). ## Three steps 1. **Add it from the store** — [the listing](https://chromewebstore.google.com/detail/bapkchcgnleolmemfdagdigikmgngihb){rel=""nofollow""}. One click, no build, no configuration. 2. **Click the InterMIND icon.** The panel opens on your meetings. If you are already signed in at intermind.com, you are in. 3. **Start or join a meeting, then share the tab you are working in.** Chrome's normal share picker appears; you pick the tab. If you are not signed in, the extension opens the intermind.com login tab itself, hands the panel a one-time key for the session you just created, and closes that tab. The key never travels through a page-controlled channel like a URL — a crafted link cannot make your browser deposit your session under someone else's key. ## What your participants see Sharing a **tab**: we measured that the side panel does not appear in the captured stream — participants see the tab you picked, not the panel beside it. Treat that as our measurement rather than a documented guarantee: Chrome's screen-capture documentation does not state the behavior of browser UI either way, and the W3C Screen Capture specification explicitly leaves the boundary of browser UI implementation-dependent (checked August 2026). Sharing your **entire screen**: everything visible on that screen is captured, panel included. The property above is share-mode specific, and the mode this workflow uses is the tab share. ## What it does not do - **It does not remove the share picker.** There is no one-click "share the tab I'm on" from a side panel: Chrome does not grant extensions tab capture from the panel context, and the request to add that capability was closed as won't-fix by the Chromium team (checked August 2026). - **It is not a second product.** Same account, same meetings, same app — a different place to put it. It needs an InterMIND account; the Basic plan is free. - **Your participants install nothing.** They join by link in an ordinary tab, as they do today. The extension is for the person who is presenting. - **It is a Chromium surface.** The side panel exists in Chromium-based browsers; the Chrome Web Store listing above is the only listing today. - **It does not make a small screen bigger.** A narrow panel holds the call, the chat and the participants — not a wall of video tiles. ## FAQ **Does the InterMIND side panel show up in my screen share?** Not when you share a tab — we tested this and the panel does not appear in the captured stream. Neither Chrome's documentation nor the W3C Screen Capture specification states the behavior of browser UI in a capture (the spec leaves it implementation-dependent), so this is a measured result, not a documented guarantee (checked August 2026). If you share your entire screen instead, everything on that screen is captured, including the panel. **Do I need an InterMIND account to use the extension?** Yes. The panel is the InterMIND app, and it uses your intermind.com session. The Basic plan is free, and if you are not signed in when you open the panel, the extension walks you through signing in and returns you to the panel. **Do the people I invite have to install it?** No. Participants join by link in a normal browser tab and need no account and no extension. The extension changes what the presenter's screen looks like, not what joining takes. **Does the panel stay open when I switch tabs?** Yes. The extension declares one panel for every tab, and the panel lives in the browser frame rather than inside a page, so switching tabs neither closes it nor swaps its contents. **What does the extension collect?** Nothing of its own. `storage` keeps panel preferences on your machine; everything else is the intermind.com session you already have, under the [privacy policy](https://intermind.com/privacy). **Which browsers does this work in?** The side panel is a Chromium feature, so this is a Chrome scenario; the Chrome Web Store listing is the only listing today. On browsers without a side panel you are back to arranging windows — the trade described in [the long version](https://intermind.com/blog/present-and-edit-at-the-same-time). ## Try it - **[Add InterMIND to Chrome](https://chromewebstore.google.com/detail/bapkchcgnleolmemfdagdigikmgngihb){rel=""nofollow""}** — the store listing. - **[Read why presenting goes blind](https://intermind.com/blog/present-and-edit-at-the-same-time)** — the long version, with what each platform documents. - **[Try the live demo](https://intermind.com/demo)** — see a translated call before installing anything. - **[See the other apps](https://intermind.com/downloads)** — desktop and mobile, if the browser is not where you meet. --- *Sources: [Chrome Web Store — InterMIND — Meet in the side panel](https://chromewebstore.google.com/detail/bapkchcgnleolmemfdagdigikmgngihb){rel=""nofollow""}, [Chrome for Developers — chrome.sidePanel API](https://developer.chrome.com/docs/extensions/reference/api/sidePanel){rel=""nofollow""}, [Chrome for Developers — chrome.tabCapture API](https://developer.chrome.com/docs/extensions/reference/api/tabCapture){rel=""nofollow""}, [W3C — Screen Capture](https://www.w3.org/TR/screen-capture/){rel=""nofollow""}, [Chromium issue 40926394 — chrome.tabCapture from side panel](https://issues.chromium.org/issues/40926394){rel=""nofollow""}. Browsers change their APIs and documentation over time; check those pages for the current state. All facts checked August 2026.* # Meeting agenda examples for 12 kinds of meetings — and what each one leaves behind (2026) - **Twelve agendas you can paste.** Weekly, stand-up, one-on-one, kickoff, sprint review, retro, all-hands, leadership, board, client call, QBR and hiring debrief, owner and minutes per item. - **Each ends with what it leaves behind.** Decisions, open items, owners; the usual lists skip who writes them, where, in whose language. - **InterMIND keeps the whole meeting in each member's language,** the agenda in the channel, the call and the recap with its action items. Guests join free by link, no account; you pay only for active members. A good meeting agenda example is worth more than a definition: you see the purpose line, the items with an owner and a time box next to each, the outcome each item needs, and the minutes adding up to the booking. Below are twelve, for the meetings most teams actually run, written so that you can paste one into a message and change the names. Each example ends with the line the usual lists leave out — **what the meeting leaves behind**. An agenda is a promise about outcomes; the recap is where the promise is kept. If you want the anatomy of the format first, it is in the [meeting agenda template](https://intermind.com/blog/meeting-agenda-template) guide. This one is all examples. ## How to read the examples Every item is written the same way: **item — owner — minutes — type**. The type is one of three: *decision* (ends with a sentence that starts "we agreed"), *discussion* (input is needed, no decision today) or *information* (could have been a message — keep these short or move them to the chat). The last slot is always the same: five minutes for outcomes and owners, where each item is marked decided, open or deferred to a date. ## 1. Weekly team meeting — 30 minutes > **Purpose:** unblock this week's work and decide what we don't do. :br**1. Blockers raised in the channel this week** — everyone — 10 min — *discussion*:br**2. One decision the team owes this week** — item owner — 10 min — *decision*:br**3. Announcements that need a face, not a message** — lead — 5 min — *information*:br**4. Outcomes and owners** — lead — 5 min :br**Leaves behind:** the decision in one sentence, the blockers with an owner each, and the item that was deferred — with its date. ## 2. Daily stand-up — 15 minutes > **Purpose:** surface today's blockers; nothing else. :br**1. Since yesterday, until tomorrow, blocked by** — each person — 1 min each — *information*:br**2. Blockers that need two people** — pairs named — 3 min — *discussion*, taken offline :br**3. Parking lot** — facilitator — 2 min :br**Leaves behind:** the list of blockers and who is pairing on each. If a stand-up produces decisions, it has stopped being a stand-up. The full format — the six rules, the three questions and the version that works better, the asynchronous variant for a team across time zones — is in [the stand-up meeting guide](https://intermind.com/blog/stand-up-meeting). ## 3. One-on-one — 30 minutes > **Purpose:** the report's agenda first, the manager's second. :br**1. Your items** — report — 12 min — *discussion*:br**2. Follow-ups from last time** — both — 5 min — *information*:br**3. One piece of feedback each way** — both — 8 min — *discussion*:br**4. Next steps, written down** — both — 5 min :br**Leaves behind:** two or three next steps with names and dates, and the running history both people can read before the next one. The full structure is in the [one-on-one meeting template](https://intermind.com/blog/one-on-one-meeting-template). ## 4. Project kickoff — 60 minutes > **Purpose:** leave with one definition of done, one owner per workstream, one channel. :br**1. What we are building and for whom** — sponsor — 10 min — *information*:br**2. Definition of done and the date it is judged against** — project lead — 15 min — *decision*:br**3. Workstreams and owners** — project lead — 15 min — *decision*:br**4. How we communicate: the channel, the weekly, the recap** — project lead — 10 min — *decision*:br**5. Risks each person already sees** — everyone — 5 min — *discussion*:br**6. Outcomes and owners** — 5 min :br**Leaves behind:** the project's first record — done means X by date Y, owners per workstream, and the channel every later meeting of the project will live in. The full kickoff — the checklist for before, during and after, the client variant, and how the kickoff becomes the project's channel — is in the [kick off meeting guide](https://intermind.com/blog/project-kickoff-meeting). ## 5. Sprint review — 45 minutes > **Purpose:** show what shipped and decide what the feedback changes. :br**1. The sprint goal, restated** — product owner — 3 min — *information*:br**2. Demo of what shipped, by item** — builders — 25 min — *information*:br**3. Stakeholder feedback and what it changes in the backlog** — product owner — 12 min — *decision*:br**4. Outcomes and owners** — 5 min :br**Leaves behind:** the accepted items, the rejected ones with the reason, and the backlog changes with a name next to each. ## 6. Retrospective — 45 minutes > **Purpose:** choose one or two changes for the next sprint — not a list of ten. :br**1. Last retro's actions: done, not done, why** — facilitator — 5 min — *information*:br**2. What went well / what didn't** — everyone, in writing first — 15 min — *discussion*:br**3. Pick the changes we commit to** — team — 15 min — *decision*:br**4. Owners and the check date** — 5 min :br**5. Appreciation round** — 5 min :br**Leaves behind:** one or two actions with owners, and the previous actions marked done or not — the retro that forgets its own actions is the retro nobody believes in. ## 7. All-hands — 45 minutes > **Purpose:** everyone hears the same three things and gets to ask about them. :br**1. The quarter in three numbers** — CEO or lead — 10 min — *information*:br**2. One decision that affects everyone, explained** — decision owner — 10 min — *information*:br**3. Team or customer story** — a team — 10 min — *information*:br**4. Questions, including the ones submitted in writing** — all — 15 min — *discussion*:br**Leaves behind:** the three numbers, the decision in plain words, and the answers to the questions — for everyone, including the office that joined at 7 a.m. and the one that joined at 9 p.m., in the language each of them reads. The full format — cadence by company size, how to collect and answer the questions, and what the all-hands leaves behind — is in the [all-hands meeting guide](https://intermind.com/blog/all-hands-meeting). ## 8. Leadership weekly — 60 minutes > **Purpose:** decisions that cross teams; everything inside one team stays inside it. :br**1. Numbers against plan** — finance or ops — 10 min — *information*:br**2. Cross-team decisions on the table** — owners — 30 min — *decision*, one at a time :br**3. Risks and escalations** — anyone — 10 min — *discussion*:br**4. People changes** — HR or lead — 5 min — *information*:br**5. Outcomes and owners** — 5 min :br**Leaves behind:** the decisions, each with the person who will tell their team, and the escalations with an owner and a date. ## 9. Board meeting — 90 minutes > **Purpose:** approve what needs approval, decide the two strategic items, record it. :br**1. Call to order, quorum, approval of the previous minutes** — chair — 5 min — *decision*:br**2. Consent agenda: routine reports and renewals, approved in one motion** — chair — 5 min — *decision*:br**3. CEO report** — CEO — 15 min — *information*:br**4. Financials** — treasurer — 15 min — *information*:br**5. Strategic item A** — sponsor — 20 min — *decision*:br**6. Strategic item B** — sponsor — 20 min — *decision*:br**7. Executive session, if needed** — chair — 5 min :br**8. Next meeting, adjournment** — chair — 5 min :br**Leaves behind:** the minutes — motions verbatim, who moved and seconded, the vote counts — in the format described in [how to write meeting minutes](https://intermind.com/blog/how-to-write-meeting-minutes). Any member may pull an item out of the consent agenda for discussion; that is what makes the single motion legitimate. ## 10. Client call — 45 minutes > **Purpose:** agree the scope change and its price before the end of the month. :br**1. What changed since the last call** — account lead — 5 min — *information*:br**2. The scope change: what is in, what is out** — client — 15 min — *discussion*:br**3. Price and timeline options** — account lead — 15 min — *decision*:br**4. Who sends what by when** — both — 5 min :br**5. Next call** — both — 5 min :br**Leaves behind:** the agreed scope in one paragraph, the price option chosen, and the two or three deliverables with names and dates — the same text on both sides of the call, so the client's record and yours are not two different documents. ## 11. Customer QBR — 60 minutes > **Purpose:** show the value delivered, agree the next quarter's goals, surface the risk early. :br**1. Last quarter: the goals we set and what happened** — account manager — 15 min — *information*:br**2. Usage, outcomes, open issues** — customer success — 15 min — *discussion*:br**3. Next quarter's goals** — both — 20 min — *decision*:br**4. Renewal timeline and who owns it** — account manager — 5 min — *information*:br**5. Outcomes and owners** — 5 min :br**Leaves behind:** the next quarter's goals in the customer's words, the open issues with owners on both sides, and the renewal date on everyone's calendar. ## 12. Hiring debrief — 30 minutes > **Purpose:** decide on the candidate today, from written scores, not from the loudest interviewer. :br**1. Scores submitted in writing before the meeting** — recruiter — 3 min — *information*:br**2. Each interviewer: evidence for the score, two minutes, no reacting to others yet** — interviewers — 12 min — *information*:br**3. Discussion of the disagreements only** — hiring manager — 10 min — *discussion*:br**4. Decision and who tells the candidate by when** — hiring manager — 5 min — *decision*:br**Leaves behind:** the decision, the evidence it rested on, and the name of the person who owes the candidate an answer — by a date. ## How to adapt an example Three edits turn an example into your agenda. Change the purpose sentence until it describes what *this* meeting produces; if you cannot, cancel the meeting. Put the hardest decision first, while attention is fresh, and move every *information* item that nobody will discuss into the channel the day before. Then make the minutes add up: the time boxes should total the booking minus five minutes for the close, and the close is the one item you never cut. ## What the agenda leaves behind — and where Look at the twelve "leaves behind" lines again. Every one of them is a list of decisions, open items and owners — the agenda with three words added per item. The question is who writes those words, and where they end up. InterMIND is a communication space where a meeting lives in a channel, so the agenda is posted in the channel the day before — as a note that, during the call, goes on every screen next to the video tiles with *Share to conference*, read by each participant in their own language, like the channel's chat around it — and when the call ends the recap is written from the meeting itself: a summary, the points marked agreed, open or disputed, the action items with owners, each line keeping its timestamp. It arrives by email, as a message in the channel and as a link in the calendar event, and every signed-in member reads it **in their own language** — the record is translated per reader, not written once in the language the room happened to use. The channel keeps the recap of every past session, so the sprint review from six weeks ago is one click away, and the host can send a copy of every recap to a CRM or tracker address, so the client call's outcomes reach the system of record without anyone forwarding anything. In an organization with team status pages on, the open action items of earlier sessions are judged when the next recap is written, done or not done from what was said, with the verdicts on the organization's status page; team status pages are a preview feature an organization's admin switches on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). A guest joins by link, without an account and at no cost — from a phone, in the browser — and hears the meeting live in their own language. There is no record for a guest afterwards — the account is free, and it is what makes the record reachable. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing); members who go quiet keep their access at no cost. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. ## FAQ **What does a meeting agenda look like?** A short document with a purpose sentence at the top, the items in order, and next to each item the person who brings it, the minutes it gets and the outcome it needs — decision, discussion or information — plus links to pre-reads and a final five-minute slot for outcomes and owners. The twelve examples above are the shape; the [template](https://intermind.com/blog/meeting-agenda-template) is the blank version. **What should be on a team meeting agenda?** The blockers people raised during the week, the one decision the team owes, announcements that genuinely need a face rather than a message, and the closing slot where each item is marked decided, open or deferred. Status updates that nobody will discuss belong in the channel the day before, not on the agenda. **What is the main purpose of a staff meeting agenda?** To make the meeting produce something: a decision taken, a blocker removed, a piece of information everyone now shares. The agenda states the purpose, limits the items to what needs everyone in the room, and reserves time to record the outcomes — which is why a staff meeting with an agenda ends when the list is done rather than when the hour is up. **How do you write an agenda for a board meeting?** Follow the order the bylaws expect: call to order and quorum, approval of the previous minutes, the consent agenda, officer and committee reports, the strategic items that need a decision, any executive session, next meeting and adjournment. Each decision item names a sponsor and a time box; pre-reads go out with the agenda. The chair sets the agenda, usually with the CEO or executive director, and members can ask for items to be added. **What is a consent agenda?** A block of routine items that need a vote but not a discussion — approving the previous minutes, accepting reports, routine renewals — approved together by a single motion. Any member can ask for an item to be pulled out and discussed separately. It is what keeps the time for the two items that actually need the board. **How many items should a meeting agenda have?** Three to five for a 30-minute meeting, five to seven for an hour, and the minutes next to them should add up to the booking minus five for the close. More items than that means either a longer meeting or several items that are information and belong in a message. **Should the agenda be sent before the meeting?** Yes — with the invitation, or the day before at the latest, after collecting items in writing. People who read the agenda arrive with positions; people who first see it in the room spend the first ten minutes forming one. # Meeting agenda template: format, examples, and how the agenda comes back as the recap (2026) - **An agenda is the recap with the outcomes blank.** Each item gets an owner, time box and outcome; the close marks each decided, open or deferred. - **Outcomes get in only if someone types them.** In Teams, Zoom, Google Workspace and Slack the agenda is a document beside the meeting, in one language. - **InterMIND keeps the whole meeting in each member's language,** agenda, chat and recap, next to those tools rather than instead of them. Guests join free by link, no account; you pay only for active members. A meeting agenda is the list of what a meeting is for: the items to cover, in order, each with the person who brings it, the minutes it gets, and the outcome it needs — a decision, a piece of information, or a plan. A meeting with an agenda ends when the list is done. A meeting without one ends when the calendar says so. This guide is the craft first — the format, a template you can copy, five filled-in agendas for the meetings most teams actually run — then the mechanics: where the agenda lives in the tools your team already uses, and what happens to it after the call. Because the agenda's real test is not the meeting. It is the next morning, when someone asks what was decided on item 3. ## What a meeting agenda is — and what it isn't Three documents surround a meeting, and they are often confused: | | Written | What it holds | Who reads it | | -------------------- | ------------ | ---------------------------------------------------------- | --------------------------------------- | | **Invitation** | Days before | Time, place or link, who is invited | Everyone invited, once | | **Agenda** | A day before | Items in order, owner, time box, outcome needed, pre-reads | Everyone invited, before and during | | **Recap or minutes** | Right after | What was decided, what stays open, who does what by when | Everyone invited, and whoever missed it | The agenda is the middle document, and it is the one that makes the third one possible: a recap is an agenda with the outcomes filled in. If your [meeting minutes](https://intermind.com/blog/how-to-write-meeting-minutes) are hard to write, the cause is usually upstream — there was no list to fill in. An agenda is not a schedule of speakers and not a wish list of topics. "Marketing update, 20 min" is a slot. "Decide whether the Q4 campaign ships in two languages or three — Lena, 15 min, decision" is an agenda item. ## What to include: the standard format A usable agenda carries seven elements. Most templates you'll find online are a subset of this list: 1. **Purpose, in one sentence.** What the meeting exists to produce. If you cannot write the sentence, the meeting is probably a message. 2. **Items, in order.** The order is a decision: the item that needs the most minds goes first, while attention is fresh; announcements go last or into the chat. 3. **An owner per item.** The person who brings it, frames it and will be asked about it afterwards. 4. **A time box per item.** Minutes, not "a few". The numbers should add up to the meeting length minus five minutes for the close. 5. **The outcome each item needs.** Mark every item *decision*, *information* or *discussion*. A decision item ends with a sentence that starts "we agreed". An information item could have been an email — if the agenda has too many of them, shorten the meeting. 6. **Pre-reads.** Links to anything that must be read before, not during. The agenda is where the reading list lives. 7. **The last five minutes: outcomes and owners.** Every item gets one of three states — decided, open, deferred to a date — and every action gets a name and a day. This slot is the one most agendas leave out and the one that produces the recap. What stays out: anything that doesn't need everyone in the room. One-to-one items go into one-to-one meetings; status updates that nobody will discuss go into the channel the day before. ## How to write one: before, during, after **The day before, collect items where the team already talks.** Post one message in the team's channel: "Agenda for Thursday — reply with your item, owner, minutes, and whether it needs a decision." Items that come in writing are already half-framed; items that arrive at the start of the meeting cost the meeting ten minutes. Close the list the evening before and send the agenda with the invitation, not instead of it. **During the meeting, run the list, not the clock.** Open with the purpose sentence. For each item: the owner frames it in one minute, the room works it inside the time box, and before moving on the facilitator says the outcome aloud — "so we're recording: decided, two languages, Lena owns the brief by the 12th". Reading the outcome back is what turns a conversation into a record while the people who had it are still in the room. An item that runs over is not extended; it is parked with a date. **After the meeting, publish the agenda with the outcomes filled in.** The same day, to everyone invited, including the people who weren't there. The five-minute close has already produced the text; the recap is the agenda with three words added per item. Then put it where the next meeting will find it — an agenda that lives in one person's notes is an agenda the team doesn't have. How the meeting itself is run between those two documents — the opening, the time boxes, the read-back in the last five minutes — is in [how to run an effective meeting](https://intermind.com/blog/how-to-run-an-effective-meeting). ## A meeting agenda template > **\[Team] — \[Meeting name]**:br**Date:** \[date] · **Time:** \[start]–\[end] · **Link:** \[meeting link] :br**Purpose:** \[one sentence — what this meeting produces] :br**Facilitator:** \[name] · **Notes:** \[name or "the recap"] :br**Pre-reads:** \[link], \[link] > > **1. \[Item]** — \[owner] — \[minutes] — *decision*:br > \[One line: the question to decide, and the options on the table.] > > **2. \[Item]** — \[owner] — \[minutes] — *discussion*:br > \[One line: what input is needed and from whom.] > > **3. \[Item]** — \[owner] — \[minutes] — *information*:br > \[One line. Could it be a message instead?] > > **4. Outcomes and owners** — facilitator — 5 min :br > Each item: decided / open / deferred to \[date]. Each action: \[name] — \[task] — by \[date]. > > **Parking lot:** \[items raised but not on the list — carried to the next agenda] ## Five filled-in examples ### Weekly team meeting — 30 minutes > **Purpose:** unblock this week's work and decide what we don't do. :br**1. Blockers raised in the channel this week** — everyone — 10 min — *discussion*:br**2. Scope cut for the release: drop the export or ship it unpolished?** — Mateusz — 10 min — *decision*:br**3. Hiring: two finalists, interview slots** — Priya — 5 min — *information*:br**4. Outcomes and owners** — 5 min ### One-on-one — 30 minutes > **Purpose:** the report's agenda first, the manager's second. :br**1. Your items** — report — 12 min — *discussion*:br**2. Follow-ups from last time** — both — 5 min — *information*:br**3. One piece of feedback each way** — both — 8 min — *discussion*:br**4. Next steps, written down** — 5 min :br > Pre-read: last session's recap. ### Project kickoff — 60 minutes > **Purpose:** leave with one definition of done, one owner per workstream, one channel. :br**1. What we are building and for whom** — sponsor — 10 min — *information*:br**2. Definition of done and the date it is judged against** — project lead — 15 min — *decision*:br**3. Workstreams and owners** — project lead — 15 min — *decision*:br**4. How we communicate: the channel, the weekly, the recap** — project lead — 10 min — *decision*:br**5. Risks each person already sees** — everyone — 5 min — *discussion*:br**6. Outcomes and owners** — 5 min ### Client call — 45 minutes > **Purpose:** agree the scope change and its price before the end of the month. :br**1. What changed since the last call** — account lead — 5 min — *information*:br**2. The scope change: what is in, what is out** — client — 15 min — *discussion*:br**3. Price and timeline options** — account lead — 15 min — *decision*:br**4. Who sends what by when** — 5 min :br**5. Next call** — 5 min :br > Pre-read: the current statement of work. ### Decision meeting — 45 minutes > **Purpose:** choose the vendor. Leave with one name. :br**1. The criteria we agreed on, restated** — facilitator — 5 min — *information*:br**2. Vendor A against the criteria** — evaluator — 10 min — *discussion*:br**3. Vendor B against the criteria** — evaluator — 10 min — *discussion*:br**4. Decision, dissent recorded** — all — 15 min — *decision*:br**5. Who tells the vendors, by when** — 5 min Twelve more, from the daily stand-up to the board meeting, are in [meeting agenda examples](https://intermind.com/blog/meeting-agenda-examples); the one-on-one has [its own template](https://intermind.com/blog/one-on-one-meeting-template). Notice what the examples have in common: every item has a name next to it, every meeting ends with the same slot, and the total minutes equal the booking. That is the whole craft. ## Where the agenda lives in the tools you already use Each major platform has a place for the agenda, and each stops at a different point. Documented behaviour only, from the vendors' own pages, checked October 2026: | Platform | Where the agenda is written | What happens to it after the meeting | | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | *Add an agenda* in the meeting's Details when scheduling, or *Notes* in the meeting controls during the call; the notes are a Loop document that any attendee or organizer can edit, with tasks assigned by tagging people | Saved automatically and reachable from the Teams calendar and the meeting recap; external attendees cannot access or edit the notes | | **Zoom Workplace** | AI Companion generates an agenda when the meeting is scheduled, from the title, a prompt or previous documents, with a time stamp per section; the host can grant participants edit access | The agenda is shared, accessed and edited in Zoom Canvas; requires the setting enabled, an auto-generated meeting ID and desktop app 6.5.10 or later | | **Google Workspace** | The Calendar event's description field; for eligible Workspace editions and Google AI plans, *Take notes for me* can be switched on in Calendar when the event is created | Notes arrive as a Google Doc after the meeting, shared with all guests, organization guests or hosts only; the notes support one language at a time — multiple languages spoken in the same meeting are not supported | | **Slack** | A canvas from the meeting-agenda template, shared in the channel, with sections for objectives, time allocations, next steps and action items with due dates | The canvas stays in the channel as a document; what was said in the call is not in it unless someone types it | Two things are the same everywhere. The agenda is a document next to the meeting, and the outcomes get into it only if a person writes them — or, where the vendor offers an AI notetaker, in one language, the meeting's. ## How the agenda comes back as the recap InterMIND is a communication space where a meeting lives in a channel, so the agenda has an obvious home: the channel's chat, the day before, where the items arrive as replies. If the agenda is drafted somewhere else, it can land in the channel by email — every channel has its own address, and a message sent to it appears as a regular message with the sender named and attachments kept. The recap is not the only thing that comes back in the reader's language. The channel's chat is translated per reader — each member types in their own language and reads the others in theirs — and during the call the agenda, posted as a note, goes on everyone's screen next to the video tiles with *Share to conference*: the sharer edits it live while the room watches, and every participant reads it in their own language, with the original a toggle away. When the call ends, the recap is written from the meeting itself: a summary, the points marked agreed, open or disputed, the action items with owners, each line keeping its timestamp. It arrives by email, as a message in the channel and as a link in the calendar event, and every signed-in member reads it **in their own language** — the record is translated per reader, not written once in the language the room happened to use. Any member can edit it, every edit keeps author and revision history, and the channel keeps the recap of every past session, so item 3 from three weeks ago is one click away. The host can add a recap copy to any address — a CRM or a tracker inbound mailbox — so the outcomes reach the system of record without anyone forwarding anything. In an organization with team status pages on, the open action items of earlier sessions are judged when the next recap is written: an item someone reported finished is marked done, an item discussed but not finished is marked not done with the reason in the words of the meeting, an item nobody brought up stays open — the verdicts on the organization's status page rather than in the recap — and at the start of the next session Mia names the open items and their owners, so the parking lot is spoken about rather than lost. Team status pages are a preview feature: an organization's admin switches them on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). A guest joins by link, without an account and at no cost — from a phone, in the browser — and hears the meeting live in their own language. There is no record for a guest afterwards — the account is free, and it is what makes the record reachable. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing); members who go quiet keep their access at no cost. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. Agendas as a craft survive every tool: somebody still has to decide what the meeting is for. What doesn't have to survive is the second job — rewriting the agenda by hand after the call, in one language, for people who read others. ## FAQ **What is a meeting agenda?** A meeting agenda is the ordered list of what a meeting will cover: each item with the person who brings it, the minutes it gets and the outcome it needs — a decision, information or discussion — plus the pre-reads and a closing slot for outcomes and owners. It is sent before the meeting and becomes the skeleton of the recap after it. **How do you write a meeting agenda?** Write the purpose in one sentence, collect items in writing the day before, give each item an owner, a time box and an outcome type, order them with the hardest decision first, link the pre-reads, and reserve the last five minutes for outcomes and owners. Send it with the invitation and publish it again after the meeting with the outcomes filled in. **What should a meeting agenda include?** Seven things: the purpose; the items in order; an owner per item; a time box per item in minutes; the outcome each item needs; pre-reads; and the closing slot where every item is marked decided, open or deferred and every action gets a name and a date. **How do I add an agenda to a Microsoft Teams meeting?** According to Microsoft's documentation, when scheduling in the Teams calendar you select *Add an agenda* in the meeting's Details; during a meeting, *Notes* in the meeting controls opens the same collaborative notes, which any attendee or organizer can edit and where tasks are assigned by tagging people. The notes are saved automatically and reachable from the calendar and the meeting recap. External attendees cannot access or edit them. **Is there a meeting agenda template in Word?** Yes — Microsoft publishes free agenda templates for Word in its template gallery (word.cloud.microsoft, "agenda templates" and "meeting agendas"). The template in this guide is plain text, so it pastes into Word, Google Docs, a Slack canvas or a chat message without reformatting. **What is a consent agenda in a board meeting?** A consent agenda groups routine items that need a vote but not a discussion — approving the previous minutes, accepting reports, routine renewals — into one block approved by a single motion. Any member can ask for an item to be pulled out and discussed separately. It is a board practice; the rules for using one come from the organization's bylaws and the procedure it follows. **What are the 5 P's of meetings?** A common planning mnemonic: purpose, participants, process, preparation and product (sometimes listed as payoff). In agenda terms: the purpose sentence, the invitee list, the order and time boxes, the pre-reads, and the outcomes the meeting must leave behind. **How long should a meeting agenda be?** As long as the meeting: the time boxes should sum to the booking minus five minutes for the close. In items, three to five for a 30-minute meeting, five to seven for an hour. If the list is longer, either the meeting is too short or several items are information that belongs in a message. --- *Sources: [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Microsoft — agenda templates for Word](https://word.cloud.microsoft/create/en/agenda-templates/){rel=""nofollow""}; [Zoom — Generating meeting agenda with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0081706){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Slack — Meeting agenda template](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. checked October 2026.* # Your meeting recaps on the AI cloud you already use: how the host picks Azure, Google or AWS once, for the whole organization - **One gateway per organization, picked once.** An admin chooses Azure OpenAI, Vertex AI, Bedrock in your own AWS account or your own endpoint; every AI feature follows. - **Only text leaves, and there is an off switch.** Audio, video and recordings never reach the model; one switch turns AI off for the whole organization. - **InterMIND keeps the whole meeting in each member's language,** translation on its own EU engine, recaps on the gateway you chose. Guests join free by link, no account; you pay only for active members. Every meeting platform now ships AI features, and every AI feature adds at least one company to the list of who sees your meeting content. For most organizations that list already has a shape: the language-model gateway they use for their own AI — Azure OpenAI with their Microsoft 365 tenant, Google Vertex AI with Google Workspace, Amazon Bedrock with their AWS estate. Their compliance team has reviewed that gateway once, with its DPA, its region and its zero-training terms. InterMIND runs its AI features on that same gateway. This post explains what that means in practice, what leaves your organization for an AI call and what does not, how the setting works, how other meeting tools handle the same question in their public documentation, and what a host (or the client asking them) can check without taking our word for it. ## What "the same gateway" means An organization's AI features in InterMIND — meeting recaps, document summaries, the writing assistant in notes, Ask AI, and Mia, the AI participant you address by name in a meeting — all run through **one language-model gateway per organization**. An organization admin picks the gateway on the Billing page, and the choice applies to every AI feature at once. | Gateway | Where the model runs | How it is configured | | ----------------------------------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ | | **Azure OpenAI** (Microsoft) | EU Data Zone — processing and storage inside EU member states | InterMIND's own tenant; the default for every organization | | **Google Vertex AI** (Google Cloud) | EU multi-region endpoint | InterMIND's own project; selectable from the same card | | **Amazon Bedrock** (AWS) | The AWS region of the organization's choice, in its **own AWS account** | The organization adds an IAM access key with Bedrock invoke rights in Settings; models, quotas and the Marketplace agreement stay in its account | | **Your own endpoint** | Wherever you run it | Any OpenAI-compatible server — vLLM in your data centre, or a deployment in your own tenant | For an organization already on Microsoft 365 or Google Workspace, the consequence is simple: **no new AI sub-processor enters the perimeter.** Meeting recaps on Azure OpenAI are a party the organization has already approved, under the Microsoft Products and Services DPA and the EU Data Boundary it already relies on; the same holds for Google Workspace customers on Vertex AI. An organization on AWS goes one step further: with Bedrock in its own account, the meeting content never even passes through InterMIND's cloud tenant on the way to the model. The gateways InterMIND uses are configured with **zero data retention** and **no training on customer content** — settings that are Azure OpenAI's default for the EU Data Zone and Google Cloud's contractual position for Vertex AI (see the sources at the end). InterMIND's own [subprocessors page](https://intermind.com/legal/subprocessors) lists Microsoft and Google with region and purpose; it lists Google only for organizations that selected Vertex AI. ## What leaves the organization for an AI call, and what does not Each AI feature sends only what it needs, once: - **Meeting recap:** the meeting transcript and the chat window of that session, at meeting end. - **Document summary:** the extracted text of a document shared in the meeting chat. - **Writing assistant:** the text of the note being edited. - **Ask AI:** the question and the documentation it searches. - **Mia in the meeting:** the question addressed to her, the transcript so far, the chat and shared documents of the session, and the recaps of the room's previous sessions. What never goes to a language model: audio and video streams, recordings, and speech recognition. Live translation of voice, chat and notes runs on InterMIND's own engine in the EU — it is a separate pipeline from the AI features and does not use any hyperscaler gateway. The [Security page](https://intermind.com/docs/security) has the full table of what each party sees. ## The off switch Some organizations do not want any language model near their meetings, whichever gateway it is. The **AI features** switch on the Billing page turns every AI feature off for the whole organization: recaps arrive without a summary, documents are shared without a summary, the writing assistant and Ask AI are hidden, and Mia does not listen. Transcription and translation keep working, because they do not depend on a language model. Turning the switch back on restores everything. This is the setting a client's security questionnaire asks about first — "can AI features be disabled at the tenant level?" — and the answer is yes, per organization, by its own admin. ## Mia: an AI participant that speaks every participant's language *Status, 19 September 2026: Mia in meetings is in preview — it is being tested inside InterMIND; any account can switch her on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). This section describes how she works in the preview.* Mia is the part of this that people notice in a meeting. Say her name — "Mia, what did we agree on last time?" — or write to her in the private mode of the meeting chat (the lock next to the message field), and she answers from this meeting's transcript, chat and shared documents, and from the recaps of the previous sessions of the same room. Two design decisions matter for the perimeter question: - **Mia runs on the organization's gateway**, like every other AI feature, and her voice is synthesized by the same vendor (Azure AI Speech or Google Cloud Text-to-Speech, EU regions). On an organization's own endpoint she answers in text. - **Mia is not a participant of the call.** Her answer is written natively in each language present in the room and voiced on each participant's own device. Nothing of hers enters the audio stream, the recording or the transcript, and every participant hears her in their own language. ## How meeting tools handle the same question today The table states what each vendor's public documentation says about where its AI runs and what the customer can choose. It is a list of documented facts, not a ranking. | Vendor | Model provider named in public documentation | Customer chooses the gateway or region? | Documented sovereignty option | Source, checked September 2026 | | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Zoom** | Sub-processor list names Anthropic (US, SCCs), OpenAI (US/EU, SCCs), Perplexity and Suki AI as "Intelligent Features Service Provider" receiving customer content when AI features are enabled | Not stated as a customer choice | Not stated in the sub-processor list | [Zoom sub-processors](https://www.zoom.com/en/trust/subprocessors/){rel=""nofollow""}, page updated 2026-04-29 | | **Otter.ai** | Anthropic Claude for summaries and queries, under a zero-data-retention agreement (per a Claude customer story) | Not stated | Enterprise plan controls ("keep data out of training", SSO/SCIM) | [Claude customer story: Otter](https://claude.com/customers/otter){rel=""nofollow""}; [Otter Enterprise](https://otter.ai/enterprise){rel=""nofollow""} | | **Fireflies.ai** | Security page names no model provider | Not stated | Enterprise "Private Storage": recordings and transcripts in the customer's own S3/GCS bucket (storage, not the model) | [Fireflies security](https://fireflies.ai/security){rel=""nofollow""}; [Private Storage announcement](https://fireflies.ai/blog/fireflies-private-storage){rel=""nofollow""}, 2023-08 | | **tl;dv** | Anthropic for generative AI, on anonymised and shuffled segments | Yes — the customer chooses EU or US for AI processing | "Privately hosted AI is available on request at Enterprise level" | [tl;dv security commitment](https://tldv.io/features/security-commitment/){rel=""nofollow""}; [tl;dv on GDPR-compliant assistants](https://tldv.io/blog/gdpr-compliant-meeting-assistants-you-can-actually-trust/){rel=""nofollow""}, 2025-12-08 | | **InterMIND** | Microsoft (Azure OpenAI, EU Data Zone) by default; Google (Vertex AI, EU) when selected; Amazon Bedrock in the organization's own AWS account; or the organization's own endpoint | Yes — the organization admin picks the gateway; AI can be switched off per organization | The gateway the organization already uses for its own AI, or its own endpoint | [Subprocessors](https://intermind.com/legal/subprocessors); [Security](https://intermind.com/docs/security) | Two things stand out in that table without any verdict. Region choice for AI processing exists in the category (tl;dv documents EU or US). A choice of the **gateway itself** — running the vendor's AI on the customer's own hyperscaler tenant, or in the customer's own AWS account — is not documented by the vendors above; it is the axis this post is about. ## What the host's IT, or a client's reviewer, can verify The questions below are the ones that recur in AI vendor security reviews in 2026 — a vendor-side guide to those reviews lists written zero-training policies extending to third-party model providers, sub-processor transparency naming the model provider and region, and the ability to disable AI as consistently requested items (see the sources). Here is where each answer is verifiable for InterMIND: - **Which model provider, in which region?** The [subprocessors page](https://intermind.com/legal/subprocessors) names Microsoft (Azure OpenAI, EU Data Zone) and, for organizations that selected it, Google (Vertex AI, EU multi-region). The gateway an organization uses is visible to its admin on the Billing page. - **Does the model provider train on our content?** No. Zero data retention and no training are the configured terms on both gateways; the provider's own documentation for those terms is linked in the sources. - **Can we keep our content out of your AI vendor entirely?** Yes: bring your own endpoint, or, on AWS, your own Bedrock account. The key you enter is stored encrypted and never displayed again. - **Can we turn AI off?** Yes, per organization, by its admin; transcription and translation are unaffected. - **What does an AI call contain?** Listed feature by feature above and on the [Security page](https://intermind.com/docs/security) — never audio, never video, never recordings. ## FAQ **Which AI providers does InterMIND use for meeting recaps?** By default, Azure OpenAI in Microsoft's EU Data Zone, from InterMIND's own tenant. An organization admin can switch the organization to Google Vertex AI on Google's EU multi-region endpoint, to Amazon Bedrock in the organization's own AWS account, or to the organization's own OpenAI-compatible endpoint. The choice applies to every AI feature of the organization. **Can we run InterMIND's AI features on our own Azure or Google Cloud tenant?** Not on your tenant — on ours, on the same gateway your tenant uses: Azure OpenAI or Vertex AI. For your own tenant or your own hardware, choose **Your own endpoint** and point InterMIND at any OpenAI-compatible server, for example vLLM in your data centre or a model deployment in your own cloud project. For AWS, the Bedrock option works in your own account by design. **Can AI features be disabled for the whole organization?** Yes. The AI features switch on the Billing page turns off recaps, document summaries, the writing assistant, Ask AI and Mia for every meeting of the organization. Transcription and live translation keep working, because they run on InterMIND's own engine, not on a language model. **Does the meeting audio go to the AI provider?** No. Audio and video streams, recordings and speech recognition never reach a language model. The AI features receive text: the transcript and chat window at meeting end for a recap, a document's extracted text for its summary, a note's text for the writing assistant, a question for Ask AI or Mia. **Is meeting content used to train the AI models?** No. Azure OpenAI in the EU Data Zone and Vertex AI are configured with zero data retention and no training on customer content; the providers' documentation of those terms is linked in the sources below. On your own endpoint, retention and training are whatever you configure. **Where does Mia's voice come from, and is she in the recording?** Mia's voice is synthesized by the same vendor as the organization's gateway — Azure AI Speech or Google Cloud Text-to-Speech, in EU regions. She is not a participant of the call: her answer is voiced on each participant's device in that participant's language, so it is not in the audio stream, the recording or the transcript. **What happens to an organization's AI settings for guests in a meeting?** The meeting host's organization decides. What a guest meets of the room's AI — Mia's spoken answers to others and her notes in the chat — runs on the host organization's gateway and under its switch; a guest cannot change either. Mia answers questions from licensed participants of paid plans only, so a guest's own question gets no answer from her. --- ## See it for yourself - **[Read the Security page](https://intermind.com/docs/security)** — the AI gateway table, what each party sees, and how to switch AI off. - **[Try the live demo](https://intermind.com/demo)** — the production translation pipeline on your own audio, no signup. - **[See the subprocessors list](https://intermind.com/legal/subprocessors)** — vendor, country, purpose, data, location and safeguards for every party. - **[Read the speech-to-text comparison](https://intermind.com/blog/speech-to-text-on-your-own-gateway)** — the three gateways' speech services on the same 153 voice notes, and why the recogniser follows the gateway. --- *Sources: Zoom sub-processors ([zoom.com/en/trust/subprocessors](https://www.zoom.com/en/trust/subprocessors/){rel=""nofollow""}, page updated 2026-04-29); Otter.ai ([Claude customer story](https://claude.com/customers/otter){rel=""nofollow""}, [Otter Enterprise](https://otter.ai/enterprise){rel=""nofollow""}); Fireflies.ai ([security](https://fireflies.ai/security){rel=""nofollow""}, [Private Storage](https://fireflies.ai/blog/fireflies-private-storage){rel=""nofollow""}, 2023-08); tl;dv ([security commitment](https://tldv.io/features/security-commitment/){rel=""nofollow""}, [GDPR-compliant meeting assistants](https://tldv.io/blog/gdpr-compliant-meeting-assistants-you-can-actually-trust/){rel=""nofollow""}, 2025-12-08); Azure OpenAI data handling and EU Data Zone ([Data, privacy, and security for Azure OpenAI](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/data-privacy){rel=""nofollow""}); Google Cloud generative AI data governance for Vertex AI ([Generative AI and data governance](https://cloud.google.com/vertex-ai/generative-ai/docs/data-governance){rel=""nofollow""}); Amazon Bedrock data protection ([Data protection in Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html){rel=""nofollow""}); AI vendor security review items ([Merciv, AI vendor security review process](https://www.merciv.com/blog/ai-vendor-security-review-process){rel=""nofollow""}, 2026-07-07); InterMIND statements verified against the shipped code and [/legal/subprocessors](https://intermind.com/legal/subprocessors); all checked September 2026.* # Meeting cadence: how often each meeting should happen, with a template for a team of 5 to 50 — and where each recurring meeting keeps its history (2026) - **Cadence is set per meeting, not per team.** Daily for blockers, weekly for decisions, every two weeks for review, quarterly for direction; a template covers 5 to 50 people. - **A series is only as good as its memory.** Teams, Zoom, Google Workspace and Slack leave one document per occurrence, in the meeting's language. - **InterMIND keeps the whole meeting in each member's language,** every session in one channel, next to Teams or Slack, not instead of them. Guests join free by link, no account; you pay only for active members. Meeting cadence is the fixed rhythm of a recurring meeting: how often it happens, on which day and at which hour, and for how long. It is set once, per meeting series, and then left alone — the point of a cadence is that nobody schedules the meeting, nobody asks whether it is on this week, and the work between two occurrences is shaped by the knowledge of when the next one is. A team's "meeting rhythm" or "operating rhythm" is the set of all its cadences together: the daily, the weekly, the one-on-ones, the monthly, the quarterly, and how they fit into one calendar without colliding. This guide is the craft first — what cadence is and what it isn't, the four rules for choosing one, the cadence of each meeting most teams run — then a template you can copy, sized for a team of 5, 15 and 50 with the hours it costs each person per week, and the signals that a cadence should change. The last part is the one most cadence guides skip: a recurring meeting is a series, and a series is only as useful as its memory. Where the history of each one lives — in the tools your team already uses, and in a channel built to keep it — decides whether the weekly of three weeks ago is a search or a question to the room. ## What meeting cadence is — and what it isn't Three words get used for the same calendar entry, and they are not the same thing: | | What it fixes | Decided by | Changes | | ------------ | --------------------------------------------------- | ----------------------------------- | --------------------------------------------------- | | **Cadence** | How often, which day and hour, how long | The team, once per series | When the team's work changes — quarterly at most | | **Schedule** | The next occurrence's date and the people invited | The organizer, per occurrence | When someone is away or a holiday falls on the slot | | **Agenda** | What this occurrence is for: items, owners, minutes | The owner of the meeting, each time | Every occurrence | The cadence is the slow layer. A weekly that moves every week has a schedule but no cadence, and the team pays for it twice: once in the scheduling, and again in the work that cannot be planned around a slot that keeps moving. The agenda is the fast layer, and it has [its own guide](https://intermind.com/blog/meeting-agenda-template); this one assumes each occurrence has a list. Cadence is not "how many meetings we have". A team with a daily stand-up, a weekly and one-on-ones has three cadences and a sane week; a team with the same three meetings booked ad hoc has none and a full calendar. And it is not a company-wide number: the right cadence for a stand-up and for an all-hands differ by a factor of twenty, which is why cadence is set per meeting and then assembled into a rhythm, not chosen once for everything. ## Four rules for choosing a cadence **1. The cadence follows the rate of decisions, not the calendar.** Ask how long a question can wait before the wait costs more than the meeting. A blocker costs a day for every day it is not raised, so the meeting that surfaces blockers is daily. A scope decision can wait a week without harm, so the meeting that makes it is weekly. A direction change — what the team is for, who is on it — is a quarter's question. If you find yourself calling a meeting between occurrences, the cadence is too slow; if occurrences are cancelled for lack of items, it is too fast. **2. The cost is headcount times length times frequency.** A 30-minute weekly for 12 people is six hours a week, 300 hours a year. Written down next to what the meeting produces, that number decides most cadence arguments on its own. Set a budget per person — two to four hours a week of recurring meetings is a common range for a team member, more for a lead — and let the cadences compete for it, so adding one means slowing another. **3. A fixed slot, the same link, rescheduled and never cancelled.** Same day, same hour, same meeting link for every occurrence. A series that keeps its slot can be planned around; a series that keeps its link has one address for its history. When the slot cannot be held — a holiday, a trip — the occurrence moves, it does not disappear: a cancelled meeting tells the team the cadence is optional, and from then on it is. How the series itself is set up in Google Calendar and Outlook — the pattern, the end rule, one occurrence moved without the rest — is in [recurring meeting](https://intermind.com/blog/recurring-meeting). **4. Each occurrence reads from the last one.** A recurring meeting is a series, and the series has a memory: the open items of last time are the first thing checked this time, and the parking lot of this time is the start of the next agenda. A cadence without that thread is a set of unrelated meetings that happen to share a slot; the thread is what makes a weekly a weekly. Where the thread lives — in whose notes, in which tool, in which language — is the subject of the second half of this guide. ## The cadence of each meeting most teams run The cadences below are the ones teams converge on in practice; the reasoning is rule 1 applied to each meeting's purpose. The length is the ceiling. | Meeting | Cadence | Length | What it produces | Who | | -------------------------- | -------------------------------------------------------------- | ---------- | --------------------------------------------------- | ----------------------- | | **Stand-up** | Every working day, same hour | 15 min | Today's blockers, a name per blocker | One team | | **Weekly team meeting** | Weekly, fixed day | 30–60 min | Decisions, priorities for the week, open items | One team | | **One-on-one** | Weekly; every two weeks once established | 30–45 min | The report's items, follow-ups, feedback each way | Manager and one report | | **Planning** | Every one or two weeks, at the start of the cycle | 60 min | What is in the cycle, who owns what | One team | | **Review or demo** | At the end of each cycle | 30–60 min | What shipped, shown; what did not, and why | Team and stakeholders | | **Retrospective** | Every two weeks or monthly, after the review | 45 min | Two or three changes to how the team works | One team | | **Leadership meeting** | Weekly | 60 min | Cross-team decisions, risks, hiring | Leads | | **All-hands** | Weekly up to about 30 people; every two weeks or monthly above | 25–45 min | Numbers, one decision explained, questions answered | Everyone | | **Client or partner call** | Weekly during delivery; monthly in steady state | 30–45 min | Scope, next steps, who sends what by when | Account lead and client | | **Quarterly review** | Once a quarter | 90–120 min | Goals for the quarter, the cadence itself reviewed | Team or leads | Two things in the table are not obvious until you have run both. The retrospective sits *after* the review, not before, so that it works from what actually shipped. And the quarterly review is where the cadence itself is on the agenda: once a quarter, every recurring meeting is asked whether it still produces what it was set up for, at the cost it has. The agendas for each of these — the items, owners and minutes — are in [meeting agenda examples](https://intermind.com/blog/meeting-agenda-examples); the stand-up, the one-on-one, the [all-hands](https://intermind.com/blog/all-hands-meeting) and the [project kickoff](https://intermind.com/blog/project-kickoff-meeting) have their own guides. ## A meeting cadence template for a team of 5 to 50 The same cadences assembled into a week, at three sizes. The hours are per person, recurring meetings only, before client calls; they are the budget of rule 2, written out. | Meeting | 5 people | 15 people (2–3 sub-teams) | 50 people (5–7 teams) | | ----------------------------- | --------------------------- | ------------------------------------------------ | ---------------------------------------------------------- | | **Stand-up** | Daily, 10 min, everyone | Daily, 15 min, per sub-team | Daily, 15 min, per team | | **Weekly team meeting** | Weekly, 30 min, everyone | Weekly, 45 min, per sub-team | Weekly, 45 min, per team | | **One-on-one** | Weekly, 30 min | Weekly, 30 min; every two weeks once established | Weekly or every two weeks, 30 min, with the direct manager | | **Planning and review** | Folded into the weekly | Every two weeks, 60 min, per sub-team | Every two weeks, 60 min, per team | | **Retrospective** | Monthly, 45 min | Every two weeks, 45 min, per sub-team | Every two weeks, 45 min, per team | | **Leadership meeting** | — | Weekly, 45 min, the three leads | Weekly, 60 min, the team leads | | **All-hands** | The weekly is the all-hands | Every two weeks, 30 min | Monthly, 45 min | | **Quarterly review** | Half a day, everyone | Half a day, everyone | Half a day per team; one day for the leads | | **Hours per person per week** | About 2.5 | About 3 (leads about 4) | About 3 (team leads about 5) | The template to copy — one block per team, kept where the team talks, so that a new member reads the rhythm on day one: > **\[Team] — our meeting cadence** · reviewed \[date], next review \[date, one quarter on] :br**Budget:** \[hours] per person per week of recurring meetings. > > **Stand-up** — every working day \[time] — 15 min — \[link] — owner: \[rotating facilitator] :br > Leaves behind: today's blockers with a name each, posted in \[channel] by \[time + 20 min]. > > **Weekly** — \[day] \[time] — \[minutes] — \[link] — owner: \[name] :br > Leaves behind: decisions, open items, the parking lot for next week. > > **One-on-ones** — weekly, \[day], 30 min each — the same link per pair — owner: the report :br > Leaves behind: next steps with names and dates, visible to both. > > **Planning and review** — every two weeks, \[day] \[time] — 60 min — \[link] — owner: \[name] :br > Leaves behind: the cycle's scope with owners; what shipped and what did not. > > **Retrospective** — every two weeks, after the review — 45 min — \[link] — owner: \[rotating] :br > Leaves behind: two or three changes to how we work, each with an owner. > > **All-hands** — \[monthly / every two weeks], \[day] \[time] — \[minutes] — \[link] — owner: \[name] :br > Leaves behind: the numbers, the decision explained, every question answered or dated. > > **Rules:** fixed slots, same link every time; an occurrence is rescheduled, never cancelled; each meeting opens with last time's open items; the cadence itself is reviewed at the quarterly. The block is plain text; it pastes into a chat message, a document or a canvas without reformatting. ## The weekly budget: checking a cadence with arithmetic Rule 2 as a worked example, for the 15-person column. A team member attends a daily stand-up (5 × 15 min), a weekly (45 min), a one-on-one (30 min), planning and review every two weeks (30 min a week averaged), a retrospective every two weeks (about 22 min a week averaged) and an all-hands every two weeks (15 min a week averaged): about three hours and ten minutes a week. A lead adds the leadership meeting and two or three one-on-ones on the other side of the table: about four and a half. Across fifteen people that is roughly 50 hours a week, 2,500 a year. The number is not an argument against meetings. It is the price, and the question is whether what the cadence produces — the blockers caught in a day rather than a week, the decisions made on Tuesday rather than in a thread that runs to Friday — is worth it. Usually it is, for the meetings in the table. The arithmetic finds the ones where it is not: the 60-minute weekly that could be 30, the status meeting that duplicates the stand-up, the leadership meeting with nine people and two deciders. ## When to change a cadence: five signals A cadence is reviewed quarterly and changed rarely, because changing it costs the planning that depended on it. Between reviews, five signals say a cadence is wrong now: 1. **Meetings are being called between occurrences.** The questions cannot wait for the slot; the cadence is too slow, or the meeting is the wrong size for the questions it gets. 2. **Occurrences are cancelled for lack of items**, two or three times in a row. Too fast — or the agenda is being collected too late to show that there are items. 3. **Decisions are made elsewhere** and reported to the meeting. The meeting has become a status meeting; either move the decision back into it or shorten it to what it still does. 4. **Open items are older than twice the cadence.** An action item two weeks old on a weekly, a month old on a fortnightly, is a sign the series has no memory — nobody checks last time's list — or that the item is a project, not a task. 5. **Attendance drifts.** When the people who need the decision stop coming and the people who do not keep coming, the slot or the invite list is wrong before the frequency is. The fix is almost never "more meetings". It is one cadence slowed, one sped up, one meeting merged into another, and the parking lot of one series moved to where it belongs. Which meetings to drop altogether, what replaces them in writing and where that writing lives is the subject of [how to improve team productivity](https://intermind.com/blog/how-to-improve-team-productivity). ## Where each recurring meeting keeps its history in the tools you already use A recurring meeting lives in a calendar, and what each occurrence leaves behind lives wherever the tool puts it. Documented behaviour only, from the vendors' own pages; each cell names the month its fact was checked. | Platform | How the series is scheduled | What one occurrence leaves behind | Where it goes, and for whom | | -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Microsoft Teams** | In the Teams calendar: "Select a timeslot on the calendar or select New. Add meeting details and attendees. Turn on the Teams meeting toggle. Select Save"; "when you schedule a meeting in Teams, it'll automatically appear in your Outlook calendar, and vice versa". The scheduling page does not state how a recurring meeting is set up (checked September 2026) | *Notes* in the meeting controls, or *Add an agenda* in the meeting's Details — a Loop component that any attendee or organizer can edit, with tasks assigned by tagging people (checked October 2026). A recap — recording, transcript, shared files, notes, agenda and follow-up tasks — after meetings that were recorded or transcribed; the AI parts require Teams Premium or a Microsoft 365 Copilot license; "not currently available for ad-hoc events" (checked August 2026) | The notes are saved automatically and reachable from the Teams calendar and the meeting recap; external attendees cannot access or edit them (checked October 2026). The recap is generated in the language the meeting was held in (checked August 2026) | | **Zoom Workplace** | A scheduled meeting; AI Companion can generate the agenda when the meeting is scheduled, from the title, a prompt or previous documents (checked October 2026) | A meeting summary with AI Companion — quick recap, summary, next steps — on paid Zoom Workplace plans (checked August 2026) | Sent by email, listed on the Summaries page and postable to the meeting's group chat in Team Chat; participants receive it when the host chose to share it, only the host can edit it, and unauthenticated users do not receive the email. The documentation does not state that a summary can be produced in a different language per participant (checked August 2026) | | **Google Workspace** | A Calendar event with a Meet link; "Recurring meetings keep the same settings as the first meeting" (checked September 2026). On eligible Workspace editions and Google AI plans, *Take notes for me* is switched on in Calendar when the event is created (checked October 2026) | A Google Doc with summary, decisions and next steps, when *Take notes for me* was on (checked October 2026) | The Doc is emailed to the organizer and attached to the event, shared with all guests, organization guests or hosts only, per the setting; "this feature supports one language at a time" (checked October 2026) | | **Slack** | A huddle in the team channel, with "a dedicated message thread to share notes, links, and files" (checked October 2026) | A canvas from the meeting-agenda template, with sections for objectives, time allocations, next steps and action items with due dates (checked October 2026) | The canvas stays in the channel; what was said in the huddle is not in it unless someone types it (checked October 2026) | Across the four, each occurrence leaves one document or one summary, in the language it was written or held in, and the thread between occurrences — last time's open items at the start of this time — is a person's job: someone opens the previous document and reads it into the meeting. Where that is fine, any of the four will do and the table is the whole answer. The next section is one way the job gets done where the series needs a memory of its own, read by members who do not all read the same language. ## How a series keeps its history in a channel InterMIND is a communication space where a recurring meeting lives in a channel. The meeting link is permanent, so the room is the same every occurrence; the cadence is set once, in Google Calendar or Outlook, on an event the product pre-fills with the join link and the recap link — and a one-off room that already met can be made recurring from its row without losing its chat and recaps. Whatever the cadence, the channel keeps the whole series in one place and **in each member's language**: the chat is translated per reader — each member types in their own language and reads the others in theirs, with the original one toggle away — and the channel keeps the recap of every past session, not only the latest, so the weekly of three weeks ago is a switch between sessions on the recap page rather than a question to the room. An ad-hoc meeting by link keeps only its latest recap, and its chat is wiped when the call ends; a series belongs in a channel. Rule 4 is what the recap does. When the call ends, the recap is written from the meeting itself — a summary, the action items with owners — and arrives by email to each signed-in participant, as a message in the channel and as a link in the calendar event, each member reading it in their own language rather than the one the room happened to use. Any member can edit it, every edit keeps author and revision history. In an organization with team status pages on, the open action items of earlier sessions are judged when the next recap is written: an item someone reported finished is marked done, an item discussed but not finished is marked not done with the reason in the words of the meeting, an item nobody brought up stays open — the verdicts on the organization's status page rather than in the recap — and at the start of the next session Mia names the open items and their owners, so last time's list is the first thing spoken about rather than the first thing forgotten. Team status pages are a preview feature: an organization's admin switches them on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). The cadence block itself — the template above — is a note in the channel, where a new member finds it on day one. During the quarterly, the note goes on everyone's screen next to the video tiles with **Share to conference**: the sharer edits it live while the room watches, and every participant reads it in their own language. The same works for a previous session's recap, for reviewing last cycle together before planning the next. A series is members-only. A colleague or a client who belongs in the channel is added by email invitation onto a free account and reads the channel in their language. Someone who needs one occurrence only — a partner for one review, a candidate for one call — joins an ad-hoc meeting by link, from a phone, without an account and at no cost, hears the meeting live in their own language and gets nothing afterwards: the account is free, and it is what makes the record reachable. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing) — joined a meeting, wrote in a chat, asked Mia; a member on leave for a month keeps access and costs nothing that month, and the series they come back to is in the channel, with every session's recap. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. A cadence survives every tool: somebody still has to decide how often, hold the slot, and open each occurrence with what the last one left open. What does not have to survive is the second job — finding last time's document, reading it into the room, and typing this time's up by hand, in one language, for people who read others. ## FAQ **What is meeting cadence?** Meeting cadence is the fixed rhythm of a recurring meeting: how often it happens, on which day and at which hour, and for how long. It is set once per meeting series — a daily stand-up, a weekly team meeting, a monthly all-hands — and left alone, so that nobody schedules the meeting and the work between occurrences can be planned around it. A team's meeting rhythm is all of its cadences together. **What is a good meeting cadence?** One that matches how long each kind of question can wait. Blockers cannot wait a week, so the meeting that surfaces them is daily and short; decisions can wait a week, so the team meeting is weekly; review and planning follow the team's cycle, every one or two weeks; direction is quarterly. A good cadence also fits a budget — two to four hours a week of recurring meetings per team member is a common range — and is reviewed once a quarter rather than changed ad hoc. **How often should a team meet?** For most teams of five to fifty: a daily stand-up of fifteen minutes or less, a weekly team meeting of 30 to 60 minutes, one-on-ones weekly or every two weeks, planning and review every one or two weeks, a retrospective every two weeks or monthly, and an all-hands weekly up to about thirty people and every two weeks or monthly above that. The template in this guide lays the set out for 5, 15 and 50 people with the hours it costs each person. **What does cadence mean in meetings?** Cadence means the regular, repeating interval at which a meeting is held — "a weekly cadence", "a two-week cadence" — and by extension the fixed day, hour and length that come with it. A "cadence meeting" or "cadence call" is a recurring meeting held on that interval, usually between a team and a stakeholder or a client, to review progress and next steps; the term is common in sales and in client delivery. **How often should one-on-ones be?** Weekly, 30 minutes, for a new report in their first 90 days and for anyone remote or in another time zone; every two weeks, 45 minutes, once the relationship is established and the work is going well, with a monthly session for growth replacing one regular one. The rule that matters more than the interval: a one-on-one is rescheduled, never cancelled. The [one-on-one meeting template](https://intermind.com/blog/one-on-one-meeting-template) has the structure and the questions. **How do you decide the cadence of a recurring meeting?** Ask what the meeting produces and how long that result can wait: the wait sets the frequency. Multiply headcount by length by frequency to see the cost, and set it against a per-person budget so that adding one cadence means slowing another. Fix the slot and the link, open each occurrence with the last one's open items, and put the cadence itself on the agenda of the quarterly review. Change it when meetings get called between occurrences, when occurrences are cancelled for lack of items, or when open items grow older than twice the interval. **What is the difference between meeting cadence and meeting rhythm?** Cadence is the property of one recurring meeting — its frequency, slot and length. Rhythm, or operating rhythm, is the set of all a team's or a company's cadences and how they fit together: the daily inside the weekly, the weeklies inside the monthly, the quarterly review where the rhythm itself is adjusted. You choose cadences one meeting at a time and then check that the rhythm fits in the budget and the calendar. --- *Sources: [Microsoft — Schedule a meeting in Microsoft Teams](https://support.microsoft.com/en-us/office/schedule-a-meeting-in-microsoft-teams-943507a9-8583-4c58-b5d2-8ec8265e04e5){rel=""nofollow""}; [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""}; [Zoom — Generating meeting agenda with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0081706){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Google Meet — Start or schedule a Google Meet video meeting](https://support.google.com/meet/answer/9302870){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Use huddles in Slack](https://slack.com/help/articles/4402059015315-Use-huddles-in-Slack){rel=""nofollow""}; [Slack — Meeting agenda template](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Each table cell names the month its fact was checked — the earliest checked August 2026, the latest checked October 2026. Vendors change plans, features and language lists over time; check their pages for the current state.* # Meeting notes template: what to capture, who writes them now, and where they live after the call (2026) - **Six elements, outcomes not dialogue.** Header, purpose, a block per item marked decided, open or deferred, decisions, actions with owner and date, a parking lot. - **Every tool keeps the notes in one language.** In Teams, Zoom, Google Workspace and Slack they sit beside the meeting; last week's actions are checked by hand. - **InterMIND keeps the whole meeting in each member's language,** note, chat and recap, next to those tools rather than instead of them. Guests join free by link, no account; you pay only for active members. Meeting notes are the working record of a meeting: what was said that matters, what was decided, who does what by when, and what was raised but not resolved. They are written during the call, by one person, and they are read afterwards by everyone — including the people who weren't there. Notes are lighter than [minutes](https://intermind.com/blog/how-to-write-meeting-minutes) and fuller than a [recap](https://intermind.com/blog/meeting-recap); they are the document the other two are made from. This guide is the craft first — what to capture, a template you can copy, two filled-in examples — then the mechanics: where the notes live in the tools your team already uses, and what happens to them after the call. The second half matters more than it looks. The notes' real test is not the meeting; it is three weeks later, when someone asks whether item 2 was ever done. ## Meeting notes, minutes and the recap Three records come out of a meeting, and people use the words interchangeably. They aren't the same document: | | Written | What it holds | Tone | Who reads it | | ----------- | --------------------- | --------------------------------------------------------------------------- | --------------- | -------------------------------------------------------------------------- | | **Notes** | During the call | What was said that matters, decisions, actions, open questions | Working, plain | Everyone invited, the same day; the note-taker, when writing the other two | | **Minutes** | After, from the notes | Attendance, each item, decisions with how they were reached, votes, actions | Formal, neutral | Members, auditors; the body that approves them | | **Recap** | After, from the notes | Decisions, action items, open questions — one screen | Short | Everyone invited, a month later | Notes are the raw material. A meeting with a chair and votes turns them into minutes; a working call turns them into a recap. If there are no notes, the other two get written from memory, which is how a decision becomes three different decisions by Friday. One thing notes are not: a transcript. Writing down what everyone said is a different job, and in 2026 it is a machine's job. The note-taker writes down what the meeting *meant*. ## What to capture: the format A usable page of meeting notes carries six elements. Most templates you'll find are a subset of this list, and the ones that fail usually leave out the last two: 1. **The header.** Meeting name, date, the link, who was there and who sent apologies. Thirty seconds, before anyone speaks. 2. **The purpose, in one sentence.** Copied from the [agenda](https://intermind.com/blog/meeting-agenda-template) if there is one; written on the spot if there isn't. It is the line against which the notes are judged at the end: did the meeting produce this? 3. **One block per item, in agenda order.** Two or three lines of what was said — positions, not a play-by-play, attributed only when it matters. Then the outcome, marked: *decided*, *open* or *deferred to a date*. 4. **Decisions, each in one sentence.** The sentence starts "we agreed" and contains the thing agreed, not the discussion that led to it. A decision buried inside the discussion text is a decision nobody will find. 5. **Action items — owner, task, date.** One line each. An action with no owner is a wish; an action with no date is a hope. Both go in the parking lot instead. 6. **The parking lot.** Anything raised that the meeting did not resolve, with the name of the person who raised it. It feeds the next agenda. This is the element most templates drop, and the reason the same question gets asked in three consecutive meetings. What stays out: verbatim quotes unless someone asks to be quoted, tone, the note-taker's opinion, and anything said off the record. A reader should not be able to tell whose side the note-taker was on. ## How to take meeting notes: before, during, after **Before the meeting, build the skeleton.** Take the agenda and turn it into headings: one block per item, the header pre-filled from the invitation, the previous session's open actions pasted at the top. Ninety percent of the formatting happens before the call. If there is no agenda, the first note of the meeting is that there wasn't one. **During the meeting, write outcomes, not dialogue.** For each item you need the positions raised, the decision, and the actions. The habit that does most of the work: when a decision is made, read it back aloud — "so I'm noting: two languages for the Q4 campaign, Lena owns the brief by the 12th" — and let the room correct it while everyone still remembers. Reading the outcome back is what turns a conversation into a record while the people who had it are still in it. If an item runs out of time, it is not resolved; it goes to the parking lot with a date. **After the meeting, publish the same day.** Clean up the notes while the context is fresh — ten minutes, not an evening — and send them to everyone invited, including, especially, the people who missed the meeting. Then put them where the next meeting will find them. Notes that live in one person's notebook are notes the team doesn't have, and the parking lot in them is a parking lot nobody will empty. ## A meeting notes template > **\[Team] — \[Meeting name] — notes**:br**Date:** \[date] · **Time:** \[start]–\[end] · **Link:** \[meeting link] :br**Present:** \[names] · **Apologies:** \[names] · **Notes:** \[name] :br**Purpose:** \[one sentence — what this meeting is for] :br**Open from last time:** \[action] — \[owner] — \[done / not done] > > **1. \[Item]** — \[owner] :br > \[Two–three lines: what was said that matters, positions attributed only where it matters.] :br**Outcome:** decided / open / deferred to \[date] :br**Decision:** \[one sentence — "we agreed …"] :br**Action:** \[name] — \[task] — by \[date] > > **2. \[Item]** — \[owner] :br > \[Summary.] :br**Outcome:** \[decided / open / deferred] :br**Action:** \[name] — \[task] — by \[date] > > **Decisions (all items, one line each)**:br > – \[decision] :br > – \[decision] > > **Action items**:br > – \[name] — \[task] — by \[date] :br > – \[name] — \[task] — by \[date] > > **Parking lot:** \[question] — raised by \[name] — to the next agenda :br**Next meeting:** \[date] · **Record:** \[link to recording / document] The two lists at the bottom repeat what is already in the item blocks. That is deliberate: the blocks are for the people who were there, the lists are for the people who weren't. ## Two filled-in examples ### Weekly team meeting — 30 minutes > **Product — Weekly — notes**:br**Date:** 6 October 2026 · **Time:** 10:00–10:30 · **Present:** Mateusz, Priya, Lena, Tomás (notes) · **Apologies:** Ana :br**Purpose:** unblock this week's work and decide what we don't ship. :br**Open from last time:** Priya — interview slots to the two finalists — done. > > **1. Blockers raised in the channel** — everyone :br > Two blockers: the export job fails on files over 50 MB (Mateusz); the staging login loops on Safari (Lena). Lena has a fix in review. :br**Outcome:** open :br**Action:** Mateusz — reproduce the export failure with a 60 MB file — by 7 Oct > > **2. Scope cut for the release: drop the export or ship it unpolished?** — Mateusz :br > Mateusz would ship the export behind a flag; Priya would drop it and avoid a support wave. Lena noted the two enterprise trials asked for it. :br**Outcome:** decided :br**Decision:** we agreed to ship the export behind a flag, on for the two trials only. :br**Action:** Mateusz — flag and trial allowlist — by 9 Oct > > **3. Hiring: finalists** — Priya :br > Both finalists interviewed; Priya recommends the second. No objections. :br**Outcome:** decided :br**Action:** Priya — offer to the second finalist — by 8 Oct > > **Parking lot:** should the 50 MB limit be raised? — raised by Mateusz — to next week's agenda :br**Next meeting:** 13 October 2026, 10:00 ### Client call — 45 minutes > **Aster GmbH — scope call — notes**:br**Date:** 7 October 2026 · **Time:** 14:00–14:45 · **Present:** L. Ortega, K. Sato (Aster); J. Lindqvist, P. Nowak (notes) :br**Purpose:** agree the scope change and its price before the end of the month. > > **1. What changed since the last call** — J. Lindqvist :br > The pilot ran in three countries instead of two; Aster wants Japanese support in the first phase. :br**Outcome:** information > > **2. The scope change: what is in, what is out** — K. Sato :br > In: Japanese support, the third country. Out: the custom report, which moves to phase two. Ortega wants the phase-two date in writing. :br**Outcome:** decided :br**Decision:** we agreed phase one is three countries plus Japanese support; the custom report is phase two. > > **3. Price and timeline options** — J. Lindqvist :br > Two options presented; Aster prefers the fixed-price one but needs the finance sign-off. :br**Outcome:** deferred to 14 October :br**Action:** J. Lindqvist — revised statement of work with both options — by 10 Oct :br**Action:** L. Ortega — finance sign-off on the fixed-price option — by 14 Oct > > **Parking lot:** phase-two start date — raised by L. Ortega — to the 14 October call :br**Next call:** 14 October 2026, 14:00 · **Record:** the current statement of work Notice what both examples have in common: every item ends in one of three words, every action has a name and a day, and the parking lot is not empty. Forty-five minutes of talking became a page a person who wasn't there can act on — that is the whole job. ## Where the notes live in the tools you already use Each major platform has a place for the notes, and each stops at a different point. Documented behaviour only, from the vendors' own pages, with the month each page was checked: | Platform | Where the notes are written | What happens to them after the meeting | | -------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | *Notes* in the meeting controls during the call, or *Add an agenda* in the meeting's Details when scheduling; the notes are a Loop component that any attendee or organizer can edit, with tasks assigned by tagging people | Saved automatically and reachable from the Teams calendar and the meeting recap; external attendees cannot access or edit the notes (checked October 2026) | | **Zoom Workplace** | Meeting summary with AI Companion is generated from the meeting, in three sections — quick recap, summary, next steps — on paid Zoom Workplace plans; a person's own notes are a separate document | The summary is sent by email, listed on the Summaries page of the web portal and can be posted to the meeting's group chat in Team Chat; participants receive it when the host chose to share it, only the host can edit it, and unauthenticated users do not receive the email (checked August 2026) | | **Google Workspace** | A Google Doc, usually linked from the Calendar event; on eligible Workspace editions and Google AI plans, *Take notes for me* can be switched on in Calendar when the event is created | The notes arrive as a Google Doc after the meeting, shared with all guests, organization guests or hosts only, per the setting; the feature supports one language at a time — multiple languages spoken in the same meeting are not supported (checked October 2026) | | **Slack** | A canvas from a template, shared in the channel, with sections for objectives, next steps and action items with due dates | The canvas stays in the channel as a document; what was said in the call is not in it unless someone types it (checked October 2026) | Two things are the same everywhere. The notes are a document next to the meeting, kept in the one language the room used; and whether last week's action items were done is a question the document does not answer — a person goes and checks. ## Who writes them now — and where they live afterwards InterMIND is a communication space where a meeting lives in a channel, so the notes have an obvious home: the channel's chat. The skeleton goes in the day before as a note; during the call, the note-taker can put it on everyone's screen next to the video tiles with *Share to conference*, edit it live while the room watches, and every participant reads it in their own language, with the original a toggle away — as they read the channel's chat around it, typed by each member in their own language. Notes drafted somewhere else land in the channel by email — every channel has its own address, and a message sent to it appears as a regular message with the sender named and attachments kept. When the call ends, the recap is written from the meeting itself — a summary, the points marked agreed, open or disputed, the action items with owners, each line keeping its timestamp — so the note-taker edits a draft instead of writing one. It arrives by email, as a message in the channel and as a link in the calendar event, and every signed-in member reads it **in their own language**: the record is translated per reader, not written once in the language the room happened to use. Any member can edit it, every edit keeps author and revision history, and the channel keeps the recap of every past session, so item 2 from three weeks ago is one click away. The parking lot and the action list are where the notes usually die, and where an organization with team status pages on has the checking done instead: when the next recap is written, the open action items of earlier sessions are judged against what was said — an item someone reported finished is marked done, an item discussed but not finished is marked not done with the reason in the words of the meeting, an item nobody brought up stays open — with the verdicts on the organization's status page, and at the start of the next session Mia names the open items and their owners. Team status pages are a preview feature: an organization's admin switches them on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). Where the notes need to end up in a system of record, the host adds a recap copy to any address — a CRM or tracker inbound mailbox — and every recap of the meeting or channel is also sent there, after a one-time confirmation of the address; the mechanics are in [a copy of every meeting recap in your CRM, by email](https://intermind.com/blog/how-to-get-a-copy-of-every-meeting-recap-in-your-crm-by-email). A decision taken in the hallway afterwards goes into the channel as a [voice note](https://intermind.com/blog/voice-notes-in-a-team-channel) — it arrives as text within seconds, read by each member in their own language. A guest joins by link, without an account and at no cost — from a phone, in the browser — and hears the meeting live in their own language. There is no record for a guest afterwards — the account is free, and it is what makes the record reachable. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing); members who go quiet keep their access at no cost. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. Notes as a craft survive every tool: somebody still has to decide what the meeting meant. What doesn't have to survive is the second job — retyping the outcomes after the call, in one language, and checking by hand whether anyone did what the last page said. ## FAQ **What should be included in meeting notes?** Six things: the header (meeting name, date, link, who was there); the purpose in one sentence; one block per item with two or three lines of what was said and the outcome marked decided, open or deferred; each decision in one sentence; action items with owner, task and date; and a parking lot of what was raised but not resolved, with the name of the person who raised it. **How do you write meeting notes?** Build the skeleton from the agenda before the call — one heading per item, header pre-filled, last session's open actions at the top. During the call, write outcomes rather than dialogue, and read each decision back aloud so the room corrects it on the spot. Afterwards, clean up for ten minutes, send the notes the same day to everyone invited, and put them where the next meeting will find them. **What is the difference between meeting notes and meeting minutes?** Notes are the working record taken during the call — plain, same-day, for the people who were invited. Minutes are the formal record written from the notes afterwards: attendance, each item, decisions with how they were reached, votes, and actions, in neutral language, and in boards and associations usually the document the organization is required to keep and approve. A working call needs notes and a recap; a meeting with a chair and votes needs minutes — [the minutes guide](https://intermind.com/blog/how-to-write-meeting-minutes) covers that format. **Is there a meeting notes template in Google Docs?** Google documents *Take notes for me* for Google Meet on eligible Workspace editions: switched on in Calendar when the event is created, it writes the notes into a Google Doc after the meeting and shares it per the configured setting, one language per meeting. The template in this guide is plain text, so it pastes into a Google Doc, a Word file, a Slack canvas or a chat message without reformatting. **How do I take meeting notes in Microsoft Teams?** According to Microsoft's documentation, select *Notes* in the meeting controls during a meeting, or *Add an agenda* in the meeting's Details when scheduling. The notes are a Loop component that any attendee or organizer can edit, with tasks assigned by tagging people; they are saved automatically and reachable from the Teams calendar and the meeting recap. External attendees cannot access or edit them. **Who should take notes in a meeting?** Someone who is not running the discussion: the facilitator is busy with the room, and a note-taker who is also chairing writes down their own side. In working meetings the duty rotates or sits with a designated person; in formal bodies it is the secretary. In 2026 a growing share of the first draft is written by the meeting platform from the meeting itself, and the human role shifts to editing — checking decisions, owners and dates before the notes circulate. **Should meeting notes be sent after every meeting?** Yes, the same day, to everyone who was invited and not only to those who attended — the people who missed the meeting are the ones who need them most. Notes that are not sent are notes that exist for one person; the action items in them have no witnesses and the parking lot never reaches the next agenda. --- *Sources: [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Meeting agenda template (canvas)](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Microsoft, Google and Slack pages checked October 2026; the Zoom meeting-summary page checked August 2026. Vendors change plans, features and language lists over time; check their pages for the current state.* # Meeting recap: how to write one, and what Zoom, Teams and Google Meet actually keep after the call (2026) - **Four blocks, same day.** Decisions, actions with owner and date, open questions, where the record is, to everyone invited. - **Platforms keep it in the spoken language.** Zoom, Teams and Meet write a record for the host, shared on the host's decision, in the language the meeting was held in. - **InterMIND keeps the whole meeting in each member's language,** recap and chat history, next to Zoom, Teams or Meet rather than instead of them. Guests join free by link, no account; you pay only for active members. A meeting lasts forty-five minutes. Its recap gets used for months — cited in the next call, searched when a decision is questioned, read by the person who joined the project a week later. That's the part of the meeting that does the work, and it's the part most platforms treat as an afterthought: a summary email to the host, a recording in someone's drive, a chat that scrolls away. This guide has two halves. First, the recap itself — what it is and a template you can send in five minutes. Second, what the platform does for you: where Zoom, Microsoft Teams and Google Meet put the record after the call, who receives it, who can change it, how long it stays, and — the question their documentation answers most clearly of all — in whose language. Every vendor fact is from their public documentation, checked August 2026, linked at the end. What the assistant does *during* the call — speaking up on its own, acting on a request — is a different job, mapped vendor by vendor in [the AI meeting assistant guide](https://intermind.com/blog/ai-meeting-assistant-in-the-meeting). ## What a meeting recap is A meeting recap is a short written record sent after a meeting: what was decided, who does what by when, and what stayed open. It's not [the minutes](https://intermind.com/blog/how-to-write-meeting-minutes) (the fuller, formal record) and not the transcript (every word). It's the three things a reader needs a month later, in the order they'll look for them. A recap that works has four parts: 1. **Decisions** — each one in a sentence, with who agreed. "Agreed" and "still open" are different lines. 2. **Action items** — owner, task, date. One per line. No owner, no item. 3. **Open questions** — what wasn't resolved and who's picking it up. 4. **Where the record is** — a link to the recording, the notes or the document, so the recap doesn't try to be all of them. ### A meeting recap template > **Subject:** Recap — \[meeting name], \[date] > > **Decisions** > > - \[Decision 1] — agreed by \[names]. > - \[Decision 2] — still open; \[name] to propose by \[date]. > > **Action items** > > - \[Name]: \[task] — by \[date]. > - \[Name]: \[task] — by \[date]. > > **Open questions** > > - \[Question] — \[name] to follow up. > > **Record:** \[link to recording / notes / document]. Next meeting: \[date]. Send it the same day, to everyone who was invited — not only to those who attended. The people who missed the meeting are the ones who need it most. That's the manual version. The rest of this guide is about what the platform writes for you, and what happens to it. --- ## Zoom: AI Companion summary, Previous tab, Team Chat **The summary.** Meeting summary with AI Companion produces three sections — "Quick recap", "Summary" and "Next steps" — on Zoom Workplace Pro, Pro Plus, Business, Business Plus, Enterprise and Enterprise Plus accounts. After the meeting, "meeting summaries are sent through email", appear on the Summaries page of the web portal, and can be "posted to the meeting's dedicated group chat in Chat". **Who receives it.** Participants get the summary when "the host chose to share it with them"; admins choose between host only, host and co-hosts, host and invitees in the organization, or all invitees including external parties. Two documented exclusions: "unauthenticated users will not receive an email summary", and people who joined ad hoc "will not receive the summary". **Who can change it.** "Only the host can edit the summary" and "only the host can delete a summary"; recipients can share it onward. **How long it stays.** An admin or user setting, *Auto-delete meeting summaries*, moves summaries to Trash after a set number of days; the article doesn't state a default retention. **Meeting history.** In the web portal, *Meetings → Previous* lists past meetings — "track meeting details, review participant information, and monitor your hosting activity" — with a date filter; expired meeting IDs drop out per Zoom's expiration rules. Account admins use the meeting and webinar history report for longer ranges. **Language.** Zoom lists 32 supported languages for meeting summaries. The documentation doesn't state that a summary can be produced in a language other than the one spoken, or in a different language per participant. Where the live translation layer stops on Zoom is a separate post: [Zoom live translation](https://intermind.com/blog/zoom-live-translation). ## Microsoft Teams: Recap in the chat and calendar **The recap.** "Recaps are available after Teams events, including meetings, town halls, webinars, and calls, that were recorded or transcribed. In a recap, you can find the event recording, transcript, shared files, notes, custom summary, agenda, and follow-up tasks." The AI parts — generated summaries, speaker and timeline markers, AI notes — are *intelligent recap*, which requires **Teams Premium or a Microsoft 365 Copilot license**. **Where it lives.** In the event chat (*View recap* or the Recap tab) and in the calendar event. "Recap notifications, notes, and content aren't currently available for ad-hoc events" — a meeting has to be scheduled, and recorded or transcribed, to have one. **Who can open the recording.** Recordings are stored in OneDrive or SharePoint; invited and attending users can view them, organizers and co-organizers can download and delete. "For now, guests and external attendees can view the recording only if it's explicitly shared with them." Expiration is an admin setting the organizer can adjust or remove. **Language.** Intelligent recap supports a long list of languages; the recap is generated from the transcript in the language the meeting was held in. The translated layer during the call — captions in 31 languages, the Interpreter agent in 10 — is documented as live-only: captions aren't saved and recordings keep original audio ([Teams live translation](https://intermind.com/blog/teams-live-translation)). ## Google Meet: "Take notes for me" **The notes.** Gemini's *Take notes for me* will "automatically capture meeting notes organized in Google Docs and share with your team" — a summary, decisions, next steps and discussion points, with screenshots of presentations shown for 10+ seconds. The organizer gets an email with a link; the document is attached to the Calendar event and accessible to internal invitees per the configured sharing setting — all invited guests including external, internal only, or hosts and co-hosts only. **Who can use it.** Business Standard and Plus, Enterprise Standard and Plus, and the Gemini Education Premium add-on (earlier Gemini Enterprise and AI Meetings & Messaging add-on purchasers keep access). **Language.** English, French, German, Italian, Japanese, Korean, Portuguese and Spanish — and "this feature supports one language at a time. Multiple languages spoken in the same meeting aren't currently supported." Google's speech translation during the call (English ↔ five languages, one pair per meeting) is unavailable in recordings ([Google Meet live translation](https://intermind.com/blog/google-meet-live-translation)). ## The axis the three share Put the three side by side and the same shape appears: the platform writes a record, delivers it to the host (and, on the host's decision, to some of the others), keeps it as long as an admin allows — **in the one language the meeting was held in**. Google says so outright ("one language at a time"); Zoom and Teams document a summary of the spoken transcript. A meeting held in English by a team that reads in Portuguese, Polish and German produces an English record; everyone else works from memory or a second-hand summary. We wrote up the whole axis, vendor by vendor: [how much of your meeting still exists in your language a week later](https://intermind.com/blog/the-meeting-a-week-later). ## InterMIND: the recap as the meeting's own record We build the recap as the thing the meeting leaves behind, so here's ours on the same questions: - **What it contains.** A summary — overview, points marked agreed, open or disputed with the speakers attached, action items with owners, open questions — plus the recording when the session was recorded, on one page. Each line keeps the timestamp it came from. A complete example: [/features/recap](https://intermind.com/features/recap). - **How it's produced.** Ending the call produces it. "There's no note-taker bot in the participant list and no per-meeting toggle to remember." - **Who receives it.** Signed-in members of the meeting get the link by email, in the meeting's chat, and in the calendar event — the link is minted when the meeting is scheduled and stays the same for every session. Opening it requires signing in; forwarding it to someone who wasn't in the meeting grants nothing. A participant who joined as a guest without an account gets the full translated meeting live but no recap afterwards — the account is free, and it's what makes the record reachable. - **Who can change it.** Any signed-in member can edit the summary; every edit becomes a revision with author, timestamp and a word-level diff. The host can delete a session's artifacts — summary, transcript, recording and their translations — permanently. - **How long it stays.** Channels keep the recap of every past session; ad-hoc meetings keep the latest session's, mirroring how their chat is purged after each call. The host can also BCC every recap to extra addresses — a CRM inbound address, for instance — after a one-time confirmation. - **In whose language.** The recap is displayed in the reader's language — the summary is translated for each member on demand, whatever language the meeting was held in. The chat history of the channel reads the same way ([multilingual chat](https://intermind.com/features/multilingual-chat)). - **Where it runs.** The summary runs on the AI gateway your organization selects, in an EU region, with zero data retention and no training on your content; the provider doesn't store the transcript ([where one InterMIND meeting actually runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs)). --- ## The comparison, in one table | | What's produced | Who receives it | Who can edit | How long it stays | In whose language | | ------------------- | --------------------------------------------------------------------------- | ---------------------------------------------------------------------------------- | ------------------------------------------------------- | ---------------------------------------------------- | ------------------------------------------------ | | **Zoom** | AI Companion summary: quick recap, summary, next steps (Pro and above) | Host; others per host/admin sharing setting; not unauthenticated or ad-hoc joiners | Host only | Admin/user auto-delete setting; no default stated | The spoken language; 32 summary languages listed | | **Microsoft Teams** | Recap: recording, transcript, files, notes; AI summary with Premium/Copilot | Attendees via chat and calendar; guests see the recording only if shared | Organizer controls recording; recap content per license | Admin expiration setting, adjustable by organizer | The spoken language | | **Google Meet** | Take notes for me: Google Doc with summary, decisions, next steps | Organizer by email; invitees per sharing setting | Google Doc permissions | Google Drive retention | One language per meeting (8 supported) | | **InterMIND** | Summary with timestamps + recording at one permanent link | Signed-in members by email, chat and calendar | Any member, with revision history; host deletes | Channels keep every session; ad-hoc keeps the latest | Each reader's own language | --- ## See it instead of reading about it - **[Open the example recap](https://intermind.com/features/recap)** — a complete recap rendered by the same code that writes yours, timestamps included. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener in any of 23 languages. - **[Start your first meeting](https://intermind.com/chats)** — guests join by link, each in their own language. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, monthly translation quality on real traffic, with the methodology public. --- ## FAQ **What does "meeting recap" mean?** A short written record sent after a meeting: the decisions made, the action items with owners and dates, and what stayed open — with a link to the recording or notes. It's shorter than minutes and far shorter than a transcript; its job is to be read a month later by someone who needs the outcome, not the conversation. **How do I write a meeting recap email?** Four blocks, in this order: decisions (each with who agreed, "still open" as its own line), action items (owner, task, date — one per line), open questions (with who follows up), and where the record is. Send it the same day to everyone invited, including the people who missed it. The template above fits in one screen. **How do I see my Zoom meeting history?** Sign in to the Zoom web portal, open *Meetings* and click the *Previous* tab — past meetings with details and participants, filterable by date. Expired meeting IDs drop out per Zoom's rules; account owners and admins use the meeting and webinar history report for account-wide history. AI Companion summaries live separately, on the Summaries page. **How do I find a Teams meeting recap?** Open the meeting's chat and select *View recap* (or the Recap tab), or open the event in your Teams calendar. A recap exists for scheduled meetings that were recorded or transcribed; ad-hoc meetings don't get one. The AI summary and notes inside it need Teams Premium or a Copilot license. **Does Google Meet make a meeting summary?** With *Take notes for me*, on Business Standard and Plus and Enterprise Standard and Plus editions: a Google Doc with summary, decisions and next steps, emailed to the organizer and attached to the calendar event. It works in eight languages, one language per meeting — "multiple languages spoken in the same meeting aren't currently supported". **Which platform keeps the recap in each participant's language?** Among the four above, the vendors' documentation describes Zoom's, Teams' and Meet's records as produced from the spoken language — Google states one language per meeting. InterMIND displays the recap in each reader's language, translated on demand, alongside a channel history that reads the same way. **Do guests get the InterMIND recap?** A participant who joins by link without an account gets the meeting live, fully translated, and nothing afterwards — recaps are members-only and require signing in. The account is free; it's what makes the recap and the history reachable. --- *Sources: [Zoom — Using Meeting Summary with AI](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}, [Zoom — Enabling or disabling meeting summary with AI](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0057960){rel=""nofollow""}, [Zoom — Supported languages for Zoom AI features](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0078144){rel=""nofollow""}, [Zoom — Viewing your Zoom meeting history](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058985){rel=""nofollow""}, [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""}, [Microsoft — Start, stop, and find meeting recordings in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/start-stop-and-find-meeting-recordings-in-microsoft-teams){rel=""nofollow""}, [Microsoft — Use live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}, [Google Workspace Updates — "Take notes for me" in seven additional languages](https://workspaceupdates.googleblog.com/2025/03/more-languages-for-take-notes-for-me-in-google-meet.html){rel=""nofollow""}, [Google Meet — Learn about Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}. Vendors change plans, features and language lists over time; check their pages for the current state. All facts checked August 2026.* # Microsoft Teams alternatives for teams that work across languages (2026) - **Three axes, not the whiteboard.** Who reads the space in their own language, who hears the meeting in theirs, what history remains a month later. - **Most alternatives translate per reader, on request.** Slack, Google Workspace and Zoom on request or behind an add-on; Mattermost, Rocket.Chat, Element and Nextcloud on your own servers. - **InterMIND keeps the whole space in each member's language,** chat, meetings, documents and recap, next to Teams rather than instead of it. Guests join free by link, no account; you pay only for active members. Search "Microsoft Teams alternatives" and the lists agree with each other: free-tier limits, video quality, whiteboards, how well each tool plugs into Office. Useful if Teams' bundle is your problem. Useless if your actual problem is that **your team's everyday communication happens in more than one language** — the standup, the customer channel, the document somebody pastes at 6 pm — because on those lists every alternative is the same product: a space that assumes everyone reads the same language. This is the other comparison. If you are leaving Teams (or deciding not to) because a Warsaw engineer, a São Paulo account manager and a Jakarta support lead share one channel, three axes decide the purchase — and none of them is the whiteboard: 1. **Messages: does each member read the space in their own language — automatically, or one message at a time on request?** 2. **Meetings: does every participant hear the call in their own language, or does someone hold a license that the rest don't?** 3. **Afterwards: what does the history look like a month later — and in whose language?** One more fact is recorded beside them, not ranked: where it lives — can you name the jurisdiction the messages, files and recordings sit in? Here is Teams' own baseline on those questions, then the alternatives people actually evaluate — Slack, Google Workspace, Zoom Workplace, and the self-hosted trio Mattermost, Rocket.Chat and Element, plus Nextcloud Talk — then us, with one table across all eight. Every competitor fact comes from the vendor's public documentation, checked August 2026, linked in the footer. --- ## The baseline: what you'd be leaving Teams ships more language machinery than most lists give it credit for. The documented shape: - **Chat and channel messages** can be translated one at a time (*Translate* above a message) or automatically — "Teams can automatically translate received messages" — in a list of 100+ languages, on desktop and mobile. The article names no plan or license for this, and notes an admin can switch the option off. It does not state that the translated text is saved; translation is described as something you see, not something the channel keeps. - **Meetings:** translated captions in 31 languages require the **organizer to hold a Teams Premium or Microsoft 365 Copilot license**. The **Interpreter agent** — synthetic translated speech in 10 languages — is licensed **per listener** (Microsoft 365 Copilot) and metered at **20 hours per user per month**, in scheduled meetings only. Captions are not saved; recordings keep original audio only. The full walkthrough: [Teams live translation](https://intermind.com/blog/teams-live-translation). - **Where it lives:** Teams data "resides in the geographic region associated with your Microsoft 365 or Office 365 organization". Country-level residency (France, Germany, Italy, Norway, Poland, Sweden, Switzerland among others) is offered **for new tenants only**; existing tenants in France, Germany, Norway, Switzerland and the UK "will have their data stored in the EMEA region". So a Teams channel where three languages meet is workable on the message level — each reader translates on view — while the meeting layer turns on who holds which Copilot seat, and the history stays in the language each message was written in. If that shape fits your team, staying is a defensible choice. The question is what the alternatives change. ## Slack Slack is the tool most Teams-alternative lists open with. On the three questions, its documentation says: - **Messages:** "Translate message" is an AI feature on the **Business+ and Enterprise+** plans. You set a translation language in your preferences and translate a message on request; "translations are only visible to you, so other people will always see the original message." The language list isn't sized in the guide. - **Meetings:** Huddles carry audio, video and screen sharing — group huddles on Business+ and Enterprise+, 1:1 on Free and Pro. Slack's AI feature guide lists translation for messages; it does not list voice translation for huddles (checked August 2026). - **Afterwards:** the Free plan keeps **90 days of message history**; paid plans keep it. Translated views are per reader and on request, so the stored channel is the original text. - **Where it lives:** data residency is a **Business+ and Enterprise+** feature. European locations documented: Frankfurt, Paris, Stockholm, Zurich, London. Covered: messages, canvases, snippets, files, search index. Not covered: member profiles, workspace membership, usage analytics. As a Teams alternative, Slack changes the licensing shape — translation and residency both sit on Business+ — and keeps the same reading model: one stored language, translated per reader on demand. ## Google Workspace (Chat + Meet) Google's answer is two products under one admin console. Documented: - **Messages:** "Translate for me" in Google Chat detects and translates messages **automatically, in-line**, across **120+ languages** — a per-user setting ("Translate messages to your preferred language"). It requires the **Gemini Business or Enterprise add-on, or the AI Meetings and Messaging add-on** on top of Workspace. - **Meetings:** Meet's speech translation runs **between English and five languages**, **one language pair per meeting**, as a **beta capped at 90 minutes**, unavailable in recordings — no translated audio is saved. Translated captions (text) cover more languages on Business Standard and above. Details: [Google Meet live translation](https://intermind.com/blog/google-meet-live-translation). - **Afterwards:** Chat history is kept per the admin's retention settings; the translation setting describes what a reader sees, not a second stored copy. - **Where it lives:** Data regions let an admin choose **the United States or Europe** for covered data — on Business Standard and Plus, Enterprise Standard and Plus, Frontline and Education editions. Coverage includes Chat messages, attachments and room names, and Meet recordings, transcripts and attendance reports. Users on unsupported editions "aren't covered by data region policies". Against Teams, Workspace trades Copilot seats for Gemini add-ons and gives Chat automatic in-line translation — on the reader's side, add-on attached, English-anchored in the meeting. ## Zoom Workplace (Team Chat + Meetings) Zoom's chat product rarely makes the Teams-alternative lists, but it's in the same bundle as the meetings people already run: - **Messages:** a Team Chat message is translated on request — "click the ellipsis icon… Click Translate. The message will be replaced by the translation", with *Show Original* to revert — in a list of **38 languages**. Prerequisites in the article: message translation enabled by the admin, and **Advanced Chat Encryption disabled**. - **Meetings:** translated captions in 36 languages on Business Plus and Enterprise-tier plans (add-on otherwise); the **Voice translator** — synthetic translated audio in five languages — via the Live Translation add-on, desktop only. Nothing translated is stated to persist. Walkthrough: [Zoom live translation](https://intermind.com/blog/zoom-live-translation). - **Where it lives:** Zoom's **EU Infrastructure** "hosts accounts for EU Education and Enterprise customers" and covers Meetings, Webinar, Chat, Zoom Phone and Contact Center; within it, Zoom "does not transfer outside of or access data from outside this infrastructure unless a prior agreement with a customer is in place", with exceptions for legal requirements, trust-and-safety and service notifications. The shape is Teams' shape with different numbers: per-reader translation on view, voice behind an add-on, residency behind the enterprise tier. ## Mattermost Mattermost is the open-source, self-hosted answer on most lists — and since spring 2026 it has a translation feature of its own: - **Messages:** **Automatic channel translation** (beta, introduced in v11.5) is available **on Enterprise Advanced plans**. Two back-ends: **LibreTranslate**, "a self-hosted, open-source machine translation engine", or **Agents**, "the Mattermost Agents plugin with a configured LLM backend". An admin sets the *Languages allowed*; "a worker picks up the post and translates it sequentially into each configured target language". A user's target language "is determined by their Mattermost display language" — decoupling the two "is not currently supported". - **Meetings:** calls are a Mattermost feature; the auto-translation documentation covers channel posts, not call audio. - **Afterwards:** translations are produced server-side per configured language as posts arrive — on your own server. - **Where it lives:** wherever you deploy it — Professional and Enterprise are sold as self-hosted annual seat licenses; a single-tenant **Mattermost Cloud Enterprise** exists on request. Prices are not listed; "Contact Mattermost sales". Against Teams, Mattermost moves the jurisdiction question onto your own hardware and the translation question onto your own engine or LLM — at the Enterprise Advanced tier, in beta, with you running both. ## Rocket.Chat Rocket.Chat has had message auto-translation longer than any tool on this list, and a free self-hosted tier: - **Messages:** with Auto-Translate enabled per room, "messages you receive in that room will be automatically translated into your selected language"; "each user receives translations based on their own selected language". Providers: **DeepL, Google Translate, Microsoft Translator, LibreTranslate** — the workspace administrator supplies the API credentials, so message text transits whichever provider you configure (LibreTranslate being the one you can host yourself). - **Meetings:** video runs through integrations documented for the Starter plan — Jitsi, BigBlueButton, Pexip, Google Meet, Zoom — so translation inside a call is whatever that integration offers. - **Where it lives:** the **Starter** plan is free, "self-managed, self-hosted", "for technical evaluation or small teams of up to 50 users", and is "automatically provisioned when you deploy Rocket.Chat". Paid tiers are **Commercial, Government and Defense** — on-premises, private cloud or air-gapped — priced on request; the former Pro plan "has been retired to legacy" as of April 29, 2026. Against Teams, Rocket.Chat gives each member their own reading language inside the room, at the cost of running the server and holding a translation-provider key. ## Element (Matrix) Element appears on Teams-alternative lists as the sovereign, end-to-end-encrypted option: - **Messages and meetings:** "the entire platform is end-to-end encrypted by default", including **Element Call** voice and video for 1:1 and group chat. No message or voice translation feature is documented (checked August 2026) — and end-to-end encryption by design leaves no server-side place to put one. - **Where it lives:** **Community** is free — "free of charge frontend and backend", self-hosted; **Enterprise** is priced per seat per month, self-hosted; **Sovereign** is priced per deployment and air-gapped, "no internet connectivity". Against Teams, Element answers the fourth question as completely as software can — and answers the first two with the original language only. ## Nextcloud Talk Nextcloud Talk is "a fully self hosted, on-premises audio/video and chat communication service", and the translation story sits in Nextcloud's AI apps: - **Meetings:** the **live\_transcription** app provides live transcription and translation in Talk calls — "the transcription is done on your own server… while the translation is done using a translation task processing provider". Requirements: Nextcloud 33, the High-Performance Backend, and either an NVIDIA GPU with at least 10 GB VRAM or a 4-thread x86\_64 CPU. 27 languages are listed for transcription. - **Messages:** translation in Talk and other apps goes through Nextcloud's core translation API, backed by the **translate / translate2** apps — local machine translation on your server — or another registered provider. - **Where it lives:** "ideal for on-premises private cloud deployments or hosting with a trusted, local provider". Against Teams, Nextcloud puts all of it on your own hardware, including the GPU that does the transcribing. ## InterMIND We build for exactly the case the lists skip, so here is our side of the same four questions, stated the same way: - **Messages:** the space is translated for each member as its default behavior — chat and shared notes in **23 languages**, documents in **30**. There is no per-message *Translate* button to press and no add-on to hold; a member who reads Polish reads the channel in Polish. The numbers differ per pipeline on purpose — [there is no single honest answer](https://intermind.com/blog/how-many-languages-do-you-support). - **Meetings:** every participant picks their language on joining and **hears every speaker in it, simultaneously**, in the speaker's own voice — no English anchor, no per-meeting pair, no per-listener license. **Participants pay nothing and need no account**; guests join by link, the host's plan covers the room. ([Why participation is free](https://intermind.com/blog/free-for-participants).) - **Afterwards:** the meeting persists as a channel. Its chat history is readable in each member's language, signed-in members receive the recap in their own language, and documents live in the same space. We audited the whole axis: [how much of your meeting still exists a week later](https://intermind.com/blog/the-meeting-a-week-later). - **Where it lives:** **EU at every runtime hop** — voice and chat translation on our own engine on dedicated servers in France, meeting orchestration in Paris, the database in Frankfurt, EU-resident storage; the recap runs on the AI gateway the organization selects, in an EU region (Azure OpenAI EU Data Zone by default), with zero data retention; document translation goes through one named EU sub-processor (DeepL). The runtime map, vendor by vendor: [where one InterMIND meeting actually runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs). And because "our translation is great" is exactly the claim you shouldn't take from any vendor, quality is published monthly, per language pair, on real traffic: [/benchmark](https://intermind.com/benchmark). --- ## The comparison, in one table | | Messages in each member's language | Meetings: everyone hears their own language? | Who pays for translation | History a month later | Where it can live | | -------------------- | -------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- | ----------------------------------------------------------------------- | | **Microsoft Teams** | On request or auto-translate on view, 100+ languages; not stated as saved | Interpreter agent, 10 languages, per licensed listener, 20 h/month; captions 31 languages behind organizer Premium/Copilot | Organizer and each listener (Copilot) for voice; chat translation names no license | Original language of each message; captions not saved, recordings original audio | Microsoft region of the tenant; country residency for new tenants only | | **Slack** | On request, visible only to you; Business+ and Enterprise+ | Not listed for huddles | Business+ plan | Original text; Free plan keeps 90 days | Business+ data residency: Frankfurt, Paris, Stockholm, Zurich, London | | **Google Workspace** | Auto, in-line, 120+ languages; Gemini or AI Meetings & Messaging add-on | Meet: English ↔ 5, one pair per meeting, 90-min beta | Gemini add-on per user | Original text per retention policy; no translated audio saved | US or Europe data regions on Business Standard+ editions | | **Zoom Workplace** | On request, 38 languages, message replaced on view; Advanced Chat Encryption must be off | Voice translator, 5 languages, add-on, desktop; captions 36 languages | Host plan tier or add-on | Original text; translated output not stated to persist | Zoom EU Infrastructure for EU Education and Enterprise accounts | | **Mattermost** | Auto, server-side into each allowed language (beta); target = display language | Not covered by the auto-translation documentation | Enterprise Advanced license + your LibreTranslate or LLM | Translated posts produced on your server per configured language | Self-hosted; single-tenant cloud on request | | **Rocket.Chat** | Auto per room, each user's own language; DeepL / Google / Microsoft / LibreTranslate via admin key | Via integrations (Jitsi, BigBlueButton, Pexip, Meet, Zoom) | Your provider key; Starter free to 50 users | Per the provider you configured, on your server | Self-hosted or dedicated cloud; on-prem / air-gapped tiers | | **Element** | Not documented | Element Call, end-to-end encrypted, original language | — | Original, end-to-end encrypted | Self-hosted (Community free), Enterprise per seat, Sovereign air-gapped | | **Nextcloud Talk** | Via the translate apps on your server | Live transcription on your server + translation via a task provider (GPU/CPU requirements) | Your hardware | On your server | On-premises or a local provider | | **InterMIND** | Yes — 23 languages chat and notes, 30 documents, as the space's default | Yes — every participant hears every speaker in their chosen language, 23 languages | Host's plan only; participants free, no account | Channel history in each member's language; recap to signed-in members in theirs | EU at every runtime hop: France, Paris, Frankfurt | --- ## How to choose (including when not to switch) - **Your team writes and meets in one language.** Stay on Teams — or on whichever item in the list solves the problem you actually have. A multilingual space solves a problem you don't have. - **A Microsoft shop where the multilingual few hold Copilot seats:** Teams' message auto-translation covers the channels for everyone, and the Interpreter agent covers 10 languages for exactly those seats, 20 hours a month, in scheduled meetings. - **Translation on request is enough, and residency in a named EU city matters:** Slack on Business+ documents both, per reader, with the original text stored. - **Your channels should translate themselves and your meetings route through English with one other language:** Google Chat's Translate-for-me with the Gemini add-on plus Meet's English ↔ 5 speech translation, one pair at a time. - **Nothing may leave your own servers, and you have people to run them:** Rocket.Chat (free to 50 users, translation via a provider key you hold), Mattermost Enterprise Advanced (beta auto-translation on your LibreTranslate or LLM), Nextcloud Talk (transcription on your own GPU), or Element if end-to-end encryption outranks translation entirely. - **The space itself is multilingual** — people replying to each other in three languages, guests without your licenses, a team that needs to *reread* last month's decision in their own language, and a compliance officer who wants a jurisdiction they can name: that's the case we built [InterMIND](https://intermind.com/chats) for. ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener in any of 23 languages. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, monthly translation quality on real traffic, with the methodology public. - **[Compare feature-by-feature](https://intermind.com/compare/microsoft-teams)** — InterMIND vs Microsoft Teams, with every competitor cell sourced. --- ## FAQ **What can I use instead of Microsoft Teams?** For a team that shares one language, the usual list holds: Slack, Google Workspace (Chat + Meet), Zoom Workplace, and the self-hosted options Mattermost, Rocket.Chat, Element and Nextcloud Talk. For a team that doesn't, compare the fences instead of the logos: Slack translates messages on request on Business+; Google Chat translates automatically with a Gemini add-on; Zoom translates 38 languages on view; Mattermost and Rocket.Chat translate on your server with your own engine or key; Element and Nextcloud keep everything on-premises; InterMIND translates the whole space — chat, meetings, documents, history — for every member on the host's plan. **What is the best Microsoft Teams alternative for a multilingual team?** It depends on which axis is broken for you. If reading messages in your own language on request is enough, Teams already does that in 100+ languages and Slack does it on Business+. If the *meeting* must reach every participant in their language, the documented options narrow fast: Teams' Interpreter (10 languages, per-listener Copilot license, 20 h/month), Meet's speech translation (English ↔ 5, one pair per meeting), Zoom's Voice translator (5 languages, add-on), or InterMIND (23 languages, every participant, host's plan covers everyone). **Is there a free alternative to Microsoft Teams?** Several, with different meanings of "free". Slack's Free plan keeps 90 days of history and does not include message translation. Rocket.Chat's Starter plan is free for up to 50 users, self-hosted, and includes auto-translate once you supply a provider key. Element's Community edition is free to self-host, without translation. InterMIND is free for participants by design — guests join by link with no account, and the [live demo](https://intermind.com/demo) needs no signup; the host's plan covers the room. **Are there European alternatives to Microsoft Teams?** If "European" means where the data sits: Slack offers Business+ residency in Frankfurt, Paris, Stockholm and Zurich; Google Workspace offers a Europe data region on Business Standard and above; Zoom's EU Infrastructure covers EU Enterprise and Education accounts; Mattermost, Rocket.Chat, Element and Nextcloud run wherever you deploy them. InterMIND runs in the EU at every hop — France, Paris, Frankfurt — as the default for every plan, not a tier. **Does Microsoft Teams translate chat messages?** Yes. Teams translates a chat or channel message on request, or automatically for received messages, in a list of 100+ languages, on desktop and mobile; the article names no license for it and notes an admin can turn the option off. What it doesn't state is that the translated text is saved — the channel keeps each message in the language it was written in. **Which Teams alternatives keep the history in each member's language?** Among the eight above, the vendors' documentation describes translation as something shown to a reader — on request (Teams, Slack, Zoom) or automatically (Google Chat, Rocket.Chat), with Mattermost producing translated posts server-side per configured language in beta. InterMIND is built the other way around: the channel's history, the recap and the documents are read by each member in their own language. The full audit: [the meeting, a week later](https://intermind.com/blog/the-meeting-a-week-later). **What if the tool we want to replace isn't Teams?** The same axes, applied to the other three suites: [Slack alternatives](https://intermind.com/blog/slack-alternatives), [Google Workspace alternatives](https://intermind.com/blog/google-workspace-alternatives) and [Zoom alternatives for multilingual meetings](https://intermind.com/blog/zoom-alternatives). --- *Sources: [Microsoft — Translate a message in Microsoft Teams](https://support.microsoft.com/en-us/teams/chat/translate-a-message-in-microsoft-teams){rel=""nofollow""}, [Microsoft — Use live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Microsoft — Interpreter in Teams meetings and calls](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft Learn — Teams Premium licensing](https://learn.microsoft.com/en-us/microsoftteams/teams-add-on-licensing/licensing-enhance-teams){rel=""nofollow""}, [Microsoft Learn — Location of data in Microsoft Teams](https://learn.microsoft.com/en-us/microsoftteams/location-of-data-in-teams){rel=""nofollow""}, [Slack — Pricing](https://slack.com/pricing){rel=""nofollow""}, [Slack — Guide to AI features in Slack](https://slack.com/help/articles/25076892548883-Guide-to-AI-features-in-Slack){rel=""nofollow""}, [Slack — Data residency for Slack](https://slack.com/help/articles/360035633934-Data-residency-for-Slack){rel=""nofollow""}, [Google Workspace Updates — Translate for me in Google Chat](https://workspaceupdates.googleblog.com/2024/12/translate-for-me-in-google-chat.html){rel=""nofollow""}, [Google Meet — Learn about Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, [Google Workspace — Choose a geographic location for your data](https://knowledge.workspace.google.com/admin/compliance/choose-a-geographic-location-for-your-data){rel=""nofollow""}, [Google Workspace — Data covered by data regions](https://knowledge.workspace.google.com/admin/compliance/data-covered-by-data-regions){rel=""nofollow""}, [Zoom — Translating messages in Chat](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058113){rel=""nofollow""}, [Zoom — Enabling and configuring translated captions](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0059081){rel=""nofollow""}, [Zoom — Using the Voice translator for meetings](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""}, [Zoom — European Union public sector sovereignty controls explainer](https://library.zoom.com/advanced-enterprise-services/public-sector-sovereignty-controls/european-union-public-sector-sovereignty-controls-explainer){rel=""nofollow""}, [Mattermost — Pricing](https://mattermost.com/pricing/){rel=""nofollow""}, [Mattermost — Set up Auto-translation (Beta)](https://docs.mattermost.com/administration-guide/manage/admin/autotranslation.html){rel=""nofollow""}, [Rocket.Chat — Our plans](https://docs.rocket.chat/docs/our-plans){rel=""nofollow""}, [Rocket.Chat — Auto-Translate messages](https://docs.rocket.chat/docs/auto-translate-messages){rel=""nofollow""}, [Element — Pricing](https://element.io/pricing){rel=""nofollow""}, [Nextcloud Talk](https://nextcloud.com/talk/){rel=""nofollow""}, [Nextcloud — Live Transcription and Translation in Nextcloud Talk](https://docs.nextcloud.com/server/stable/admin_manual/ai/app_live_transcription.html){rel=""nofollow""}, [Nextcloud — Local Machine translation 2 (translate2)](https://docs.nextcloud.com/server/31/admin_manual/ai/app_translate2.html){rel=""nofollow""}. Vendors change plans, prices, language lists and beta status over time; check their pages for the current state. All facts checked August 2026.* # Your SOPs Are Translated. Your Meetings About Them Aren't. - **The document is fine, the conversation isn't.** A DMS keeps translated SOPs in sync; CAPA reviews, inspection prep and CMO calls around them run in one language. - **InterMIND is not a DMS and signs nothing.** MasterControl, Veeva or SmartSolve hold the source of truth; InterMIND sits beside them in the meeting room. - **InterMIND keeps the whole meeting in each member's language,** voice, live shared protocol, chat and the transcript bundle for the audit record. Guests join free by link, no account; you pay only for active members. A quality director quoted in a recent [MasterControl analysis](https://www.mastercontrol.com/uk/gxp-lifeline/electronic-document-management-for-multilingual-compliance/){rel=""nofollow""} said 30% of her documentation-management time goes to keeping translated SOPs (Standard Operating Procedures) in sync across sites. The pains MasterControl describes are real and well-known to anyone running multilingual GxP (Good Practice) operations: - Subtle procedural differences emerging between language versions of a controlled document - Asynchronous updates leaving sites operating from outdated guidance - Training competency hard to verify when materials live in different languages - Approval cycles inflating with every additional language reviewer A controlled document management system — MasterControl, Veeva, IQVIA SmartSolve — is built to solve the **document layer**. Version control, approval routing, controlled distribution, audit trail. That part is well-served. But documents do not sit on shelves. They are **discussed.** And the discussion layer carries a second multilingual problem that no DMS (Document Management System) is designed to fix. --- ## Where Multilingual Breaks Down in Regulated Discussions A SOP gets approved in the DMS. Now what happens around it? **Cross-site CAPA (Corrective and Preventive Action) review.** Eight quality leads from five plants across four countries dial in to walk through a deviation. Three of them are operating in their second or third language. The conversation produces the corrective-action wording. **The wording goes into the audit record. In whose language?** **Inspection readiness.** EU sites prep for an FDA visit. The talking-points walkthrough happens in English over Zoom because that is the lingua franca. The operators who will face the inspectors think and respond in Polish, Spanish, Mandarin. Practice in one language, perform in another — a known driver of inconsistency findings. **Vendor and CMO Q\&A.** A SOP change triggers questions from a contract manufacturer. Twenty back-and-forth clarifications happen on a call. Each one modifies how the procedure is read. **The audit trail of those clarifications exists only in someone's notes — in one language.** **SOP rollout training.** A new procedure goes live across plants. The walkthrough happens once, in English, recorded once. Operators in Brazil, Italy, and Vietnam re-watch with auto-subtitles, miss nuance, and ask the same question three times in three local meetings. In every one of these cases, the document is fine. The DMS is doing its job. **The conversation around the document is where the language tax compounds.** --- ## What InterMIND Does in Those Rooms InterMIND is a space for everyday communication in the language each member thinks in — meetings, chat, files and the recap — with translation built into the core, not bolted on. For regulated discussions, four capabilities matter. ### 1. Live Voice Translation in 23 Languages Each participant picks their own translation language at the start of the call. Speech is translated as it is spoken, with tone and intent preserved. Live subtitles run alongside the audio in every language in the room. No interpreters, no separate tools. (On-demand file translation in chat covers a wider 30 — see [the per-surface breakdown](https://intermind.com/blog/how-many-languages-do-you-support).) ### 2. Live Shared Protocol — Per-Viewer Language with Diffs This is the capability that maps directly onto the asynchronous-update pain MasterControl describes — and inverts it. The host shares a meeting protocol typed live during the call. **Every participant sees it in their own language, in real time.** When the host edits a line, the change is translated and pushed to every viewer with a **diff view**: previous wording, new wording, difference highlighted. No participant is reading yesterday's version of the procedure. Language versions of the protocol stay synchronized to the second, not to the next translation cycle. ### 3. Real-Time Translation of Chat and Attachments Every chat message in the meeting is translated for every viewer. Files dropped into the chat — RFP annexes, deviation forms, supplier certificates, PDFs of draft procedures — are translated on demand into the requesting participant's language. Translations are cached per language and re-translated only on the changed paragraphs when the source updates. ### 4. Compliance-Grade Transcript Bundle After the meeting you export one bundle: full transcript with timestamps, speaker tags, source language and target language for every utterance, the final protocol, and all language versions of it. Suitable for the audit record. For the data-protection layer underneath all of this — where the meeting runs, how erasure and retention work, what the sub-processor list says — we ran the codebase through a [full GDPR audit and closed each item against the code](https://intermind.com/blog/gdpr-audit-what-we-closed). --- ## What InterMIND Does Not Do InterMIND is not a document management system. It does not store master SOPs, route controlled-document approvals, manage versioning of controlled documents, or replace your e-signature workflow. DocuSign, Adobe Sign, and PandaDoc own legally binding signatures and signature audit trails. **We do not sign documents.** MasterControl, Veeva, and IQVIA SmartSolve own the controlled-document lifecycle. **We do not manage SOPs.** InterMIND lives in the meeting room next to those systems. The DMS holds the source of truth. We make sure the discussion of that source happens without language loss, and that the discussion itself is captured on the audit record in every language that was in the room. --- ## Walkthrough: A Cross-Site CAPA Review Eight participants — Frankfurt (German), Madrid (Spanish), Wrocław (Polish), Mumbai (English), São Paulo (Portuguese), Shanghai (Mandarin), and two Boston (English) leads. The deviation is on a tablet-coating step at the Wrocław plant. | Step | What Happens | | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Pre-meeting | Each participant logs in and picks their translation language. UI language and translation language can differ — a Spanish speaker can keep an English UI and still receive translation in Spanish. | | Discussion | Each person speaks their native language. Audio is translated to every other language live. Live subtitles run in parallel. | | Live protocol | The host (Boston) types the proposed CAPA wording into the shared protocol pane. Every participant sees it in their own language as it is typed. The Wrocław lead suggests an edit; the host accepts; every participant sees the diff in their language. | | Attachments | The host drops the deviation report PDF into chat. Each participant requests the translation in their language; results are cached. | | Close | Transcript bundle exported: original-language audio, per-speaker transcript, translated transcripts, final protocol, and all language versions of the protocol. | The CAPA decision goes into the DMS. The discussion that produced it is on the audit record, in every language that was in the room. --- ## Where to Start InterMIND's Basic plan is free forever — no credit card required. The fastest way to see whether the fit is real for your team is to walk through your own scenario against ours. → [See use cases](https://intermind.com/use-case) — The Mind.com Team **Your DMS keeps the document straight. We keep the conversation straight.** --- *Sources: [MasterControl — Multi-language documentation challenges in European life sciences manufacturing](https://www.mastercontrol.com/uk/gxp-lifeline/electronic-document-management-for-multilingual-compliance/){rel=""nofollow""} — the 30% figure and the four documentation pitfalls cited above; checked August 2026.* # Multilingual customer support without hiring agents or writing code - **Three steps, no hires, no code.** A booking page in your calendar, one reusable InterMIND link in its description, each side picks their own language. - **It is the spoken call, not the ticket queue.** Ticketing, help-center localization and email stay with Zendesk or Intercom; every stranger with the link waits for your approval. - **InterMIND keeps the whole conversation in each side's language,** voice and chat, the recap in your inbox and your CRM. Customers join free by link, no account; you pay only for active members. Most advice about multilingual customer support is advice about **staffing and text**: hire agents per language, localize your help center, translate incoming tickets. That is a real approach with a real cost, and the tooling for it is mature. This page describes a different, much smaller setup — one that a single support person can put in place in an afternoon, with no new hires, no translation software to administer, and no code. The customer books a slot, joins from a link, and **speaks their own language out loud**. You speak yours. Afterwards the summary arrives in your inbox and, if you want, in your CRM. The whole recipe is three steps, and the only tools involved are your existing calendar and one meeting link. --- ## The setup, in three steps ### Step 1 — Make a booking page in the calendar you already use Google Calendar's appointment scheduling produces a public booking page: customers pick a slot, it lands on your calendar. This is the standard feature in Google Workspace; nothing custom is involved. Use whatever your team already runs on. The recipe does not care which scheduler it is — its only requirement is that the booking page has a **description field** you can put a link in. ### Step 2 — Put one reusable InterMIND link in the booking page description Create one ad-hoc meeting in InterMIND and copy its link. It looks like `intermind.com/abc-def-ghi`. Paste that link into the booking page description, so it travels into every confirmation and calendar invite your scheduler sends. **One link is enough, permanently.** When a call ends, the meeting link keeps working: the next visitor who opens it starts a fresh session on the same URL. You are not generating a link per customer, and you are not maintaining a list of them. Two consequences of that design are worth knowing before you publish the link anywhere: - **A stranger with the link cannot walk in.** Every anonymous visitor lands in a waiting room and joins only after you approve them — there is no setting anywhere in InterMIND that turns that approval off. An unanswered knock is denied automatically after 5 minutes. This is what makes a *publishable* support link safe. - **Ad-hoc rooms don't accumulate history.** Chat messages from a session are deleted when it ends, and the recap covers the most recent session only. For customer support that is usually the point — one customer's call leaves nothing behind for the next one to find. ### Step 3 — Let each side pick their own language When the customer opens the link, they enter a name and pick their language. You pick yours. From that point each participant hears the others in their own language, and chat messages are translated per participant as well. Voice and chat translation cover the same **23 languages**: English, Russian, Spanish, French, German, Italian, Portuguese, Polish, Dutch, Czech, Hungarian, Danish, Finnish, Icelandic, Norwegian, Romanian, Swedish, Ukrainian, Japanese, Korean, Turkish, Chinese (Simplified) and Hindi. Nobody installs anything. The customer joins in a browser, with no account to create — and pays nothing: only the host's side of the room has a plan. --- ## What happens after the call, without anyone writing it up When the session ends, InterMIND generates a recap — a title, an overview, key takeaways, sectioned points with timestamps, action items, open questions and topics — and emails it to the registered participants. If the conversation produced nothing summarizable, no email is sent at all. Two details matter for a support workflow: - **The email is a single snapshot in the meeting's source language.** Per-language text lives on the recap page it links to: open `/r/...` and the summary is served in *your* language, translated on our own EU-resident engine and cached. The recap page requires sign-in — the link alone grants nothing, membership in the meeting is the boundary. - **The recap can be BCC'd to your CRM.** Support and sales CRMs accept mail at a per-account inbound address; adding yours to the recap means the call write-up lands on the customer's record without anyone copying it there. Up to 10 addresses can live in your address book, and an address only becomes active after you click a confirmation link *inside that CRM inbox* — a delivery test, because some CRMs accept mail over SMTP and then silently discard senders that aren't allowlisted. Participants stay in the To field deliberately: the participant addresses are what CRMs match against to file the message on the right record. --- ## What this setup is and isn't It is worth being precise about where this recipe fits, because it does not replace a support desk. **What it does:** turn a scheduled conversation into one where language is not a constraint, and produce a written record of it automatically, in each reader's language. **What it does not do:** ticketing, queueing, help-center localization, or asynchronous email support. Those remain the domain of a support platform. The vendors in that space document their multilingual layer explicitly: - **Zendesk** documents multiple-language support via dynamic content — *"You can create and edit all your language variants directly in Zendesk or you can export all your dynamic content and send it off to a translation agency"* — and publishes language tables per product (counted from those tables in August 2026: 52 locales for the agent interface, 38 for the help center, 32 for live conversation translation). Its conversation-translation documentation enumerates the channels it works in: *"Zendesk messaging, Live chat, Social channels, Sunshine Conversations channels, Email, web form, or API channels."* Voice is not among the channels listed there. - **Intercom** lists supported languages for Messenger localization (45 entries counted from its table, August 2026) and documents Fin AI Agent's AI Answers across 64 listed entries covering 47 base languages, with the stated fallback that *"when Fin can't find relevant support content in the customer's language, it will translate existing support content in your chosen fallback language."* Those layers are about **text**: tickets, articles, chat. The recipe above is about the **spoken conversation** — the moment when a customer would otherwise have to explain a problem in a language they are not fluent in, or wait for an agent who speaks theirs. The two compose. A team can run its help center and ticket queue exactly as it does today, and add a booking link for the calls where writing it out in a second language is the actual bottleneck. --- ## Where the limits are The honest constraints of the setup, so you can size it before you adopt it: | Plan | Voice translation | Chat translation | Participants | | ---------- | ------------------- | ---------------------- | ------------ | | Basic | 120 min / 30 days | 10,000 words / 30 days | 50 | | Pro | 1,500 min / 30 days | Unlimited | 100 | | Business | Unlimited | Unlimited | 300 | | Enterprise | Unlimited | Unlimited | 1,500 | Two notes that decide whether Basic is enough: the window is a **rolling 30 days**, not a calendar month, and the voice-minute pool belongs to the **host's account** — a three-person support team on one plan shares those 120 minutes rather than getting 120 each. A support desk running several calls a week outgrows Basic quickly; Pro's 1,500 minutes is the next wall. --- ## FAQ **How do I offer multilingual customer support without hiring multilingual agents?** Hold the conversation in a room that translates it. The customer books a slot, joins a meeting link from the booking page, and each side picks their own language — voice and chat are translated per participant across 23 languages. The staffing question changes from "who on my team speaks Portuguese" to "who is free at 3pm". **What are the best AI tools for multilingual customer service?** It depends which layer you mean, and they are different products. For tickets, help-center articles and chat, the established support platforms document their own multilingual layers (Zendesk's dynamic content and conversation translation, Intercom's Messenger localization and Fin AI Agent). For the spoken conversation — a live call where the customer talks in their language and you answer in yours — that is what a translating meeting room like InterMIND does. Most teams need the first; teams whose customers get stuck explaining problems in a second language need the second as well. **Do my customers need an account or an app to join?** No. A customer opens the link in a browser, types a name, picks a language and knocks. There is no account to create, nothing to install, and nothing for them to pay — the host's plan covers the room. **Is it safe to publish a permanent meeting link on a public booking page?** Yes, because the link is not the door. Anyone arriving anonymously waits for the host to approve them, and no configuration turns that approval off; an unanswered request expires after 5 minutes. Ad-hoc rooms also delete their chat when a session ends, so nothing from one customer's call is visible to the next. **Does the customer get the summary in their own language?** The emailed recap is one snapshot in the meeting's source language. The recap page it links to serves the summary in the reader's own language — but that page requires sign-in and meeting membership, so it is the practical path for your team rather than for a one-off customer. **How do the call notes get into our CRM?** By email, without an integration: add your CRM's inbound address to the recap BCC list. The write-up then arrives on the customer's record automatically. The address has to be confirmed from inside that CRM inbox once before it goes live. --- ## Try it - **[Start a meeting and copy its link](https://intermind.com/chats)** — the same link you would paste into a booking page description. - **[Try the live demo](https://intermind.com/demo)** — hear the translation before you set anything up. - **[See how translation quality is measured](https://intermind.com/benchmark)** — the FLORES-200 results, per language pair. The same three steps, applied to sales: the [discovery call](https://intermind.com/blog/discovery-call) with international leads, the [book-a-demo flow](https://intermind.com/blog/book-a-demo) without an SDR stack, and the [sales follow-up email](https://intermind.com/blog/sales-follow-up-email) that starts from the generated write-up. --- *Sources: vendor documentation — Zendesk [multiple language support with dynamic content](https://support.zendesk.com/hc/en-us/articles/4408882999066-Providing-multiple-language-support-with-dynamic-content){rel=""nofollow""}, [language support by product](https://support.zendesk.com/hc/en-us/articles/4408821324826-Zendesk-language-support-by-product){rel=""nofollow""}, [understanding conversation translation](https://support.zendesk.com/hc/en-us/articles/4408832500506-Understanding-conversation-translation){rel=""nofollow""}; Intercom [localize the Messenger](https://www.intercom.com/help/en/articles/180-localize-the-messenger-to-work-with-multiple-languages){rel=""nofollow""}, [Fin AI Agent multilingual support](https://www.intercom.com/help/en/articles/8322387-set-up-fin-ai-agent-s-multilingual-support){rel=""nofollow""}. Language counts were tallied from the vendors' own tables, which enumerate rather than state a total. Checked August 2026.* # One-on-one meeting template: structure, cadence, and a running history both of you can read (2026) - **The report's meeting, four items, same link every week.** Their items first, follow-ups, feedback each way, next steps with names and dates. - **The history is what templates skip.** Teams notes and a Slack canvas keep one document per pair, hand-typed, in one language. - **InterMIND keeps the whole conversation in each member's language,** a channel for the pair with note, chat and every recap, next to Teams or Slack rather than instead of them. Guests join free by link, no account; you pay only for active members. A one-on-one is a recurring, private meeting between a manager and one person who reports to them. It is the one meeting on the calendar that belongs to the report: their blockers, their growth, their questions first; the manager's items second. It is not a status update — status lives in the channel — and it is not a performance review, although a year of good one-on-ones is what makes the review contain no surprises. This guide gives you the template, the monthly variant, the way to prepare and run it, the cadence, the first one-on-one with a new report, fifteen questions by situation — and then the part templates skip: where the history of your one-on-ones lives, so that "didn't we discuss this in March?" has an answer both of you can open. ## What a one-on-one is for Three things, in this order: 1. **Unblocking.** What is in the report's way this week that only the manager can move — a decision, a priority call, a conversation with someone else. 2. **Growth.** Where the report wants to be in a year, and what this quarter does about it. This is the item that disappears first when the meeting becomes a status update, and the one people quit over when it has been missing for a year. 3. **Feedback both ways.** One specific piece each. Small, frequent and two-directional beats one annual document. What it is not for: reviewing the task list (the channel does that), announcements (the team meeting does that), and the manager's own update (two minutes, at the end, if at all). ## The 30-minute template > **\[Report] / \[Manager] — one-on-one**:br**Cadence:** weekly, \[day, time] · **Link:** \[the same meeting link every week] :br**Pre-read:** last session's recap and its open items > > **1. Your items** — report — 12 min :br > \[Added to the agenda the day before; the report decides the order.] > > **2. Follow-ups from last time** — both — 5 min :br > \[Each open item: done, not done and why, or dropped on purpose.] > > **3. One piece of feedback each way** — both — 8 min :br > \[Specific: a situation, what happened, what to keep or change.] > > **4. Next steps, written down** — both — 5 min :br > \[Two or three items with a name and a date. The manager's items are here too.] ## The 45-minute monthly variant Once a month, swap item 3 for a longer growth conversation and give the meeting fifteen more minutes: > **1. Your items** — report — 10 min :br**2. Follow-ups from last time** — both — 5 min :br**3. Growth: where you want to be in a year, and what this quarter does about it** — report leads — 20 min :br**4. Feedback each way** — both — 5 min :br**5. Next steps, written down** — both — 5 min The growth item has a fixed question behind it — "what would you like to be doing more of, and what is in the way?" — and a fixed output: one development step per quarter with a date, written in the report's words. ## How to prepare and run it **The day before, the report adds their items where both of you already talk.** One message in your shared one-on-one channel: "Thursday — 1. the review process, 2. the conference, 3. a question about the roadmap." The manager adds theirs below. Items written the day before get thought about; items raised in the first minute get reacted to. **In the meeting, the manager's job is to listen and to write outcomes aloud.** Open with the report's first item, not with "how are you" that expects "fine". Ask the second question — "what makes you say that?" — more than you state anything. When something is agreed, say it as a sentence: "so we're recording — you draft the proposal, I get you fifteen minutes with Dana before the 20th." That sentence is the record; writing it down during the meeting is what makes the next one start from facts. **After the meeting, the next steps go where both of you will see them before the next session** — not into the manager's private notes, and not into a document only the manager can edit. A one-on-one whose history lives in one head is a one-on-one that restarts from zero every time a manager changes. ## Cadence: how often, how long, and the rule about cancelling | Situation | Cadence | Length | | ------------------------------------------- | ------------------------------------------ | ------ | | New report, first 90 days | Weekly | 30 min | | Remote or in another time zone | Weekly | 30 min | | Established, co-located, work is going well | Every two weeks | 45 min | | Monthly growth conversation | Once a month, replaces one regular session | 45 min | The rule: a one-on-one is rescheduled, never cancelled. A cancelled one-on-one tells the report exactly where they stand in the manager's week, and the message is heard louder than anything said in the meeting. Keep the same link every time: the history of the meeting then has one address. How the one-on-one fits next to the stand-up, the weekly and the rest of a team's recurring meetings, with a template sized for 5 to 50 people, is in [meeting cadence](https://intermind.com/blog/meeting-cadence). ## The first one-on-one with a new report The first session is the only one with a fixed agenda set by the manager, because the report does not yet know what to bring: > **1. How you like to work** — report — 10 min: hours, focus time, how you prefer to get feedback, what a good week looks like. :br**2. What the team needs from this role in the first 90 days** — manager — 10 min: in writing, before the meeting. :br**3. How we will run these: cadence, where items go, where the notes live** — both — 5 min. :br**4. Your first three questions** — report — 5 min. From the second session on, the template above applies and the report owns item 1. ## Fifteen questions, by situation **When the report's list is short** - What took more of your time this week than it should have? - What are you putting off, and what would make it easier to start? - Who on the team would you like to work with more? **When something is stuck** - What decision are you waiting on, and from whom? - If you could change one thing about how we work, what would it be? - What do you need from me this week that you haven't asked for? **Growth** - What would you like to be doing more of a year from now? - What is one skill you'd like to be known for? - Which piece of recent work are you proudest of, and why? **Feedback** - What is one thing I could do differently that would help you? - When did I last get in your way? - Is there feedback you have been meaning to give someone and haven't? **Well-being** - How sustainable is your current pace? - What is one thing outside work that is taking energy right now, if you want to share it? - Is there anything you'd like me to know that we haven't talked about? Three per meeting is plenty. The point is the second question, not the first. ## Where the running history lives in the tools you already use A one-on-one is the meeting with the longest memory: the item from March matters in September. Where the notes live is therefore a design decision, not an afterthought. Documented behaviour only, from the vendors' own pages, checked October 2026: | Tool | What it offers for one-on-ones | Where it stops | | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | Collaborative notes — a Loop component with agenda, notes and tasks assigned by tagging people — are available in Teams **group** chats on desktop and web; meeting notes can also be started from the meeting's Details or the Notes control | The chat-notes page documents group chats, not one-on-one chats; external guests cannot edit notes; the notes are one document in one language | | **Slack** | A one-on-one template as a canvas, meant to live in a private channel per manager–report pair, with sections for development resources, goals and meeting-prep reminders | The canvas holds what someone types into it; what was said in the call is not in it unless a person writes it | Both are the right idea — one place per pair, kept over time — with the same two limits: the record is written by hand, and it exists in one language. ## A running history both of you can read InterMIND is a communication space where a meeting lives in a channel, so a one-on-one is a channel with two members and one permanent meeting link. The report posts the items the day before as a note; the manager adds theirs; during the call either of you puts the note on both screens with *Share to conference*, edits it live, and the other reads it in their own language — as they read the channel's chat. When the session ends, the recap is written from the meeting itself: a summary, the points marked agreed, open or disputed, the next steps with owners, each line keeping its timestamp — editable by either of you, with every edit keeping author and revision history. The channel keeps the recap of every past session, so the question from March is one click away in September, and the recap is members-only: forwarding the link grants nobody access. In an organization with team status pages on, the open items of earlier sessions are judged when the next recap is written — reported finished, marked done; discussed but not finished, marked not done with the reason in the words of the meeting; not brought up, left open — with the verdicts on the organization's status page rather than in the recap, and at the start of the next session Mia names the open items and their owners. Team status pages are a preview feature: an organization's admin switches them on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). One more property, said once: the manager and the report each speak and read in their own language — the chat, the shared note and the record are translated per reader, not written in whichever language the two of you compromise on. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing); the report installs nothing and pays nothing. When the one-on-one runs as a meeting by link instead — with a contractor who is not in your organization — the other person joins by link, without an account and at no cost, and hears the session live in their own language. There is no record for a guest afterwards — the account is free, and it is what makes the record reachable. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. ## FAQ **What is a one-on-one meeting?** A recurring private meeting between a manager and one of their reports, owned by the report: their blockers, growth and questions come first, the manager's items second. It is not a status update and not a performance review; it is the place where the small conversations happen that make the review contain no surprises. Other names: 1:1, one-to-one, check-in. **How do you conduct a one-on-one meeting?** Let the report set the first item and the order; ask more than you state; when something is agreed, say it aloud as a sentence with a name and a date; end with next steps written where both of you will see them before the next session. Keep it to the booking — 30 minutes weekly, 45 for the monthly growth conversation — and reschedule rather than cancel. **How do I prepare for a one-on-one with my manager?** Add your items to the shared agenda the day before, in the order you want them; read the last session's notes and update the open items — done, not done and why; bring one question about priorities and one piece of feedback for your manager. If the meeting has no shared agenda, propose one: the template above works from either side. **What should be on a one-on-one meeting agenda?** Four items: the report's items (the largest block), follow-ups from last time, one piece of feedback each way, and next steps written down with names and dates. Once a month, a twenty-minute growth conversation replaces the feedback item and the meeting runs 45 minutes. **How often should one-on-ones be?** Weekly for a new report in the first 90 days and for anyone remote or in another time zone; every two weeks for an established, co-located report whose work is going well; plus a monthly growth session. Rescheduled when needed, never cancelled. **How should I structure my one-on-one meetings?** Same link, same slot, same four items every time, with the report's items first. The structure is what lets the content change: when the shape is predictable, both people prepare, and the history of the meeting becomes readable because every session looks the same. **Is a one-on-one the same as a performance review?** No. A review is a periodic, formal assessment, usually tied to compensation and documented by HR. A one-on-one is informal, frequent and owned by the report. The relationship between them is that a year of honest one-on-ones is what makes a review uneventful. --- *Sources: [Microsoft — Use collaborative notes in Microsoft Teams chats](https://support.microsoft.com/en-us/teams/chat/use-collaborative-notes-in-microsoft-teams-chats){rel=""nofollow""}; [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Slack — One-on-one meeting template](https://slack.com/templates/1-1-coaching){rel=""nofollow""}. checked October 2026.* # Otter.ai alternatives: the 9 best in 2026 (and when to switch) - **Switch for minutes or languages.** Otter caps minutes and transcribes in six languages; Fireflies and Fathom lift the caps, Notta and MeetGeek add languages. - **No notetaker fixes a meeting the room could not follow.** Every tool here, Otter included, assumes the meeting happened in one language and transcribes it. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes and documents translated as the meeting happens, with the summary as a by-product. Guests join free by link, no account; you pay only for active members. Otter.ai made "AI meeting notes" a category, and for English-first teams it's still a fine default. But the two complaints that send people searching for an Otter alternative in 2026 are consistent: **the minute caps** (300/month free, 1,200 on Pro — heavy meeting loads burn through both) and **the language list** — Otter transcribes in six languages (English, Spanish, French, German, Japanese, Chinese) in a market where competitors claim 30, 58, or 100+. Below are the 9 alternatives worth shortlisting, with pricing and limits verified in July 2026. Full disclosure: **we build one of them** ([InterMIND](https://intermind.com){rel=""nofollow""}), and it's the right pick only for one specific case — meetings that happen in more than one language, live. For everything else we'll point you to the competitor that fits. > Deciding between the two biggest names? We wrote the head-to-head: [Otter vs Fireflies, honestly compared](https://intermind.com/blog/otter-vs-fireflies). And the detailed 1-on-1 against us: [InterMIND vs Otter](https://intermind.com/compare/otter). --- ## The verdict table | Tool | Best for | Free plan | Paid from\* | Languages | | ---------------------------------------------------- | --------------------------------------- | --------------------------- | ------------------------------- | ------------------ | | [InterMIND](https://intermind.com/#tool-1) | Live-translated multilingual meetings | Yes (Basic) | per active member, 14-day trial | 23 voice / 30 docs | | [Fireflies.ai](https://intermind.com/#tool-2) | Unlimited transcription, 100+ languages | Unlimited (400 min storage) | $10/seat/mo | 100+ | | [Fathom](https://intermind.com/#tool-3) | Free unlimited recording | Unlimited | \~$16/mo | 38 | | [tl;dv](https://intermind.com/#tool-4) | Sales clips and coaching | Unlimited recording | \~$18/seat/mo | 30+ | | [Notta](https://intermind.com/#tool-5) | Non-English transcription + translation | 120 min/mo | \~$9/mo | 58 | | [MeetGeek](https://intermind.com/#tool-6) | Whole-team auto-capture | 3 h/mo | $9.99/user/mo | 100+ | | [Read AI](https://intermind.com/#tool-7) | Engagement analytics | 5 meetings/mo | $15/user/mo | 16+ | | [Krisp](https://intermind.com/#tool-8) | Noisy calls, no bots | Trial | \~$8/user/mo | 16+ | | [Built-in notetakers](https://intermind.com/#tool-9) | One-platform teams | Included | with suite plan | varies | \*Lowest advertised per-user price on annual billing, July 2026; month-to-month typically runs 1.5–2× higher. --- ## How to choose in 30 seconds - **You hit Otter's minute caps** → [Fireflies](https://intermind.com/#tool-2) (unlimited transcription) or [Fathom](https://intermind.com/#tool-3) (unlimited and free). - **Your recordings aren't in English** → [Notta](https://intermind.com/#tool-5) or [MeetGeek](https://intermind.com/#tool-6) — both transcribe far beyond Otter's six languages. - **Your *meetings* aren't in one language** — the room can't follow each other live → no notetaker fixes that, including Otter. You need [live translation](https://intermind.com/#tool-1). - **Otter is fine but pricey at team scale** → check [your platform's built-in notetaker](https://intermind.com/#tool-9) before paying anyone. --- ## The 9 best Otter.ai alternatives []{#tool-1} ### 1. InterMIND — when your meetings aren't in one language Otter and every tool below share one assumption: the meeting happens in a language everyone understands, and the AI writes it down. InterMIND is for when that assumption breaks. Each participant picks their language on joining and *hears* every speaker in it — in the speaker's own voice, as it is said — while the chat, shared notes, and dropped-in documents translate per viewer too. The post-meeting summary is a by-product, not the product. - **Price:** free Basic plan; Pro and Business billed per active member (the members active in the previous 28 days), 14-day trial — [pricing](https://intermind.com/pricing). - **Languages:** 23 live (voice, chat, notes), 30 for documents. [Why we count it that way.](https://intermind.com/blog/how-many-languages-do-you-support) - **Limits:** voice minutes and chat words metered on a rolling 30-day window, shared across the team. - **Best for:** international teams, cross-border sales, any recurring call where the room speaks more than one language. - **Honest caveat:** single-language meetings don't need it — pick a notetaker below instead. Quality is the thing to verify, not trust: per-language-pair scores are [published monthly](https://intermind.com/benchmark), and [the demo](https://intermind.com/demo) plays the production pipeline on a real meeting, live — no signup needed. []{#tool-2} ### 2. Fireflies.ai — the obvious first candidate The default Otter rival, and on the two pain points that push people off Otter it wins outright: transcription is **unlimited on every plan** (storage is what's capped) and it covers **100+ languages** with auto-detection. - **Price:** free (unlimited transcription, 400 min storage/team); Pro $10/seat/mo annual ($18 monthly), 8,000 min storage; Business $19/$29 unlimited; Enterprise $39 annual. - **Languages:** 100+, with multi-language detection on Business+. - **Best for:** teams that transcribe a lot, in many languages, and want CRM/automation hooks. - **Vs Otter:** no minute anxiety and vastly more languages; the live-transcript editing workspace is weaker. Full head-to-head: [Otter vs Fireflies](https://intermind.com/blog/otter-vs-fireflies). []{#tool-3} ### 3. Fathom — the generous free plan Unlimited free recordings, transcription, and instant summaries. If Otter's caps are the whole problem and your meetings are mostly English, the move takes an afternoon. In September 2026, the AI email client Superhuman acquired Fathom. Per TechCrunch, the free plan had already driven Fathom past 400,000 monthly active users, with more than 1 million people having used it to record a meeting. - **Price:** free unlimited; Premium $16/mo annual; Team $15, Business $25/user/mo annual (2-seat minimum). - **Languages:** 38. - **Best for:** individuals and small teams that want free and low-friction. - **Vs Otter:** more free value; fewer team knowledge-base features. []{#tool-4} ### 4. tl;dv — clips and coaching on a budget Free unlimited recording and transcription, with the paid tiers aimed at sales teams: clips, multi-meeting AI reports, CRM sync, coaching scorecards. - **Price:** free (limited AI summaries); Pro \~$18/seat/mo annual; Business \~$59/seat/mo annual. - **Languages:** 30+. - **Best for:** sales teams that want Gong-lite workflows without Gong pricing. - **Vs Otter:** better sales tooling and languages; the AI layer is what you pay for. []{#tool-5} ### 5. Notta — the language workhorse Notta's pitch is the transcript in another language: 58 transcription languages, translated transcripts on paid plans, bilingual and real-time translation views as add-ons. For *recorded* non-English audio, this is the specialist. - **Price:** free 120 min/mo; Pro from \~$9/mo annual, 1,800 min/mo; Business \~$16.67/seat/mo annual; real-time translation add-on from \~$6/mo. - **Languages:** 58. - **Best for:** individuals transcribing and translating across European and Asian languages. - **Vs Otter:** 58 languages vs 6 — but still after-the-fact; the live meeting stays untranslated. []{#tool-6} ### 6. MeetGeek — auto-capture for teams Joins everything on the calendar, transcribes in 100+ languages, and builds a searchable library with summaries and automations — capture-by-default for a whole team. - **Price:** free 3 h/mo; Pro $9.99/user/mo (20 h/mo); Business $17/user/mo (unlimited). - **Languages:** 100+, auto-detected. - **Best for:** managers who want every call captured without anyone pressing record. - **Vs Otter:** more languages, cheaper entry, set-and-forget; its transcript workspace is post-call focused rather than live. []{#tool-7} ### 7. Read AI — metrics, not just minutes Transcripts plus meeting *analytics*: talk time, engagement, sentiment, and reports that follow up in email and Slack. - **Price:** free 5 meetings/mo (1 h cap); Pro $15/user/mo annual; Enterprise $22.50; Enterprise+ $29.75/user/mo annual. - **Languages:** 16+. - **Best for:** leaders optimizing meeting culture, not just recall. - **Vs Otter:** adds analytics Otter lacks; higher per-seat price for full features. []{#tool-8} ### 8. Krisp — bot-free and noise-proof On-device audio processing: noise cancellation with an AI notetaker on top. No bot joins the call, and it works across any calling app — including phone bridges the bot-based tools can't touch. - **Price:** Core \~$8/user/mo annual (unlimited AI notes); Advanced \~$15/user/mo annual; 7-day trial. - **Languages:** 16+. - **Best for:** noisy environments, call centers, bot-averse counterparties. - **Vs Otter:** cleaner audio in, no bot; lighter search and collaboration features. []{#tool-9} ### 9. Zoom, Teams, and Meet's own notetakers Zoom AI Companion, Copilot in Teams, and Gemini in Meet all generate meeting summaries on paid tiers now — before paying a third party, check whether "good enough" is already in your suite. Where each stops (especially on translation) is documented in our platform guides: [Zoom](https://intermind.com/blog/zoom-live-translation), [Teams](https://intermind.com/blog/teams-live-translation), [Google Meet](https://intermind.com/blog/google-meet-live-translation). - **Price:** bundled with the suite. - **Best for:** teams that live in one platform. - **Vs Otter:** zero setup and zero extra cost; weaker cross-meeting search and no cross-platform story. --- ## The distinction the listicles blur Every Otter alternative above competes on the same axis: **recall** — how well the meeting gets written down. Price per seat, minutes per month, languages per transcript. There's a second axis the category quietly ignores: **comprehension** — whether everyone in the room could follow the meeting *as it happened*. Otter's six languages vs Fireflies' hundred doesn't matter to the participant who couldn't understand the discussion live; a transcript of a meeting you couldn't follow is [documentation of the problem, not a solution to it](https://intermind.com/blog/why-translation-quality-marketing-is-broken). If that's your actual situation, the fix isn't a better notetaker — it's [simultaneous interpretation built into the meeting](https://intermind.com/features/simultaneous-interpretation), which is the job InterMIND does and the reason it sits oddly at the top of this list. --- ## FAQ **What's the best free Otter alternative?** Fathom — unlimited free recordings, transcription, and summaries. tl;dv also records and transcribes free but limits AI summaries tightly. **What's the best Otter alternative for other languages?** For transcribing recordings: Notta (58 languages) or MeetGeek/Fireflies (100+ claimed). For *live* meetings in multiple languages: [InterMIND](https://intermind.com/compare/otter) — it translates the meeting while it happens instead of transcribing it afterward. **Is Fireflies better than Otter?** Different trade: Fireflies gives unlimited transcription and 100+ languages; Otter gives a live transcript you can highlight, comment on, and edit during the call, but meters your minutes and caps languages at six. The full comparison: [Otter vs Fireflies](https://intermind.com/blog/otter-vs-fireflies). **Does Otter.ai translate?** No. Otter transcribes in six languages, one language per conversation. It doesn't translate meetings live or translate transcripts between languages. **Can I just use Zoom's or Teams' built-in AI notes?** Often yes — on paid suite tiers they're decent and free-ish. You give up cross-meeting search, CRM sync, and multi-platform capture. --- ## Compare InterMIND head-to-head Prefer a direct one-on-one to the listicle above? These pages line InterMIND up feature-by-feature against the tools people cross-shop most: | Comparison | The trade-off | | ----------------------------------------------------------------------------- | --------------------------------------------------------- | | [InterMIND vs Otter](https://intermind.com/compare/otter) | Live translation vs six-language transcription | | [InterMIND vs Fireflies](https://intermind.com/compare/fireflies) | Live translation vs unlimited 100+-language transcription | | [InterMIND vs Zoom](https://intermind.com/compare/zoom) | Built-in interpretation vs AI Companion summaries | | [InterMIND vs Microsoft Teams](https://intermind.com/compare/microsoft-teams) | Built-in interpretation vs Copilot summaries | Or skip the shortlist and [start a multilingual meeting](https://intermind.com/chats) to hear it on your own call. --- ## Test the axis that actually differentiates If languages are why you're leaving Otter, don't take any vendor's language count on faith — including ours: - **[Run the live demo](https://intermind.com/demo)** — InterMIND's production pipeline, your voice, any of 23 languages. - **[Read the benchmark](https://intermind.com/benchmark)** — per-pair quality published monthly, full distribution. - **[InterMIND vs Otter, feature by feature](https://intermind.com/compare/otter)** — the detailed 1-on-1. — The Mind.com Team --- *Sources: vendor pricing pages ([Otter.ai](https://otter.ai/pricing){rel=""nofollow""}, [Fireflies.ai](https://fireflies.ai/pricing){rel=""nofollow""}, [Fathom](https://fathom.ai/pricing){rel=""nofollow""}, [tl;dv](https://tldv.io/app/pricing/){rel=""nofollow""}, [Notta](https://www.notta.ai/en/pricing){rel=""nofollow""}, [MeetGeek](https://meetgeek.ai/pricing){rel=""nofollow""}, [Read AI](https://www.read.ai/pricing){rel=""nofollow""}, [Krisp](https://krisp.ai/pricing/){rel=""nofollow""}), checked July 2026; [TechCrunch — Superhuman acquires Fathom](https://techcrunch.com/2026/09/14/superhuman-acquires-yc-backed-notetaker-fathom-as-productivity-platforms-push-for-agentic-work/){rel=""nofollow""}, checked September 2026. Prices are annual-billing rates unless noted and may change.* # Otter vs Fireflies (2026): which AI notetaker fits — and when neither does - **Otter for the workspace, Fireflies for the meter.** Otter has the live transcript you highlight and edit; Fireflies transcribes without limits and covers 100+ languages against Otter's six. - **Neither translates a live meeting.** Both assume everyone understood the discussion and the AI only transcribes; the transcript arrives after the call. - **InterMIND keeps the whole meeting in each member's language,** voice as it is spoken, chat, notes and documents, with notes still generated afterwards. Guests join free by link, no account; you pay only for active members. Otter.ai and Fireflies.ai are the two names everyone shortlists for AI meeting notes, and the comparison is genuinely close — they just meter you differently and speak a different number of languages. Here's the honest breakdown, from a vendor of neither: we build [InterMIND](https://intermind.com){rel=""nofollow""}, a live meeting *translator*, and we'll flag the one scenario where both notetakers lose. Everything else below is a straight comparison you can act on. **The short verdict:** Otter has the better *workspace* — live transcript you can highlight and edit, cleaner collaboration. Fireflies has the better *meter* — unlimited transcription on every plan and 100+ languages against Otter's six. Transcript-centric English teams lean Otter; volume and language breadth lean Fireflies. --- ## Side by side | | Otter.ai | Fireflies.ai | | ----------------------------------- | --------------------------------------- | ----------------------------------------------- | | **Free plan** | 300 min/mo, 30 min/conversation | Unlimited transcription, 400 min *storage*/team | | **Entry paid (annual)** | Pro $8.33/user/mo | Pro $10/seat/mo | | **Mid tier (annual)** | Business $19.99/user/mo | Business $19/seat/mo | | **What's metered** | Transcription minutes (1,200/mo on Pro) | Storage (8,000 min on Pro; unlimited Business+) | | **Meeting length cap** | 90 min (Pro), 4 h (Business) | — | | **Transcription languages** | 6 (EN, ES, FR, DE, JA, ZH) | 100+ with auto-detection | | **Multi-language meetings** | One language per conversation | Multi-language mode on Business+ | | **Live transcript workspace** | Highlight, comment, edit live | Post-call focused | | **Automations/CRM** | Business+ | CRM + automation integrations | | **Live translation of the meeting** | No | No | *Pricing verified on vendor pricing pages, July 2026 ([Otter](https://otter.ai/pricing){rel=""nofollow""}, [Fireflies](https://fireflies.ai/pricing){rel=""nofollow""}); annual-billing rates.* ## Choose Otter if… - Your team **works in the transcript** — highlights mid-call, shared notes, edits. Otter's live workspace is the best reason to pick it. - Meetings are **English-first** (or within its six languages) and predictable in volume, so the minute caps don't bite. - You want the lower entry price and don't need automation pipelines. ## Choose Fireflies if… - You transcribe **heavily or unpredictably** — unlimited transcription removes the meter anxiety entirely. - Your recordings span **languages Otter doesn't have** — 100+ with auto-detection is a different league than six. - You want notes flowing into **CRM and automations** without buying the top tier. ## The scenario where both lose Both tools assume the meeting itself worked — that everyone in the room understood the discussion, and the AI just needs to write it down. When your meetings happen across languages — a German engineer, a Brazilian PM, a Japanese client — that assumption is the problem. A transcript (even Fireflies' 100-language one) is delivered *after the call*, to people who couldn't fully follow it *during* the call. That's a different product category: [live simultaneous interpretation built into the meeting](https://intermind.com/features/simultaneous-interpretation). InterMIND translates the voice as it's spoken — each participant hears every speaker in their own language, in the speaker's own voice — and translates the chat, shared notes, and documents alongside, with [per-language-pair quality published monthly](https://intermind.com/benchmark). The meeting notes still get generated; they're just no longer the only thing standing between half your room and the discussion. The 1-on-1s, if you're weighing a switch: [InterMIND vs Otter](https://intermind.com/compare/otter) · [InterMIND vs Fireflies](https://intermind.com/compare/fireflies). The wider field: [the 9 best Fireflies alternatives](https://intermind.com/blog/fireflies-ai-alternatives) and [the 9 best Otter alternatives](https://intermind.com/blog/otter-ai-alternatives). --- ## FAQ **Is Otter or Fireflies cheaper?** Entry level: Otter Pro at $8.33/user/mo annual vs Fireflies Pro at $10. But Otter meters minutes (1,200/mo on Pro) while Fireflies transcribes without limits — at real volume, Fireflies is usually cheaper per transcribed hour. **Which supports more languages, Otter or Fireflies?** Fireflies by a wide margin: 100+ transcription languages with auto-detection vs Otter's six (English, Spanish, French, German, Japanese, Chinese). **Do Otter or Fireflies translate meetings?** Neither translates a live meeting. Fireflies transcribes many languages but doesn't translate between them in real time; Otter neither transcribes beyond its six nor translates. For live translation, that's [a different category](https://intermind.com/blog/best-ai-conference-translation-tools). **Can I use both free plans?** Yes, and plenty of people do: Fathom or Fireflies free for volume capture, Otter free for the occasional transcript-workspace session. Watch the two bots colliding in the same call, though — pick one recorder per meeting. --- ## If language is the real bottleneck - **[Run the live demo](https://intermind.com/demo)** — hear the production pipeline translate a real meeting live, in any of 23 languages — no signup needed. - **[Read the benchmark](https://intermind.com/benchmark)** — per-pair quality, monthly, no averaging tricks. — The Mind.com Team --- *Sources: vendor pricing pages ([Otter.ai](https://otter.ai/pricing){rel=""nofollow""}, [Fireflies.ai](https://fireflies.ai/pricing){rel=""nofollow""}), [Otter — supported languages](https://help.otter.ai/hc/en-us/articles/360047247414-Supported-languages){rel=""nofollow""}, [Fireflies — supported languages](https://guide.fireflies.ai/articles/2973706448-learn-about-fireflies-supported-languages){rel=""nofollow""}, checked August 2026. Prices are annual-billing rates unless noted; vendors change plans and language lists over time — check their pages for the current state.* # Speak in your own voice — in a language you don't speak - **You are heard in your own voice.** Recognition, translation, then zero-shot synthesis from a sample of your speech, for every participant, both directions. - **Not a flawless double, and nothing stored unasked.** The live sample dies with the session; the optional saved sample in Settings stays until you press Remove. Lip-sync is on the roadmap, not shipped. - **InterMIND keeps the whole meeting in each member's language,** voice in all 23 languages, captions and transcript alongside. Guests join free by link, no account; you pay only for active members. Here is the part of real-time translation that almost everyone gets wrong, and that almost no one talks about: **the voice you hear.** You can have excellent speech recognition and excellent translation, and still end up with a meeting that feels like a machine reading a list. Because the last step — turning the translated text back into sound — is where most tools quietly substitute *you* with a single generic synthetic narrator. Eight people in the room, one robot voice for all of them. You lose who is speaking, the emphasis, the personality. Intelligible, but not a conversation. InterMIND does the last step differently. When you speak, the other participants hear the translation in a voice that's **recognizably yours** — carrying your timbre and your way of speaking — now saying the words in their language. It isn't a flawless impression yet; the point is that it's *you* rather than a stock narrator, and it's getting better. This works for every participant, in both directions, at the same time. This post is the missing chapter of [*Inside the four translation pipelines that run InterMIND*](https://intermind.com/blog/inside-the-translation-pipelines): that piece explained how audio becomes translated audio. This one is about whose voice comes out the other end. --- ## The default everyone ships, and why it's flat If you've used live translation in any of the big meeting platforms, you know the sound. A neutral, evenly-paced voice reads the translation. It's the same voice whether the speaker is your CEO opening a town hall or a colleague cracking a joke. The technology underneath is text-to-speech with one fixed voice model, and the design assumption is that intelligibility is enough. In a real meeting it isn't. Half of what a meeting communicates is *who* is saying it and *how*. Strip the voice and you've turned a discussion into a transcript that happens to be spoken aloud. People stop reacting to each other and start waiting their turn. ## What InterMIND does instead The translation runs as a **cascaded pipeline** — three specialized stages in sequence rather than one model trying to do everything. The first two stages are covered in the [pipelines post](https://intermind.com/blog/inside-the-translation-pipelines); the voice step is the one this post is about: 1. **ASR — speech recognition.** Your words are transcribed in your own language, as you speak, on our own engine — the media server that carries the call (Mind API, OVH France) — so translation can start before the sentence ends. 2. **MT — translation.** The transcript is grouped into stable sentence fragments — *clauses* — so translation can begin before you've finished the sentence, and each fragment is translated progressively into the listener's language. 3. **Zero-shot TTS — voice synthesis.** Each translated fragment is spoken back out **using a sample of your own voice**, and streamed to the listener. It's that third stage — ASR → MT → **zero-shot TTS** — that produces the effect. "Zero-shot" means the system doesn't need a pre-recorded enrollment or a training session for your voice. It models your voice from the audio of the meeting you're already in. ## The warm-up: how it starts sounding like you so fast There's a chicken-and-egg problem hiding in "use a sample of your own voice." At the very start of a call, the system hasn't *heard* enough of you yet to model your voice well. InterMIND handles this with a progressive warm-up: - **For roughly the first 5–10 seconds**, while it's still gathering enough of your speech, each translated fragment is synthesized using the audio fragment that matches what you *just said* in your source language. The voicing is anchored to your real, immediate speech. - **Once there's a long enough sample** — that 5–10 second mark — the system locks onto it and uses it to voice everything afterward. In practice you don't hear a switch flip. The translation sounds more like you as the conversation gets going — not a perfect double of your voice, but clearly yours rather than a machine's, and improving as the model hears more. The combination of *progressive* translation (clause by clause, not sentence by sentence) and *progressive* voicing is what keeps the whole thing under the latency budget while still sounding human. ## Record your voice once, and skip the warm-up The warm-up above is what happens by default, with nothing set up. Since September 2026 there is an optional second path for signed-in users: a **saved voice sample** in *Settings → Your voice in translation*. Recording it is one gesture. Press **Record my voice**, wait for **Speak now**, and say the numbers from one to ten in any order. Each number lights up on the card as the speech engine hears it; when all ten are lit, the sample is checked and saved by itself. There is nothing to play back or confirm, and no countdown: the card keeps the stretch of your take that holds the numbers. A quiet room and a headset give the best result. What the saved sample changes: from your next meeting, the synthesizer voices your translation with it **from the first fragment**, so the other side hears you as you from the first sentence instead of after the warm-up. Under the hood it is the same zero-shot synthesis with a better starting point; the live warm-up still refines the voice as the call goes on. The take is gated before it is stored. It has to be **3 to 10 seconds** of clear speech (the synthesizer's input window): too quiet, clipped, mostly silence or drowned in background noise, and the card tells you what to fix and asks for another take. Numbers were chosen as the phrase for a practical reason: they are short, recognizable in every one of the 23 languages, and the engine can confirm it heard all ten, which turns "did that recording work?" into a visible yes. ## Two voice samples, two lifetimes This is the part a security or legal team asks about immediately, so here it is plainly. There are two different samples, and they live differently. **The live sample** used for the in-meeting warm-up is **ephemeral**. It exists only for the live conference session, in service of voicing the translation, and it is stored nowhere. The Mind API and SDK that power the real-time session retain no data; everything temporary dies when the conference session ends. **The saved sample** from Settings is stored **with your account, for one purpose**: it is sent to the translation engine each time you join a meeting so your translated speech can be voiced with it, and for nothing else. It stays until you press **Remove** on the card, which returns you to the standard warm-up immediately, and it is deleted together with your account. Guests cannot record one; it is a signed-in feature by design. It's worth being precise about what neither sample *is*: not one of InterMIND's **recording** features. Recording a meeting's video and audio is a separate, deliberate action you take on purpose, with its own controls. A voice sample is an input to the speech synthesizer: transient in the live case, yours to keep or delete in the saved one. ## Why no one else ships this It's not that voice cloning is a secret. It's that doing it **live, per-participant, in both directions, at conversation pace, across 23 languages, without storing anything you didn't ask it to** is a different problem than cloning a voice offline for a podcast. The big platforms optimize their translation for caption coverage and a single safe narrator voice — that's the cheap, robust default at scale. Keeping each speaker's own voice means the synthesis stage has to track every participant independently and stay inside the same latency budget the rest of the pipeline lives under. We built the voice engine ourselves, on our own infrastructure, which is what makes that trade-off ours to make. (More on why the engine is our own code: [*What one InterMIND meeting is built from*](https://intermind.com/blog/what-one-intermind-meeting-is-built-from).) ## Where this is going: lip-sync Keeping your voice is one half of a bigger goal. The other half is your **face**. Right now you hear the other person in their own voice, but if you're on camera, their lips still move to the words they actually said — in a language you don't read. The next step is **lip-sync**: re-timing the speaker's mouth to the translated audio, so that on your screen they appear to be speaking *your* language. Put the two together and the whole point of this work comes into focus. Two people who share no common language sit across a video call and see and hear each other as if each were a native speaker of the other's language — same voice, same face, no interpreter in the middle, no robot reading a script. To be clear about status: **voice is live today; lip-sync is on the roadmap, not shipped.** We're calling out the destination because it's why the voice work matters — own-voice translation isn't the feature, it's the first half of "talk to anyone, in any language, as yourself." ## Where to hear it Own-voice translation is **live today, across all 23 voice languages** — the same languages listed in the [docs](https://intermind.com/docs/translation/languages). There's nothing to turn on separately: when translation is enabled in a meeting, participants automatically hear each other in their own voices. We'll be honest about where it stands: today the voice is already recognizably *you*, and the resemblance is something we're actively pushing closer. Go listen and judge for yourself. - **[Try the demo](https://intermind.com/demo)** — runs the live voice pipeline against your audio in any of the 23 languages. - **[See the quality numbers](https://intermind.com/benchmark)** — the same production pipeline, scored monthly against FLORES-200, with the full distribution published per language pair. - **[Record your voice sample](https://intermind.com/settings)** — signed in, one take of the numbers one to ten, and you are voiced as you from the first sentence. - **[How it works, in the docs](https://intermind.com/docs/translation/own-voice)** — the short version of this post. - **[See it next to captions and a searchable transcript](https://intermind.com/blog/translation-captions-and-transcript-in-one-meeting)** — how the three pieces behave together in one meeting. A translated meeting should feel like the people who are actually in it talking to each other. Keeping your voice is how it gets there. # We earn only when you earn: how the InterMIND partner model works - **Nothing upfront, nothing fixed.** Accounts, internal use and presale are free; we take a share only of your revenue on client contracts delivered through the platform, declared once a quarter. - **One number, no audits, two rates.** Our own meter checks the declaration; sessions your interpreters work carry a lower rate than sessions the platform's AI interprets, blended by measured minutes. - **InterMIND stays behind your brand,** your client contracts with you, pays you and sees only you; an integrator buys at wholesale only after the bid is won. Our partner program fits in one sentence: **you never pay us before you've been paid. $0 upfront, $0 fixed — ever.** That sentence raises reasonable questions the moment you take it seriously. A share of *which* revenue? Do we see your clients? How many seats do you have to license? What happens in a quarter where you earn nothing? Who counts what, and how do you know the invoice is right? This post answers all of them, in order, with the arithmetic on the table. It exists so that you can understand the whole model before the first call — and so the first call can be about your contracts, not about our mechanics. ## Who this is for The program has two tracks, and they work differently: - **Language service providers (LSPs)** — interpreting agencies delivering remote or on-site interpretation, from national framework holders down to single-interpreter practices. You get the platform as a **white-label delivery tool**: your brand, your billing, your client. We take a revenue share on what you bill — nothing else. - **IT and AV integrators** — companies that build and win tenders in verticals like courts and healthcare, where a translation capability is a line in a larger bid. This is a classic **reseller** track: the entire presale phase is free, and you buy at a wholesale price only after you've won. Most of this post walks through the LSP track, because that's where the mechanics are least familiar. The integrator track is summarized [below](https://intermind.com/#the-integrator-track-reseller). ## What costs you nothing — and stays that way Start with what is *not* billed, because this is where per-seat habits mislead. **Accounts are free and unlimited.** If your operation needs 10 seats to serve several clients at once — or 50, or 200 for every interpreter on your roster — you create them. There is no per-seat license, no seat tier, no seat audit. We don't sell access; access is how you get to the point where both of us earn. **Internal use is free.** Your team's own meetings, sales calls, project calls — all of it, including calls where you try the voice translation yourself. None of this appears on any invoice. **Onboarding and presale are free.** Setting up your workspace, demo sessions for a client you're pitching, test runs before a tender submission — free. If the deal doesn't happen, that cost was ours, not yours. There is no catch hiding here. The reason we can afford this is structural, and it's covered [below](https://intermind.com/#why-we-can-price-this-way). ## What we take a share of We earn a percentage of **your revenue on client contracts delivered through the platform**. Nothing else. The definition matters, so here it is precisely: a *platform contract* is a contract with your client where the platform was used to deliver the service — for example, a court framework where hearings are interpreted through your white-label workspace, or a healthcare contract where appointments run on it. What this means in the negative: - **Not a share of your company's revenue.** Your translation business, your on-site work delivered without the platform, contracts from before the partnership — none of our business, literally. - **Not a fee per minute, per meeting, or per seat.** Usage itself is never the billable unit. A busy month with no revenue attached to it costs you nothing. - **Not a payment from your client.** Your client pays you, on your contract, on your bank account, under your brand. We are not in the transaction and not visible in it. We do not know who your clients are unless you choose to tell us. The rate is agreed per partner and is not public. Two things about it are public: **volume moves it in your favour** — the more annual revenue you deliver through the platform, the lower the marginal rate, in tiered brackets that work like tax brackets (a lower rate applies to revenue above a threshold, never retroactively to the whole sum) — and **the rate depends on who does the interpreting**, which the next-but-one section explains. ## The money flow, step by step Here is a full quarter, end to end: 1. **You win and deliver contracts as usual.** Your client signs with you, pays you, sees your brand. Delivery runs through your platform workspace. 2. **Once a quarter, you declare one number**: your revenue on platform contracts for that quarter. One figure. No client names, no contract copies, no books opened. 3. **We send one invoice**: your declared figure × your rate. A regular invoice, paid by regular bank transfer. 4. **An empty quarter is a €0 invoice.** Didn't win the tender, client paid late, business was slow — you declare zero and owe zero. The principle at the top of this post is not marketing; it is the billing rule. Worked example with a placeholder rate: an agency holds a court framework and receives **€30,000** from the court in a quarter, delivered through the platform. It declares €30,000. At a rate of X%, our invoice is **€30,000 × X%**. That is the entire administrative burden of the relationship: one declared number in, one invoice out, four times a year. ## One number, no audits — how verification actually works A fair question: if you self-declare one figure, what stops anyone from under-declaring? And symmetrically, from your side: what stops *us* from disputing your figure forever? The answer is that the platform meters its own usage. Every session in your workspace, every translated minute, is counted by our infrastructure — we operate it, so we see it. Metered usage times market interpreting rates gives a rough expected revenue. If a declaration lands wildly outside that expectation, it's visible automatically — and it becomes **a conversation, not a court case**. Deliberately, the agreement contains **no audit rights**. We never ask to see your accounting, your client list, or your contracts. The declaration plus our own meter is the entire verification apparatus. This is also why the agreement itself fits on two pages: every clause we didn't add is a week of legal review you don't spend. ## Human interpreting and AI translation carry different rates The platform supports two ways of delivering a translated session, and they are economically different for *you* — so they carry different rates: - **Your interpreter works the session; the platform delivers it.** The interpreting is done by a human you pay. Your margin on that contract is what's left after the interpreter's fee — and our share has to fit inside it. Rate: the lower, tiered X% band. - **The platform's AI does the interpreting; no human interpreter is engaged.** Your largest cost line on that contract doesn't exist, so your margin per contract is a multiple of the human-delivered case. Rate: a higher Y% — and you still keep far more per euro than on human delivery. The higher percentage is not a penalty; it reflects that on these contracts the platform is doing the work you'd otherwise pay an interpreter for. **You do not classify anything.** Real contracts mix modes — a human for rare languages, AI for common ones; a human by day, AI for the night line. Splitting your revenue by mode would be exactly the accounting burden this model exists to avoid. So the split comes from our meter, not from your books: we measure the share of AI-translated minutes across your client sessions in the quarter, and blend the rate accordingly: > **effective rate = X% + (Y% − X%) × AI share of client-session minutes** Your quarterly invoice arrives with a one-page statement showing the inputs: client-session hours, AI-translated hours, the resulting blended rate, and the formula. You see where the number came from before you pay it. Three boundary rules keep the blend honest: 1. **Assistive AI doesn't count as AI delivery.** Captions or document translation running alongside your human interpreter don't move a session into the AI band. Only spoken AI interpreting counts. 2. **Only client sessions count.** Your internal meetings — including ones where your team uses AI translation — never enter the calculation. 3. **A gross mismatch is reviewable in both directions.** The minute-based blend is an approximation; if your revenue structure genuinely diverges from it, that's a conversation and an adjustment, not a dispute clause. []{#the-integrator-track-reseller} ## The integrator track (reseller) For integrators the model is simpler, because your business is bids, not recurring service delivery: - **The presale phase is free** — proof-of-concept, demo environments, and help with the translation section of your tender response. You pay nothing while the bid is open. - **You buy at a wholesale price only after you win**, resell at your price, and keep the margin. - **Your wholesale price is grandfathered for the full duration of your client contract.** Public-sector contracts run for years at fixed prices; your input cost will not move underneath a price you can no longer renegotiate. ## What protects you from us A platform partner's real worry isn't the rate — it's the platform deciding to go around them. What we commit to is structural, not promised territory: - **Your client contracts with you, pays you, and sees your brand only.** We are not part of the transaction and don't know who your clients are unless you tell us — there is nothing on our side to go around you with. - **Signed terms are grandfathered.** Contracts you've signed keep their rate for their full duration; any revision applies to new business only. - **What we don't promise is an exclusive vertical or territory.** We're building the channel, and locking a segment to one partner isn't something we'd honestly commit to today. And one more, less obvious: because your clients contract with *you*, under *your* brand, the client relationship is your asset. A white-label platform makes your business more valuable; it doesn't insert itself between you and what you've built. []{#why-we-can-price-this-way} ## Why we can price this way No trick, just cost structure. We built and operate our own translation engine and run meetings on our own infrastructure. Adding a partner — with all their seats, workspaces, and internal use — adds approximately nothing to our costs; our capacity is a step function we expand ahead of demand, not a per-seat license bill that scales with every account you create. That means giving you free unlimited access costs us nearly nothing, and taking our earnings only as a share of your *actual* revenue is safe for us at any volume. A vendor whose economics are built on per-seat licensing cannot make you this offer without breaking its own P\&L. We can, so we do — and we'd rather take that structural advantage to market as *your* zero-risk entry than as a discount percentage on a price list. ## How to start If you run interpreting contracts — or bid in verticals where translation is a required line — the conversation starts on the [partners page](https://intermind.com/partners). Bring one real contract or one live bid; the first working session is about mapping the model onto it. The agreement that follows is two pages, and you now know everything that's in it. ## FAQ **Do you take a share of my company's whole revenue?** No. The share applies only to revenue on contracts delivered through the platform. Your other business — translation work, on-site delivery without the platform, pre-existing contracts — is entirely outside the model, and we have no visibility into it. **Do you see or contact my clients?** No. Your client contracts with you, pays you, and sees your brand only. We are not part of the transaction and don't know who your clients are unless you tell us. **How many user accounts do I need to buy?** None — accounts are free and unlimited. If serving several clients at once takes 10 seats, or your whole interpreter roster needs access, you create the accounts and pay nothing for them. There is no per-seat license anywhere in the model. **What happens in a quarter where I earn nothing?** You declare zero and receive a €0 invoice. No minimums, no fixed fees, no "platform maintenance" line. A quarter without revenue on platform contracts is a quarter you pay nothing. **How do you verify my declaration without auditing me?** The platform meters its own usage — sessions and translated minutes in your workspace. Metered usage times market interpreting rates approximates expected revenue, so a wildly divergent declaration is visible automatically. The agreement contains no audit rights: a discrepancy triggers a conversation, not an inspection of your books. **What if a contract mixes human interpreters and AI translation?** You still declare one number. The human/AI split is measured by our meter — the share of AI-translated minutes in your client sessions — and your rate is blended accordingly. The invoice comes with a one-page statement showing the hours, the split, and the formula, so the math is on the table before you pay. **What exactly counts as a "platform contract"?** A contract with your client where the platform was used to deliver the service — hearings interpreted through your workspace, appointments run on it, sessions delivered under your brand on our infrastructure. Internal meetings and unpaid demo use never count, whatever features they use. **Are your rates public?** No — rates are agreed per partner. Two things are fixed in the structure: volume moves the rate in your favour (tiered, like tax brackets, never retroactive), and contracts where the platform's AI does the interpreting carry a higher rate than contracts your interpreters deliver — because on the former, your interpreter cost line doesn't exist. **Can you raise my rate after I've signed contracts against it?** Contracts you've signed keep their terms. Any revision applies to new deals only — the same grandfathering logic that fixes an integrator's wholesale price for the duration of a won contract. **Is there a minimum commitment, setup fee, or onboarding fee?** No. $0 upfront and $0 fixed is the billing rule of the program, not a promotional period. The first euro that moves from you to us is a percentage of a euro your client has already paid you. # Pay only for the people who use it: InterMIND moves to per-active-member billing - **Seats are gone, the invoice follows use.** Everyone in a paid organization has the paid features; each renewal bills those active in the previous 28 days. - **Active means three server-side actions.** Joining a meeting, writing in a chat or asking Mia; reading or signing in does not count. Up the day a member acts, down once at renewal. - **InterMIND keeps the whole space in each member's language,** quiet members keep access at no cost. Guests join free by link, no account; you pay only for active members. Until now a Pro or Business subscription worked like most software: you bought a number of seats and assigned them to people by hand. The seat was paid for whether the person used InterMIND that month or not, and a colleague without a seat could not use the paid features until an admin freed one. That is the one place in the product where the host paid for a promise instead of for use, and it produced two mistakes in both directions at once: money for people who had moved on, and a locked door for people who had just joined. We are replacing it. From the switch, the right to use a paid plan comes with membership in a paid organization, and each renewal bills only the members who were active in the previous 28 days. Invite everyone; the invoice follows what actually happened. Messaging tools call this model fair billing, and the rest of this post is the exact rules of ours. ## What changes for a host | | Before | After | | -------------------------------------------------------- | -------------------------------------------- | ---------------------------------------------------------------- | | Who has the paid features | Members with an assigned seat | Every member of the paid organization | | What the renewal bills | The number of seats you bought | The members active in the previous 28 days | | A member who stops using InterMIND | Keeps costing a seat until an admin frees it | Drops out of the next renewal, keeps their access | | A colleague who joins mid-cycle | Needs a free seat or a purchase | Joins, and is added to the bill on the day of their first action | | Meeting guests and channel participants outside the team | Free | Free, unchanged | | The organization owner | Always a seat | Always counted, so the bill is never below one | Nothing changes for participants. The host provides the space; everyone they invite takes part in the language they think in and pays nothing, whether they sign in or join as a guest. ## What counts as active Three actions, all recorded on the server side, so the count cannot be gamed or accidentally inflated by a browser tab: - **Joining a meeting.** The moment a member enters a room, as a host or a participant. - **Writing in a chat.** A message, a file or a voice note in any channel of the organization. - **Asking Mia.** A question to the organization's AI assistant. Signing in, opening the app, reading a channel, receiving a recap by email: none of these counts. A member who only reads for a month is not billed for that month. A person the admin invited who never took any action is not a member for billing purposes either. The counter starts on the day of the first action, not on the day of the invitation. Slack, whose Fair Billing Policy is the reference for this model, bills a paid workspace for the members actively using it and treats a member with no activity for more than 28 days as inactive; our count starts one step later, at the first action, so an invitation that nobody accepts costs nothing (checked September 2026, source below). ## How the number moves inside a cycle The billed number is the organization's active-member count, and it moves by two rules: - **Up, on the day it happens.** When a member takes their first action in the current cycle, the count grows by one that day, and the difference is billed for the rest of the cycle. On a monthly plan the prorated amount appears on the next invoice; on a yearly plan it is charged right away for the rest of the year, so that a colleague who starts in month two is not free for the remaining ten. - **Down, once, at renewal.** One day before the renewal, the count is set to the number of members who were active in the previous 28 days. A member who went quiet in the middle of a cycle is dropped at that point, not earlier. We do not issue mid-cycle credits for members who go quiet. That is a deliberate simplification: the rule is easy to read on the billing page, and a member who stops using the product is simply not on the next invoice. The owner is always counted, so the number never goes below one. The count never exceeds the number of members in the organization, and each plan keeps its member ceiling as before. ## What you see before you pay - **Manage members** shows an **Active** column with each member's last activity, and a line at the top: **N of M members active in the last 28 days, billed at the next renewal**. - **The billing page** shows the same line next to the renewal date. - **A letter three days before renewal** goes to the owner and the admins: how many members the invoice will count, the amount when the plan price is known, and which members are quiet and not billed. It is written in the language each recipient reads. If the count in the letter is not what you expect, three days is enough to look at the members list and, if needed, remove someone before the renewal. ## The trial, the plans, and the contracts The 14-day trial charges nothing until it ends (since September 2026 the Pro trial starts with no card at all). The first invoice after the trial counts the members who were active by then, the owner included. Plan prices, the yearly discount and the free Basic plan are unchanged and stay on the [pricing page](https://intermind.com/pricing). What goes away is the seat: there is no quantity to choose at checkout and no seat count to edit in the customer portal, because the application sets the number from activity. Enterprise and partner agreements keep a committed number of members written into the contract. That is a term of the agreement, not a different product; the space works the same way. ## When The change is rolling out now. Your organization moves to the new count at its first renewal after the switch; until then, invoices stay exactly as they are. The Active column and the "N of M" line appear on your members page first, so you see the number before it ever reaches an invoice. ## FAQ **What counts as active on InterMIND?** Three server-side actions in the previous 28 days: joining a meeting, writing in a chat (a message, a file or a voice note), or asking Mia a question. Signing in, reading a channel and receiving a recap do not count. **Do meeting guests or outside channel participants cost anything?** No. Only members of the paid organization are counted. Guests who join a meeting by link and people who take part in a channel without being members of the team are free, as they were before. **What happens to a member who goes quiet?** They keep their access and every right of the plan. At the next renewal they are not counted; if they take an action again later, they are added to the bill on that day for the rest of the cycle. **When does my bill change?** Inside a cycle it can only go up, on the day a member takes their first action. It goes down once, one day before renewal, to the number of members active in the previous 28 days. A letter three days before renewal shows the count in advance. **How does this work on a yearly plan?** The same way. A member who becomes active in the middle of the year is charged for the rest of the year right away; members who went quiet are dropped at the yearly renewal. **Can I still buy seats for people who have not joined yet?** No, and you do not need to. Invite them; they are counted from the day of their first action, and an invitation that nobody accepts costs nothing. **Does an Enterprise contract with a fixed number of members change?** No. Enterprise and partner agreements keep the committed number written into the contract. ## Where to look - **[See the plans](https://intermind.com/pricing)** — Basic, Pro, Business, Enterprise, with the trial and the yearly discount. - **[Manage your team](https://intermind.com/docs/users/managing)** — the members list with the Active column. - **[Manage your subscription](https://intermind.com/docs/billing/manage)** — renewal, invoices, changing or cancelling a plan. *Sources: Slack's Fair Billing Policy ([slack.com/help](https://slack.com/help/articles/218915077-Slack-s-Fair-Billing-Policy){rel=""nofollow""}), checked September 2026. Facts about InterMIND are verified against the product's code and its published pricing at the date of this post.* # How do you see the room while you're presenting? - **Only partly.** Meet documents picture-in-picture, Zoom dual-monitor mode, Teams a presenter-only chat panel; each lives inside the meeting window and competes with the document you edit. - **A browser side panel sits outside that contest.** Part of the browser frame, not the tab; a shared tab does not capture it (our test, not a documented guarantee). - **InterMIND keeps the whole meeting beside the tab you edit:** call, chat and participants in the Chrome or Edge side panel. Guests join free by link, no account; you pay only for active members. The moment you share your screen, you stop being able to see the people you are sharing it with. The faces go away. The chat goes away. A raised hand — the most time-sensitive signal in the room — goes away. This is one of the most persistent complaints in every major platform's support forum, and the way people describe it is consistent. One presenter, asking Microsoft for the feature: *"As a presenter it is critical to read the audience."* A teacher on Zoom's forum: *"if I want to interact with a specific student, I have no idea who is out there."* Another, describing what they lose: *"all of the things that I'd be able to do if we were in-person."* The complaint is not that a panel is missing. It is that presenting online puts you in a position no one would accept in a room: talking to a wall, guessing whether anyone is following. ## Every fix trades one loss for another What makes this stubborn is that the available answers do not remove the problem — they move it. **The overlay covers what you're showing.** Put the participant gallery on top of the content and you get the room back, at the cost of the thing you are presenting. A host on Zoom's forum: *"the only way I can find to do is to show the gallery overlaid over the PP, which blocks some of the image."* Another user describing the same bind from both sides: *"It obstructs the screen in full screen, and then takes up more real estate than I want when I am not."* Occlusion or invisibility — pick one. **The second monitor doesn't reliably fix it either.** This is the standard advice, and it is worth being precise about its limits. It assumes you have a second display, which rules out laptop-only and travel setups. But even with two, users report losing the roster the moment slides go full screen: *"every time I put PPT into presentation mode, I lose my participant gallery. My choices are to have the shared screen on one monitor and presenter dashboard on the other, or have 2 screens mirroring each other… both showing the shared screen. Totally unacceptable for either a class or a meeting."* **Window juggling is what people actually do.** The real-world workaround is manual choreography — shrinking, dragging, re-opening. One Teams user: *"As work around I opened the Teams screen and moved to the left, just the list of participants was visible, while diminishing the screen I shared."* The reason none of these settle the matter is structural. The meeting is a window. What you are presenting is a window. On one screen, windows compete — for space, and for focus. ## The version of this that hurts most: when you're editing what you share There is a case where the trade-off stops being about comfort and starts blocking the work itself. Most advice about screen sharing assumes you are presenting something finished. A deck. A dashboard. A recorded flow. But plenty of working meetings share the thing being *changed* — the spec getting a new paragraph, the sheet getting the corrected number, the project board getting the card everyone just agreed to move. As one person put it when asking how to keep seeing participants: *"Not just PowerPoint or Excel, but anything."* Now the conflict is sharper. To edit the document, the document needs focus — it has to be the window you are typing into. So the meeting goes behind it, and with it goes the chat where someone is pasting the exact wording you should use, and the pointer you were using to show people which row you mean. Keep the meeting in front and you are talking about the change instead of making it. Make the change and you are working blind. The work moves to "after the call," away from the room that just agreed to it. ## What the platforms actually document The vendors document three different answers, and they are worth reading precisely — because one of them is closer to a solution than the others, and it is not the one people assume. Google documents picture-in-picture mode for Meet, stating you can "use picture-in-picture mode to concurrently present and find your audience," and unpinning a presentation so you "can now find more participants while you present" (checked August 2026). Both address seeing *participants*; Google's presenting page does not document a way to keep chat visible while presenting on a single screen. Zoom documents dual-monitor mode, where "gallery or speaker view can be displayed on one monitor while the other monitor displays shared content" — with stated prerequisites including the desktop app and a CPU floor of an i5 with four or more cores (checked August 2026). It is the second-monitor answer, written down as a feature. Microsoft goes furthest. Teams documents a presenter toolbar "only visible to the person presenting," and states: "Select **Chat** to view and participate in a compact view of the meeting chat while you're presenting content. Your audience won't see the chat window in your shared screen" (checked August 2026). That last one matters for anyone comparing options: a private, non-captured chat panel for the presenter is not a gap in the market — Teams documents one today. The remaining difference is what the presenter's *other* window is doing. Meet's and Teams' presenter surfaces are parts of the meeting app's own window; the document you are editing is still a separate window competing for focus with it. ## What changes when the meeting stops being a window There is one surface in a browser that does not compete for focus with the page: the browser's own side panel. Chrome documents the Side Panel API as a way for an extension to "host content in the browser's side panel alongside the main content of a webpage" (checked August 2026). The relevant property is structural. The panel is part of the browser frame, not part of the tab. It sits beside whatever tab is active, it stays put when you switch tabs, and typing into the page does not push it behind anything — because it was never in the stack the page is in. That has a second consequence, and here we should be careful to separate what is documented from what we measured. Chrome's screen-capture documentation describes tab capture as capturing the visible area of a tab, and the W3C screen-capture specification leaves the exact boundary of browser UI implementation-dependent — neither states what happens to a side panel. So we tested it: when sharing a **tab**, the side panel does not appear in the captured stream. Participants see the tab you picked, not the panel beside it. That result is share-mode specific, and the distinction is the whole point. Share your **entire screen** and everything on that screen is captured, panel included. The property we rely on holds for tab shares, which is the mode this workflow uses. Put those two properties together and the trade-off dissolves rather than gets managed: - The document is the active tab. It has focus. You type in it, and it is the full width of your screen — not half of it, and with nothing overlaid on top of it. - The meeting lives in the panel beside it, in the app's narrow layout: the call, the chat, the participants, the pointer controls. - Your participants see the document. Not your call window, not the chat you are reading — the tab you picked, and the pointer you use on it. This is what we built the InterMIND Chrome extension for — now published in the Chrome Web Store, see [the announcement](https://intermind.com/blog/meet-in-the-side-panel). The call runs in the side panel; the tab you share stays yours to edit. In a working session on a project board it means the board is at full width and being edited, the pointer still shows the room where to look, and the chat is still readable beside it — at the same time, on one screen, with no second monitor and nothing covering the content. Note what this does *not* claim to fix. The panel is narrow, so a large gallery of faces is not what fits there — this answers "keep the room and its chat reachable while I work," not "show me thirty video tiles at once." ## The honest limits Three things are worth stating plainly, because they set expectations correctly. **The share still starts with the normal picker.** You click share, Chrome asks which surface you want, you pick the tab. There is no one-click "share the tab I'm on" from a side panel — Chrome does not grant extensions tab capture from the panel context, and a request to add that capability was closed by the Chromium team as won't-fix (checked August 2026). The picker is one click. It is the mechanism, not a workaround. **This is browser-specific.** The side panel is a Chromium feature. The scenario described here is a Chrome and Edge scenario; on other browsers you are back to arranging windows. **It solves one problem.** Sharing a tab while editing it, without losing the call UI. It does not make a small laptop screen bigger, and if what you need to share is a desktop application rather than a browser tab, the tab-capture property does not apply to it. ## Where this matters most The pattern shows up wherever the artifact is live rather than finished: - **Working sessions on a doc or spec** — editing wording as the room reacts to it, instead of writing down feedback to apply later. - **Spreadsheets and planning models** — changing an input and letting everyone watch the number move, which is the whole reason the sheet is on screen. - **Project boards and backlogs** — the reason we noticed this internally: moving cards and editing tickets during a planning call while still reading what people are typing about them. - **Design and code review** — making the small fix during the call, while the pointer marks what is being discussed. What these have in common is that the value of the meeting is the *change to the artifact*, and any workflow that pushes the editing to "after the call" moves the work out of the meeting where the agreement happened. ## FAQ **How do you see participants while presenting?** Each platform documents a different partial answer. Google documents picture-in-picture and unpinning the presentation to "find more participants while you present." Zoom documents dual-monitor mode, which needs a second display. Microsoft documents a presenter toolbar visible only to the presenter (all checked August 2026). The common limit is that these surfaces live inside the meeting app's own window, so they compete with whatever else you are doing — which is why users report losing the roster anyway the moment slides go full screen, even on two monitors. **Why do I lose the participant gallery when PowerPoint goes into presentation mode?** Because presentation mode takes over the display it is on, and the meeting window is a separate window that gets pushed behind it. This is why a second monitor does not automatically settle the problem: users with two displays report the same loss, since the choice becomes which display the slideshow claims. The alternatives people fall back on are overlaying the gallery on top of the content, or manually resizing windows. **How do you see chat while sharing your screen on one monitor?** It depends on the platform. Microsoft documents a compact meeting-chat view in Teams for the presenter, stating the audience will not see that chat window in the shared screen (checked August 2026). Zoom's documented answer is dual-monitor mode, which needs a second display (checked August 2026). Google's presenting documentation covers seeing participants via picture-in-picture, not chat (checked August 2026). What none of them changes is that the presenter surface belongs to the meeting app's window — so if you also need to *edit* the shared document, that document and the meeting are still two windows competing for one focus. **Can you edit a document while screen sharing it?** Yes — the limitation is not on editing, it is on what you can see while you do it. The document has to hold focus for you to type into it, which puts the meeting interface behind it on a single screen. The document keeps being shared the whole time; you just lose sight of chat, participants and the pointer while working in it. **Do you need two monitors to present and work at the same time?** Two monitors is the standard answer and it works. It is not the only one: a browser side panel gives you a second surface on a single screen, because the panel sits in the browser frame beside the page rather than competing with it for focus. **Does the side panel show up in your screen share?** Not when you share a tab — we tested this, and the panel does not appear in the captured stream. Chrome's documentation and the W3C screen-capture specification do not state the behavior either way (the spec leaves browser-UI boundaries implementation-dependent), so treat this as a measured result rather than a documented guarantee. If you share your entire screen instead, everything visible on that screen is captured, including the panel. **Is there a way to share the current tab in one click, without the picker?** Not from a side panel. Chrome does not grant extensions tab capture from the panel context, and the request to allow it was closed as won't-fix by the Chromium team (checked August 2026). The share starts from the standard Chrome picker, where you select the tab. **Which browsers does this work in?** The side panel is a Chromium feature, so this applies to Chrome and Edge. Other browsers do not have an equivalent surface, and the window trade-off described above applies there as normal. **Does this replace a second monitor?** For this specific case — sharing a browser tab while editing it and keeping the call UI visible — it removes the reason you needed the second monitor. It does not replace a second monitor for everything else a second monitor is good for. ## Try it - **[Get the Chrome extension](https://intermind.com/blog/meet-in-the-side-panel)** — what it installs, what it asks for, and what it does not do. - **[How to share your screen in a video meeting](https://intermind.com/blog/how-to-share-your-screen-in-a-video-meeting)** — screen, window or tab, from a phone, with the laser pointer, and where Meet and Teams stop. - **[Try the live demo](https://intermind.com/demo)** — see how a translated call behaves before installing anything. - **[See what happens to a file you share into the meeting](https://intermind.com/blog/teams-meeting-shared-files)** — who can read it, in which language, and how a claim in its summary gets checked. - **[Read the translation benchmark](https://intermind.com/benchmark)** — the quality numbers, with the full per-pair distribution and the method behind them. --- *Sources: [Chrome for Developers — chrome.sidePanel API](https://developer.chrome.com/docs/extensions/reference/api/sidePanel){rel=""nofollow""}, [Chrome for Developers — chrome.tabCapture API](https://developer.chrome.com/docs/extensions/reference/api/tabCapture){rel=""nofollow""}, [W3C — Screen Capture](https://www.w3.org/TR/screen-capture/){rel=""nofollow""}, [Chromium issue 40926394 — chrome.tabCapture from side panel](https://issues.chromium.org/issues/40926394){rel=""nofollow""}, [Google Meet — Present during a video meeting](https://support.google.com/meet/answer/9308856){rel=""nofollow""}, [Zoom — Using dual monitor mode](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0064500){rel=""nofollow""}, [Microsoft — Present content in Microsoft Teams meetings](https://support.microsoft.com/en-us/teams/meetings/present-content-in-microsoft-teams-meetings){rel=""nofollow""}. Vendors change their apps and documentation over time; check their pages for the current state. All facts checked August 2026.* # Kick off meeting: agenda, checklist, example — for a project and for a new client, and how the kickoff becomes the channel (2026) - **The first meeting of a project, held once.** Team and sponsor agree purpose, what done means and when, workstream owners, and risks. - **Its real test is the month after.** Teams, Zoom, Google Workspace and Slack leave one document in the room's language, with limits for outside attendees. - **InterMIND keeps the whole project in each member's language:** the kickoff becomes the channel with its chat, files and recaps, next to Teams or Slack rather than instead of them. Guests join free by link, no account; you pay only for active members. A kick off meeting is the first meeting of a project: the one where the people who will do the work agree what the project is for, what "done" means and by when, who owns which part, how they will communicate while it runs, and what could go wrong — before any of the work starts. It is held once per project, and once per client when a new engagement begins. A project with a kickoff has a record of what everyone signed up to; a project without one finds out in week six that two people were building different things. This guide is the craft first — what the kickoff must leave behind, the checklist for before, during and after, a 60-minute agenda you can copy, two filled-in examples — then the mechanics: where the record lives in the tools your team already uses, what the person outside your organization gets, and what happens to the kickoff after it ends. Because the kickoff's real test is not the hour itself. It is the month after, when a new person joins the project and asks where to read what was agreed. ## What a kick off meeting is — and what it isn't Four meetings sit around the start of a project, and they are often confused: | | When | What it produces | Who is in it | | -------------------- | -------------------------------------- | --------------------------------------------------------------------------------- | ------------------------------------------------------------- | | **Discovery call** | Before the project is sold or approved | Whether there is a project at all, and roughly what it is | The buyer and the seller, or the sponsor and the lead | | **Planning meeting** | Before the kickoff | The plan: scope, phases, estimates, a draft schedule | The lead and the people who estimate | | **Kick off meeting** | At the start, once | One shared understanding: purpose, definition of done, owners, how we work, risks | Everyone who will do the work, plus the sponsor or the client | | **Status meeting** | Weekly, while it runs | Where things stand against the plan | The team, sometimes the client | The kickoff is the third one, and it exists because the first two were held by a few people. The [discovery call](https://intermind.com/blog/discovery-call) decided that the project is worth doing; the planning meeting decided how; the kickoff is where the whole team — and the client, if there is one — hears the same version and gets to say "that is not what I understood". It is not the planning meeting with more people in the room, and it is not a presentation of the plan: a kickoff where nobody but the lead speaks has produced a deck, not an agreement. ## What the kickoff must leave behind Everything a kickoff should contain follows from the five things it must produce. Write these five down before you write the agenda; if an item on the agenda serves none of them, it belongs in a message. 1. **The purpose, in one sentence, with the person it is for.** "Replace the warehouse system before the autumn season so the Lisbon depot ships the same day" — not "warehouse project". The sentence is what the team will measure the scope creep of week eight against. 2. **The definition of done, and the date it is judged on.** What exists at the end that does not exist now, and who says it is done. A kickoff that ends without a date and a judge has postponed its hardest decision to the moment it is most expensive. 3. **The workstreams, with one owner each.** Not a team per stream — a name. The owner is the person who will be asked in the weekly where the stream is, and who can say "we are late" without checking with anyone. 4. **How the project communicates.** Where the project's messages live, when the weekly happens, who writes the recap and where it goes, and how someone escalates. This is the item most kickoffs skip because it feels administrative; it is the one the month after is made of. 5. **The risks each person already sees, and the first next steps.** Everyone in the room has already spotted something that worries them. Five minutes of saying it aloud at the start costs less than discovering it in a status meeting. Then: the first three actions, with names and dates. What stays out: the detailed schedule (a pre-read), the budget line by line (the sponsor's meeting), and anything that only two people need to discuss. ## The kick off meeting checklist: before, during, after **Before — a week to a day ahead.** - Write the purpose sentence and the definition of done as a draft, and send them with the invitation. The kickoff confirms or corrects them; it does not discover them from scratch. - Choose the people: everyone who will own a workstream, the sponsor, and — for a client project — the client's decision-maker, not only their project contact. Anyone who is "nice to have" gets the recap instead. - Post the pre-reads where the project will live from now on: the brief, the statement of work or the plan, the draft schedule. Three documents at most. A kickoff where the pre-reads arrive during the meeting spends its first twenty minutes reading. - Book the time with the agenda inside the invitation, item by item with minutes, so that people arrive knowing the meeting ends with owners and dates. - Open the place the project will live in — the channel — before the kickoff, with the invited people already in it, so that the first message of the project is the agenda rather than "where do I find the link". **During — run the list, not the clock.** - Open with the purpose sentence, read aloud by the sponsor or the client, not by the lead. Hearing the person who wants the result say what the result is changes what the room agrees to. - For the definition of done, ask one question and wait: "On the date, what will exist that does not exist now?" Write the answer down in front of everyone while they watch. - Go through the workstreams one by one, and leave each one only when a name is next to it. "The design team" is not a name. - Spend ten real minutes on how the project will communicate: the channel, the cadence of the weekly, who writes the recap, how something urgent is raised. Decide, do not describe. - Do the risk round as a round: each person, one risk, one sentence, no discussion. Park anything that needs a decision. - Reserve the last five minutes to read the outcomes back: purpose, done, owners, how we work, risks, first actions with names and dates. Reading it aloud is what turns a conversation into a record while everyone who had it is still there. **After — the same day.** - Publish the recap to everyone invited, including the people who could not come: the five outcomes, the decisions, the actions with names and dates, the parking lot. - Put it where the project lives, not in one person's notes, so that it is the first thing a new member of the project reads. - Create the weekly from the kickoff — same place, same link, the cadence you agreed — before the day ends. A kickoff whose weekly is scheduled "next week" has already lost the first one. - Start the actions. The first three should be visible as done or in progress by the first weekly, or the kickoff has taught the team that dates are decorative. ## A kick off meeting agenda template > **\[Project name] — kick off meeting**:br**Date:** \[date] · **Time:** \[start]–\[end] · **Link:** \[meeting link] :br**Purpose:** \[one sentence — what this project produces and for whom] :br**Facilitator:** \[name] · **Recap:** \[name or "the recap"] :br**Pre-reads:** \[the brief], \[the plan or statement of work], \[the draft schedule] > > **1. Why this project, and for whom** — sponsor or client — 10 min — *information*:br > \[The purpose sentence, read by the person who wants the result. One question each from the room.] > > **2. What done means, and the date it is judged on** — project lead — 15 min — *decision*:br > \[What exists at the end that does not exist now; who judges it; the date.] > > **3. Workstreams and owners** — project lead — 15 min — *decision*:br > \[One line per workstream: what it delivers, who owns it, its first milestone.] > > **4. How we work: channel, weekly, recap, escalation** — project lead — 10 min — *decision*:br > \[Where messages live; the day and time of the weekly; who writes the recap and where it goes; how something urgent is raised.] > > **5. Risks each person already sees** — everyone — 5 min — *discussion*:br > \[One risk per person, one sentence each; parked, not solved.] > > **6. Outcomes and first actions** — facilitator — 5 min :br > Purpose, done, owners, how we work, risks — read back. First actions: \[name] — \[task] — by \[date]. > > **Parking lot:** \[raised, not decided — carried to the first weekly] Sixty minutes is the usual booking: items 2 and 3 are the ones that run over, so the agenda gives them half the hour. For a small project with three workstreams, forty-five minutes works; a kickoff that needs two hours is usually a planning meeting that has not happened yet. ## Two filled-in examples ### Internal project kickoff — a new warehouse system, 60 minutes A 60-person distributor in Valencia replaces its warehouse software with an integrator's team in Bucharest. The sponsor is the operations director; the team is the warehouse lead, the finance lead, the integrator's project manager and two of their developers. > **Purpose:** ship from the new system before the autumn season, so that the Lisbon depot ships the same day it receives an order. :br**1. Why this project, and for whom** — Marta, operations director — 10 min — *information*:br**2. Done means: all three depots on the new system by 15 September, judged by Marta on the first full week of live orders** — Andrei, project lead — 15 min — *decision*:br**3. Workstreams: data migration (Andrei), warehouse process and training (Luis), finance integration (Carmen), go-live and support (Ioana)** — 15 min — *decision*:br**4. How we work: the project channel; weekly on Tuesday 10:00; recap written from the meeting and posted to the channel; anything blocking a depot goes to Marta the same day** — 10 min — *decision*:br**5. Risks: the barcode printers in Lisbon, the finance close in August, two developers on holiday in the same fortnight** — everyone — 5 min — *discussion*:br**6. Outcomes and first actions** — 5 min :br**Leaves behind:** the project's first record — done means X by 15 September, four owners, a channel and a weekly, three risks with a name next to each. ### Client kickoff — an agency starts a six-month engagement, 60 minutes A 25-person agency in Lyon starts a new website and campaign for a client in Madrid. The client's marketing director and their e-commerce lead join; the agency brings the account lead, the project manager and the creative lead. > **Purpose:** launch the new site and the first campaign before the client's spring collection, with the client's team able to run the site themselves afterwards. :br**1. Why this project, and for whom** — Elena, client marketing director — 10 min — *information*:br**2. Done means: site live in two languages by 1 March, campaign live by 15 March, the client's team trained to publish; judged by Elena against the statement of work** — Claire, project manager — 15 min — *decision*:br**3. Workstreams: content and structure (Elena's team), design and build (Julien), campaign (Claire), training and hand-over (Julien)** — 15 min — *decision*:br**4. How we work: one shared channel for both sides; weekly on Thursday 14:00; recap to both sides the same day; changes to scope go to Elena and the account lead, not into the channel as a request** — 10 min — *decision*:br**5. Risks: product photography not ready until January, two approvers on the client side, the payment provider's integration** — everyone — 5 min — *discussion*:br**6. Outcomes and first actions** — 5 min :br**Leaves behind:** a definition of done the client said yes to in the room, one channel both sides read, and the first weekly in the calendar. The shape of the two is the same; what differs is who reads the purpose sentence and who judges done. The remaining items of a project's life — the weekly, the stand-up, the review — have their own agendas in [meeting agenda examples](https://intermind.com/blog/meeting-agenda-examples); the anatomy of the format is in the [meeting agenda template](https://intermind.com/blog/meeting-agenda-template) guide. ## Client kickoff: what changes when the other side is the client Three things change when the kickoff is with a new client rather than with your own team. **The client reads the purpose sentence, and the client judges done.** In an internal kickoff the sponsor says what the result is; in a client kickoff the client does, in their words, and the team writes those words down rather than translating them into the agency's. The definition of done is read against the statement of work, line by line, in the room — the kickoff is the last cheap moment to find that the client expected three languages where the proposal said two. **Two sides, one record.** A client kickoff produces one agreement, not two sets of notes. The recap goes to both sides the same day, from the same text; a client who receives a different summary than the team has not been in the same meeting. The same holds for the channel: one place both sides read, where the agency's question and the client's answer sit next to each other, rather than an internal channel and an email thread with the client. **The client's people are not your organization.** They have their own tools, their own accounts, often their own language. Whatever you use for the kickoff, the question to answer before sending the link is what the client's decision-maker needs to join from a phone between two other meetings — an account, an app, a licence — and what they will have afterwards: the record, or only their memory of it. ## Where the kickoff's record lives in the tools you already use Each major platform has a place for the agenda and a form of record after the meeting, and each stops at a different point for the person outside the organization. Documented behaviour only, from the vendors' own pages; each cell names the month its fact was checked. | Platform | Where the agenda and the notes are written | What the record is afterwards, and what an outside attendee gets | | -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | *Add an agenda* in the meeting's Details when scheduling, or *Notes* in the meeting controls during the call; the notes are a Loop component that any attendee or organizer can edit, with tasks assigned by tagging people (checked October 2026) | The notes are saved automatically and reachable from the Teams calendar and the meeting recap; external attendees cannot access or edit them (checked October 2026). The recap — recording, transcript, shared files, notes, agenda and follow-up tasks — is available after meetings that were recorded or transcribed; the AI parts require Teams Premium or a Microsoft 365 Copilot licence, and the recap is generated in the language the meeting was held in (checked August 2026) | | **Zoom Workplace** | AI Companion can draft the agenda when the meeting is scheduled, from the title, a prompt or previous documents (checked October 2026) | Meeting summary with AI Companion — quick recap, summary, next steps — on paid Zoom Workplace plans; sent by email, listed on the Summaries page and postable to the meeting's group chat in Team Chat. Participants receive it when the host chose to share it, only the host can edit it, and unauthenticated users do not receive the email. The documentation does not state that a summary can be produced in a different language per participant (checked August 2026) | | **Google Workspace** | The Calendar event's description, or a Google Doc linked from it; on eligible Workspace editions and Google AI plans, *Take notes for me* is switched on in Calendar when the event is created (checked October 2026) | The notes arrive as a Google Doc after the meeting, shared with all guests, organization guests or hosts only, per the setting; the feature supports one language at a time — multiple languages spoken in the same meeting are not supported (checked October 2026) | | **Slack** | A canvas from the meeting-agenda template, shared in the channel, with sections for objectives, time allocations, next steps and action items with due dates; a huddle in the channel has "a dedicated message thread to share notes, links, and files" (checked October 2026) | The canvas stays in the channel as a document; what was said in the call is not in it unless someone types it (checked October 2026) | Two things are the same across the four. The record of the kickoff is one document or one summary, in the language the room used; and for the person outside the organization, each page cited draws a line — the notes an external attendee cannot open, the email an unauthenticated participant does not get, the document shared with hosts only. Where that is fine, the table is the whole answer and any of the four will do. Where the project has two sides, the next section is one way the job gets done. ## How the kickoff becomes the channel InterMIND is a communication space where a meeting lives in a channel, so the kickoff has an obvious continuation: the channel it was held in is the project. The channel's chat is kept between sessions, its meeting link is permanent, and the weekly is set once, in Google Calendar or Outlook, on an event that carries that link — the same room opens every Tuesday, with the kickoff's agenda one scroll up. A channel created from the calendar event takes its title from the event. The agenda is a note in the channel's chat, posted the day before, with the pre-reads next to it — a PDF or a Word file dropped into the channel, or a Google Doc or OneDrive document linked from it. During the kickoff, the facilitator puts the note on everyone's screen with **Share to conference**: it opens next to the video tiles for every participant, the facilitator edits it live as the room decides — done means this, by this date, this owner — and each participant reads it in their own language, with the original a toggle away. The brief itself can go on every screen the same way, late joiners included. The whole space works like that: a message typed in French is read in Spanish by the client's e-commerce lead, in Romanian by the integrator's developer and in French by the sender, as are the files, the notes and the recap — the chat, the recap and the history, not one meeting at a time. When the kickoff ends, the recap is written from the meeting itself: a summary, the points marked agreed, open or disputed, the action items with owners, each line keeping its timestamp. It arrives by email, as a message in the channel and as a link in the calendar event, and every signed-in member reads it in their own language — the record is translated per reader, not written once in the language the room happened to use. Any member can edit it, every edit keeps author and revision history, and the channel keeps the recap of every past session, so on the first weekly the kickoff's definition of done is one click away, and in month four the new designer reads the whole project from its first hour. The host can add a recap copy to any address — the client's project mailbox, a CRM inbox — so the outcomes reach the system of record without anyone forwarding anything. In an organization with team status pages on, the open action items of earlier sessions are judged when the next recap is written: an item someone reported finished is marked done, an item discussed but not finished is marked not done with the reason in the words of the meeting, an item nobody brought up stays open — the verdicts on the organization's status page rather than in the recap — and at the start of the next session Mia names the open items and their owners, so the kickoff's first three actions are spoken about at the first weekly rather than lost. Team status pages are a preview feature: an organization's admin switches them on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). The client's decision-maker who is in the kickoff only joins by link, without an account and at no cost — from a phone, in the browser, by typing a name — and the host admits them. They hear the meeting live in their own language and read the agenda on their screen in it. There is no record for a guest afterwards: a guest of one meeting gets nothing after it ends, and the chat of a call held outside a channel is wiped when the call ends. The client's people who should read the project are added to the channel by email instead, onto a free account; from then on they read the whole channel — every message, every file, every recap — in their own language, and every call from the channel is theirs to join. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing) — joined a meeting, wrote in a chat, asked Mia; members who go quiet keep their access at no cost, and the client's people in the channel are not counted. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. The kickoff as a craft survives every tool: somebody still has to get a sponsor to say what done means and a name next to each workstream. What does not have to survive is the second project — the one where the record is rewritten by hand, in one language, for a client who reads another. ## FAQ **What is a kick off meeting?** A kick off meeting is the first meeting of a project, held once at its start, where everyone who will do the work — and the sponsor or the client — agree what the project is for, what "done" means and by when, who owns each workstream, how the project will communicate, and what risks they already see. It produces the project's first record; the planning that came before it was done by fewer people, and the kickoff is where the whole team hears one version and can correct it. **What is the purpose of a kickoff meeting?** To put one shared understanding in the room before any work starts. Five outcomes: a purpose sentence naming who the result is for; a definition of done with a date and a judge; a named owner per workstream; the way the project communicates — channel, weekly, recap, escalation; and the risks each person already sees, with the first actions dated. A kickoff that produces these five has done its job; one that presents the plan and takes questions has produced a deck. **How do you run a kickoff meeting?** Send the purpose sentence and the draft definition of done with the invitation, with the pre-reads posted where the project will live. In the meeting, let the sponsor or the client read the purpose aloud; decide done and its date in front of everyone; leave each workstream only when a name is next to it; decide how the project communicates rather than describing it; run the risks as a one-sentence round; and spend the last five minutes reading the outcomes back. Publish the recap the same day, in the project's channel, and create the weekly before the day ends. **What should be included in a kickoff meeting agenda?** Six items in an hour: why this project and for whom (10 minutes, the sponsor or client); what done means and the date it is judged on (15, decision); workstreams and owners (15, decision); how we work — channel, weekly, recap, escalation (10, decision); risks each person already sees (5, a round); outcomes and first actions, read back (5). The template above is this list with the placeholders; the two examples are it filled in. **How long should a kickoff meeting be?** Sixty minutes for most projects, forty-five for a small one with three workstreams or fewer. The two decision items — done and owners — take half the hour; everything else is shorter than people expect once the pre-reads were actually read. A kickoff that needs two hours is usually missing its planning meeting: the room is estimating and sequencing, which is a different meeting with fewer people. **Who should attend a kickoff meeting?** Everyone who will own a workstream, the sponsor, and — for a client project — the client's decision-maker, not only their day-to-day contact. The people who need to hear the agreement but will not own anything get the recap; a kickoff with twenty people in it is an announcement. One test per name on the invitation: will this person be asked, in the first weekly, where something stands? If not, they read the recap. **What is the difference between a kickoff meeting and a project planning meeting?** The planning meeting produces the plan — scope, phases, estimates, a draft schedule — and is held by the lead with the people who estimate. The kickoff takes that plan to everyone who will do the work and to the sponsor or client, and produces agreement: the same purpose, the same definition of done, named owners. Planning comes first; a kickoff held without it spends the hour planning in a room too large for it. **What is a client kickoff meeting?** The kickoff held with a new client at the start of an engagement. It follows the same agenda, with three differences: the client reads the purpose sentence and judges done, against the statement of work, in the room; both sides get one recap from the same text the same day; and the client's people join from their own tools and often their own language, so the choice of where the kickoff is held decides what the client can open afterwards — the notes, the summary, the channel — and what they cannot. **Is it "kick off meeting", "kickoff meeting" or "kick-off meeting"?** All three name the same meeting; the spelling varies by region and by house style, and the search box treats them as one query. Use one spelling in your own documents and do not worry about it in anyone else's. --- *Sources: [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Zoom — Generating meeting agenda with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0081706){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Use huddles in Slack](https://slack.com/help/articles/4402059015315-Use-huddles-in-Slack){rel=""nofollow""}; [Slack — Meeting agenda template](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Vendors change plans, features and language lists over time; check their pages for the current state. Each table cell names the month its fact was checked — the earliest checked August 2026, the latest checked October 2026.* # Real-time meeting translation: how it works, and how to evaluate one - **A live meeting where everyone speaks, types and listens in their own language,** translated as it happens: voice, chat, notes and documents, not a transcript next morning. - **Notetakers, caption plugins and pasted-text models are not it.** Judge a tool on per-pair quality on real traffic, latency on a real call, language counts per surface and where the data runs. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes and documents, quality published per pair. Guests join free by link, no account; you pay only for active members. **Real-time meeting translation** is a live meeting where each participant speaks, types, and listens in their own language — and the platform translates between them as the meeting happens, not afterwards. No human interpreter in a booth, no "let's just switch to English," no transcript you read the next morning. The category is full of tools that sound like they do this and don't. AI notetakers record and summarise. Caption add-ons subtitle the speaker. General-purpose models translate a block of text when you paste it in. Real-time meeting translation is a narrower, harder thing: every word, every chat message, every shared note, rendered into each listener's language fast enough that the conversation keeps flowing. This is the foundational guide to that category — what the term actually means, what happens under the hood, and the questions worth asking before you sign anything. It's the hub the rest of our writing branches off, so where a topic deserves its own deep dive, we link to it. --- ## What "real-time" actually rules out The hard constraint is latency. A live multilingual conversation works only if the translation arrives fast enough that people don't start talking over it. Once the translation lags far enough that people wait for it, the meeting drifts — participants hesitate, double back, and eventually default to a shared second language. So real-time meeting translation has a live budget that quietly disqualifies most of the tools marketed near it: - **AI notetakers** (think [Fireflies](https://intermind.com/compare/fireflies) or [Otter](https://intermind.com/compare/otter)) are built to transcribe and summarise a meeting — usually English-first, and most usefully *after* it ends. They answer "what did we decide." They do not translate speech live so a German speaker and a Japanese speaker each hear the other in their own language. That's a different job with a different clock. - **General-purpose LLM translation** is good prose translation with no latency contract. Fine for a document; wrong tool for a live audio channel where the model must answer while the speaker is still talking and can't pause to "think." - **Caption/subtitle plugins** show text of what the speaker said, often in one target language for everyone. That's a captioning feature, not per-participant translation. If a tool can't translate *voice* live, per listener, into each listener's chosen language, it isn't doing real-time meeting translation — whatever the homepage says. --- ## The four things "translation" means in a meeting The second trap is treating translation as one feature. A live meeting actually has at least four translation jobs running at once, and they pull in incompatible directions: 1. **Voice** — audio in, translated audio out while the speaker is still talking, every viewer in their own language. Constraint: latency. 2. **Chat** — short messages translated as they're sent, with edits that read like edits, not re-translations. 3. **Shared notes** — collaborative typing translated character-by-character, with lists, headings and checkboxes surviving intact. 4. **Documents** — a 40-page PDF dropped into chat, translated as a *file* with its tables, fonts and page breaks preserved. Constraint: fidelity, not speed. No single engine is good at all four — the latency budget that makes voice work is the opposite of the fidelity budget a document needs. Any honest platform runs several pipelines behind one language picker. We pulled ours apart in detail in [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines); the short version is that "one engine for everything" is a marketing simplification, not an architecture. --- ## How a real-time voice pipeline actually works Trace one sentence from a French speaker to a German, a Brazilian and a Japanese listener: 1. **Speech recognition runs on our own engine, on the media server that carries the call.** The browser sends audio over WebRTC to the Mind API, hosted at OVH in France; recognition happens there, word by word, and the source transcript exists before the sentence ends. No separate speech vendor, no extra hop before translation can start. 2. **Translation runs inside the same engine, per target language present in the room.** A language is translated once the first listener in it asks for a translated stream: if three people picked German, they share one German translation; if nobody picked Arabic, nothing is translated into Arabic. A four-language meeting costs what four languages cost — not forty. 3. **Each listener gets their own synthesised audio track**, mixed against the original speaker's video. Two people in the same physical room can wear headphones and hear different languages off the same meeting. The part that matters for procurement: **the engine doing the translating is its own thing, on its own infrastructure** — not a general-purpose third-party model the platform is quietly reselling. The live budget rules those out, and so does the data-residency story for anyone regulated. (Where every byte of a meeting physically runs is its own question; we mapped it vendor-by-vendor in [*Where one InterMIND meeting actually runs*](https://intermind.com/blog/where-one-intermind-meeting-actually-runs).) --- ## How to evaluate a real-time meeting translation tool Most of this category competes on a single inflated number — "200+ languages," "99% accurate." Those tell you nothing about the meeting you're about to run. Here's what actually separates one tool from another. ### 1. Per-pair quality on real traffic, not an aggregate "200 languages" means a model emits text in 200 languages. Quality ranges from production-grade on major pairs to unusable on rare ones. Ask for **per-language-pair quality, measured on real traffic, with the distribution** — median, worst 10%, sample size — not one averaged headline. We argued why the whole category dodges this in [*Why translation-quality marketing is broken*](https://intermind.com/blog/why-translation-quality-marketing-is-broken), and we publish our own numbers at [`/benchmark`](https://intermind.com/benchmark): every live pair, every month, scored against [FLORES-200](https://github.com/facebookresearch/flores){rel=""nofollow""} by a [named judge](https://intermind.com/benchmark/methodology). You don't have to take a vendor's word — including ours. And when a meeting runs on one specific pair, check that pair, not the average — the [Hindi to English voice translator](https://intermind.com/blog/hindi-to-english-voice-translator) guide walks through doing exactly that for Hindi ↔ English before relying on it. ### 2. Latency you can feel, not a spec-sheet number Voice that arrives while the speaker is still talking is the threshold for a conversation that flows. Test it on a real call with real cross-talk, not a demo script. ### 3. Honest language counts, per surface A platform's voice languages, text languages and document languages are rarely the same set, and a single number hides that. Ours, for example: **23 languages live on voice, chat and notes; 30 on documents.** A French participant can request a contract PDF in Estonian even if they can't *listen* to the meeting in Estonian — and we flag that in the picker rather than smoothing it into one figure. The reasoning is in [*How many languages do you support?*](https://intermind.com/blog/how-many-languages-do-you-support). ### 4. Where the data runs For regulated buyers, *where* the meeting is processed is part of the spec, not a footnote. Ask which vendors touch the audio, where they execute, and which are merely reselling a US model. Our full runtime map — every hop, including the AI gateway the organization selects and which of its vendors are US companies, named plainly — is in [*Where one InterMIND meeting actually runs*](https://intermind.com/blog/where-one-intermind-meeting-actually-runs) and [*Multilingual compliance meetings*](https://intermind.com/blog/multilingual-compliance-meetings). ### 5. Live translation vs. a notetaker Be clear which problem you're solving. If you need a record and a summary, an [AI notetaker](https://intermind.com/compare) is the right buy. If you need people who don't share a language to actually *talk*, you need live translation. Some teams want both; few tools do both well. ### 6. What your current platform already does Before buying anything, know exactly what's built into the tool you already pay for — and where it stops. We keep honest, sourced how-tos for each: [Zoom](https://intermind.com/blog/zoom-live-translation), [Microsoft Teams](https://intermind.com/blog/teams-live-translation), and [Google Meet](https://intermind.com/blog/google-meet-live-translation). Each one ends at the same place: captions or a fenced bilingual feature, not a room where everyone hears their own language. --- ## Where InterMIND fits We built InterMIND for the live-translation job specifically — and it starts with one person: the host opens the room and sends the link; the others join free, without an account, each in their own language. [Real-time voice, chat, notes and documents](https://intermind.com/features/realtime-translation) across **23 languages**, on our own engine hosted in the EU, with the translation quality published openly instead of asserted. It runs in the browser and in the apps; the room size follows the host's plan ([pricing](https://intermind.com/pricing)) — enough for [simultaneous interpretation at conferences and webinars](https://intermind.com/features/simultaneous-interpretation), not just calls — with cloud and local recording. It is not the best tool for "transcribe and summarise my English standup" — that's what notetakers are for, and we say so on the comparison pages rather than pretending otherwise: - [InterMIND vs. Fireflies.ai](https://intermind.com/compare/fireflies) — notetaker vs. live multilingual meeting - [InterMIND vs. Otter.ai](https://intermind.com/compare/otter) — same axis, honestly compared - [All platform comparisons](https://intermind.com/compare) If literal, word-for-word fluency is your worry, [*The false-fluency trap*](https://intermind.com/blog/false-fluency-trap) is the one to read — fast translation that's confidently wrong is worse than slow translation that's right. --- ## Try it yourself - **[Try the live demo](https://intermind.com/demo)** — hear the production voice pipeline translate a real meeting live, in any of the 23 live languages — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month quality on real traffic. Every pair in the picker, strong or weak, deep-linkable by URL. - **[Read the methodology](https://intermind.com/benchmark/methodology)** — exactly what the numbers measure, what they don't, and who the judge is. Real-time meeting translation is a narrow promise: everyone in their own language, live, fast enough to keep talking. The honest way to evaluate it is to stop reading homepages and start measuring. That's what the links above are for. --- ## FAQ **What is real-time meeting translation?** A live meeting where each participant speaks, types, and listens in their own language, and the platform translates between them as the meeting happens — voice, chat, notes, and documents — fast enough that the conversation keeps flowing. **How is it different from an AI notetaker like Otter or Fireflies?** A notetaker transcribes and summarises a meeting, mostly after it ends. Real-time meeting translation changes what participants *hear during* the call: a German speaker and a Japanese speaker each hear the other in their own language, live. **What latency does live voice translation need?** Fast enough that nobody waits for it: once translated speech lags behind the speaker, people hesitate and fall back to a shared language. The practical test is a real call with cross-talk, not a number on a page. **How do you evaluate translation quality claims?** Ask for per-language-pair quality measured on real traffic — median, worst 10%, sample size — not one averaged headline. We publish ours monthly at [`/benchmark`](https://intermind.com/benchmark). — The Mind.com Team --- *Sources: [Otter — supported languages](https://help.otter.ai/hc/en-us/articles/360047247414-Supported-languages){rel=""nofollow""}, [Fireflies — supported languages](https://guide.fireflies.ai/articles/2973706448-learn-about-fireflies-supported-languages){rel=""nofollow""}, [FLORES-200](https://github.com/facebookresearch/flores){rel=""nofollow""}, checked August 2026. Vendors change plans and language lists over time — check their pages for the current state.* # Recurring meeting: how to set it up in Google Calendar and Outlook, and how to keep its history in one place (2026) - **A recurring meeting is one calendar event that repeats.** Set the pattern, slot and end once; every occurrence inherits the invitees and the link. - **The series is the unit, the occurrence is the exception.** Change one date, this and following, or all; where the history goes depends on the link. - **InterMIND keeps the whole meeting in each member's language,** every session in one channel, next to Google Calendar or Outlook rather than instead of them. Guests join free by link, no account; you pay only for active members. A recurring meeting is a meeting that happens on a fixed pattern — every Monday at ten, every other Thursday, the first Tuesday of the month — and lives in the calendar as one event with a repeat rule rather than as a row of separate bookings. The calendar does the arithmetic: it creates the occurrences, invites the same people to each, and lets the organizer change one date or the whole series in one place. The weekly team meeting, the one-on-one, the stand-up, the monthly client call and the quarterly review are all recurring meetings; the thing they have in common is not the topic but the fact that nobody books them twice. This guide is the mechanics first — what a recurring meeting is and what a series is, the five settings every one needs, how recurrence is set in Google Calendar and Outlook and how a single occurrence is moved without disturbing the rest — then a series card you can copy, and the part most recurrence guides leave out: what each occurrence leaves behind and where it goes. A recurring meeting is a series, and a series is only as useful as its memory. How often each meeting should repeat is a separate question, answered in [meeting cadence](https://intermind.com/blog/meeting-cadence); this guide assumes the rhythm is chosen and shows how to put it on the calendar so that it stays there. ## What a recurring meeting is — and what it isn't Three calendar objects get called "the meeting", and the difference decides what happens when you edit one: | | What it is | Created | Changed | | ---------------------------------- | ---------------------------------------------------------------- | ------------------ | -------------------------------------------------------------------------- | | **One-off meeting** | A single event with a date, invitees and a link | Each time, by hand | On its own | | **Recurring meeting (the series)** | One event with a repeat rule: pattern, day and hour, length, end | Once | As a whole — new invitee, new hour, new link for every occurrence at once | | **Occurrence** | One instance the rule produced — this Monday's weekly | By the rule | As an exception: moved, shortened or cancelled without touching the series | Two consequences follow. A change made to the series reaches every future occurrence, so the series is where the invitee list, the hour and the link are maintained. A change made to one occurrence is an exception the calendar remembers alongside the rule, so the holiday Monday is moved to Tuesday once, and the following Monday is back on schedule without anyone doing anything. A recurring meeting is not the same as "a meeting we have often". A weekly that is booked each week by whoever remembers has a habit but no series: no fixed slot to plan around, no one place where the invitees are kept, and a different link each time, which means a different chat and a different set of notes each time. Making it recurring is a five-minute job and it removes all three problems at once. ## The five settings every recurring meeting needs Whatever the calendar, a recurrence rule is five decisions. Most arguments about a recurring meeting are about one of them left at its default. 1. **The pattern.** Daily, weekly, every two weeks, monthly — or a custom rule: every third Wednesday, the last Friday of the month, weekdays only. The pattern follows how long the meeting's questions can wait, which is the cadence question; the calendar only needs the answer. 2. **The day and the hour.** Fixed, and chosen for the people who must be there, across their time zones. A meeting at nine in Madrid is at ten in Bucharest and at four in the morning in Bogotá; the recurrence rule repeats that mistake every week until someone edits the series. 3. **The length.** Set on the series, not stretched occurrence by occurrence. Thirty minutes that run to forty-five every week are a sixty-minute meeting that is lying about itself. 4. **The end.** Three options exist in every calendar: no end, end after a number of occurrences, end on a date. A series with no end is the default and the most common mistake — it outlives the project, the team and sometimes the company. Put the end on the series: the project's close date, the quarter's end, or a date three months out at which the series is reviewed and either renewed or deleted. 5. **The link.** One meeting link on the series, inherited by every occurrence. This is the setting that decides where the history goes: a link that opens the same room each time keeps that room's chat, files and notes together; a link generated per occurrence scatters them. Whether the room behind the link keeps anything from one occurrence to the next is a property of the meeting tool, and the section on tools below is about exactly that. What the rule should not carry: the agenda. An agenda is per occurrence — items, owners, minutes — and it has [its own template](https://intermind.com/blog/meeting-agenda-template). The series carries the standing purpose in one sentence ("unblock this week's work and decide what we don't do"); the agenda carries what this Monday is for. ## How to set up a recurring meeting in Google Calendar and Outlook Both calendars follow the same shape, and the shape is what to remember; the labels differ by version and are on the vendors' help pages. 1. **Create the event as usual.** Title, date and time of the first occurrence, the people. For a meeting that will run in a video tool, put the meeting link in the event now — in the location or the description, or through the tool's calendar button if it has one — so that every occurrence inherits it. 2. **Open the repeat field.** It sits with the date and time and reads as "does not repeat" by default. The dropdown offers the common patterns — daily, weekly on the chosen weekday, monthly on the same day, yearly, every weekday — and a custom option. 3. **Choose the pattern, or build it.** The custom option asks for three things: the interval (every one, two or three weeks), the days (Tuesday and Thursday, or the second Monday), and the end — never, after a number of occurrences, or on a date. Set the end. 4. **Save and send.** The invitation goes out once and covers the series; invitees accept the series, and every occurrence appears in their calendars. To change the series — a new hour, a new member, a new link — open any occurrence and, when the calendar asks, choose the whole series: the change reaches every future occurrence. To change one occurrence — move this Monday to Tuesday, shorten the one before the holiday, cancel the one during the offsite — choose this occurrence only: the calendar records the exception and leaves the rule alone. The third choice, this and all following occurrences, is the one to use when the slot changes permanently from a date onward: the past stays as it was, the future follows the new rule. To end a series without losing its past, do not delete it: deleting the series removes the past occurrences from the calendar too. Set the end date to the last occurrence that should happen, or edit this and following occurrences from the first one that should not. The past stays in the calendar, and so does whatever those occurrences linked to. In InterMIND, recurrence is set in exactly this way, because the calendar is where it belongs: connect Google Calendar or Outlook once in Integrations, click the calendar half of **New meeting** or the calendar button on any meeting's row, and the calendar opens with the event pre-filled — the title, the join link and the recap link. Add the people, pick the first date and the recurrence, send. The meeting row on the Meetings page follows the dates from the calendar, including the exceptions. The one-click flow in detail, including a meeting that already met and is made recurring from its row, is in [how to schedule a meeting from Google Calendar or Outlook](https://intermind.com/blog/how-to-schedule-a-meeting-from-google-calendar-or-outlook). ## A series card you can copy One block per recurring meeting, kept where the team talks — in the channel's notes, a canvas or a pinned message — so that a new member finds the rule in words, not only in the calendar: > **\[Team] — \[Meeting name]** · series created \[date] · review by \[date] :br**Purpose:** \[one sentence — what every occurrence produces] :br**Pattern:** \[weekly / every two weeks / monthly] on \[day] at \[time, with the time zone] — \[minutes] :br**Ends:** \[date, or "reviewed on" date] :br**Link:** \[one link, the same for every occurrence] :br**Owner:** \[name — changes the series, cancels an occurrence, chairs by default] :br**Who:** \[the people on the series] · **Optional:** \[people invited to single occurrences] :br**Each occurrence leaves behind:** \[decisions, open items, the parking lot — where they are posted and by when] :br**History lives in:** \[the channel, the document, the folder — one address] :br**Exceptions this quarter:** \[holiday dates moved or cancelled, decided now] The last two lines are the ones most series lack and the ones that cost the most: a series with no agreed address for its history is a series whose history is in whoever took notes, and a series with no exceptions decided in advance is cancelled on the morning of the holiday, when nobody can plan around it. ### Four series, filled in > **Weekly team meeting** — weekly, Monday 10:00 CET, 30 min — ends at the quarter's end, reviewed at the quarterly :br > Leaves behind: decisions and open items, posted in the team channel the same day. > **One-on-one** — every two weeks, Wednesday 14:00 CET, 30 min — no end, reviewed when the report's role changes :br > Leaves behind: next steps with names and dates, visible to both. The same link every time, so both sides find the history at one address. > **Client progress call** — weekly during delivery, Thursday 16:00 CET, 45 min — ends on the project's close date :br > Leaves behind: who sends what by when, in the client's channel; the client's people are invited to the series, their occasional colleagues to single occurrences. > **Monthly all-hands** — first Tuesday, 12:00 CET, 45 min — no end, reviewed at the quarterly :br > Leaves behind: the numbers, one decision explained, every question answered or dated. The agendas inside each of these — the items, owners and minutes — are in [meeting agenda examples](https://intermind.com/blog/meeting-agenda-examples); the stand-up, the [one-on-one](https://intermind.com/blog/one-on-one-meeting-template) and the [all-hands](https://intermind.com/blog/all-hands-meeting) have their own guides. ## Where a recurring meeting keeps its history in the tools you already use The calendar keeps the rule. What each occurrence produces — notes, a recap, the chat — is kept wherever the meeting tool behind the link puts it, and that differs by tool. Documented behaviour only, from the vendors' own pages; each cell names the month its fact was checked. | Platform | How the series is scheduled | What one occurrence leaves behind | Where it goes, and for whom | | -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Microsoft Teams** | In the Teams calendar: "Select a timeslot on the calendar or select New. Add meeting details and attendees. Turn on the Teams meeting toggle. Select Save"; "when you schedule a meeting in Teams, it'll automatically appear in your Outlook calendar, and vice versa". The scheduling page does not state how a recurring meeting is set up (checked September 2026) | *Notes* in the meeting controls, or *Add an agenda* in the meeting's Details — a Loop component that any attendee or organizer can edit, with tasks assigned by tagging people (checked October 2026). A recap — recording, transcript, shared files, notes, agenda and follow-up tasks — after meetings that were recorded or transcribed; the AI parts require Teams Premium or a Microsoft 365 Copilot license; "not currently available for ad-hoc events" (checked August 2026) | The notes are saved automatically and reachable from the Teams calendar and the meeting recap; external attendees cannot access or edit them (checked October 2026). The recap is generated in the language the meeting was held in (checked August 2026) | | **Zoom Workplace** | A scheduled meeting; AI Companion can generate the agenda when the meeting is scheduled, from the title, a prompt or previous documents (checked October 2026) | A meeting summary with AI Companion — quick recap, summary, next steps — on paid Zoom Workplace plans (checked August 2026) | Sent by email, listed on the Summaries page and postable to the meeting's group chat in Team Chat; participants receive it when the host chose to share it, only the host can edit it, and unauthenticated users do not receive the email. The documentation does not state that a summary can be produced in a different language per participant (checked August 2026) | | **Google Workspace** | A Calendar event with a Meet link; "Recurring meetings keep the same settings as the first meeting" (checked September 2026). On eligible Workspace editions and Google AI plans, *Take notes for me* is switched on in Calendar when the event is created (checked October 2026) | A Google Doc with summary, decisions and next steps, when *Take notes for me* was on (checked October 2026) | The Doc is emailed to the organizer and attached to the event, shared with all guests, organization guests or hosts only, per the setting; "this feature supports one language at a time" (checked October 2026) | | **Slack** | A huddle in the team channel, with "a dedicated message thread to share notes, links, and files" (checked October 2026) | A canvas from the meeting-agenda template, with sections for objectives, time allocations, next steps and action items with due dates (checked October 2026) | The canvas stays in the channel; what was said in the huddle is not in it unless someone types it (checked October 2026) | Read across the row for the tool your team uses, and the pattern is the same in each: the series is one event, and each occurrence leaves one document or one summary, in the language it was written or held in. The thread between occurrences — last time's open items at the start of this time — is a person's job: someone opens the previous document and reads it into the room. Where that is fine, any of the four will do and the table is the whole answer. The next section is one way the job gets done where the series needs a memory of its own, read by members who do not all read the same language. ## How a series keeps its history in a channel InterMIND is a communication space where a recurring meeting lives in a channel. The meeting link is permanent, so the room is the same every occurrence; the recurrence is set once in Google Calendar or Outlook, on an event the product pre-fills with the join link and the recap link. Whatever the pattern, the channel keeps the whole series in one place and **in each member's language**: the chat is translated per reader — each member types in their own language and reads the others in theirs, with the original one toggle away — and the channel keeps the recap of every past session, not only the latest, so the weekly of three weeks ago is a switch between sessions on the recap page rather than a question to the room. An ad-hoc meeting by link keeps only its latest recap, and its chat is wiped when the call ends; a series belongs in a channel. The series card above is a note in the channel, where a new member finds it on day one. During a session, the card or the previous session's recap goes on everyone's screen next to the video tiles with **Share to conference**: the sharer edits it live while the room watches, and every participant reads it in their own language, with the original a toggle away. The same works for the agenda of this occurrence, drafted in the channel the day before. When the call ends, the recap is written from the meeting itself — a summary, the action items with owners — and arrives by email to each signed-in participant, as a message in the channel and as a link in the calendar event, each member reading it in their own language rather than the one the room happened to use. Any member can edit it, every edit keeps author and revision history. In an organization with team status pages on, the open action items of earlier sessions are judged when the next recap is written: an item someone reported finished is marked done, an item discussed but not finished is marked not done with the reason in the words of the meeting, an item nobody brought up stays open — the verdicts on the organization's status page rather than in the recap — and at the start of the next session Mia names the open items and their owners, so last time's list is the first thing spoken about rather than the first thing forgotten. Team status pages are a preview feature: an organization's admin switches them on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). A series is members-only. A colleague or a client who belongs on the series is added by email invitation onto a free account and reads the channel in their language. Someone who is needed for one occurrence only — a supplier for one review, a candidate for one call — joins an ad-hoc meeting by link, from a phone, without an account and at no cost, hears the meeting live in their own language and gets nothing afterwards: the account is free, and it is what makes the record reachable. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing) — joined a meeting, wrote in a chat, asked Mia; a member on leave for a month keeps access and costs nothing that month, and the series they come back to is in the channel, with every session's recap. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. A recurring meeting survives every tool: somebody still has to choose the pattern, hold the slot, set the end and decide the exceptions before the holiday. What does not have to survive is the second job — finding last time's document, reading it into the room, and typing this time's up by hand, in one language, for people who read others. ## FAQ **What is a recurring meeting?** A recurring meeting is a meeting scheduled as one calendar event with a repeat rule — weekly, every two weeks, monthly, or a custom pattern — so that the calendar creates each occurrence, invites the same people and carries the same link every time. The series is maintained as a whole; a single occurrence can be moved or cancelled as an exception without changing the rule. **How do I set up a recurring meeting in Outlook?** Create the event with its first date, time and invitees, open the recurrence option on the event form, choose the pattern — daily, weekly, monthly or a custom rule with an interval and days — and set how the series ends: on a date, after a number of occurrences, or never. Put the meeting link in the event before saving so every occurrence inherits it, then send; the invitation covers the series. In InterMIND, the calendar half of **New meeting** opens Outlook with the title, the join link and the recap link already in the event, and the recurrence is set there. **How do I make a meeting recurring in Google Calendar?** Open the event, change the repeat field next to the date from "does not repeat" to a pattern or to a custom rule, set the interval, the days and the end, and save. If the meeting already has a link, keep it in the event so that every occurrence opens the same room. From InterMIND, click the calendar button on the meeting's row: Google Calendar opens with the event pre-filled, and you pick the first date and the recurrence; a meeting that has already met can be made recurring the same way without losing its chat and recaps. **How do I change one occurrence of a recurring meeting without changing the series?** Open that occurrence and, when the calendar asks which events to change, choose this event only. The calendar records the exception — a new time, a shorter length, a cancellation — and leaves the rule alone, so the next occurrence is back on the regular slot. Choose this and following events when the slot changes permanently from a date onward, and all events when the change applies to the whole series. **How do I end a recurring meeting without deleting the past occurrences?** Do not delete the series: that removes past occurrences from the calendar as well. Edit the series and set its end date to the last occurrence that should take place, or open the first occurrence that should not happen and cancel this and following events. The past stays in the calendar with whatever each occurrence linked to. **Does a recurring meeting keep the same link for every occurrence?** In the calendar, the series carries one link and every occurrence inherits it, unless the meeting tool generates a new one per occurrence or someone edits an occurrence's link as an exception. Whether the room behind that link keeps anything from one occurrence to the next is a property of the meeting tool, not the calendar: the table in this guide lists what Teams, Zoom, Google Workspace and Slack leave behind per occurrence, and a channel in InterMIND keeps the chat and every session's recap at the same address. **What is the difference between a recurring meeting and a meeting series?** They are the same object seen from two sides. "Recurring meeting" is the meeting as the team experiences it — the weekly, the stand-up. "Series" is the calendar's name for the event with the repeat rule, as opposed to an "occurrence", one instance the rule produced. Changes are made either to the series or to an occurrence, which is why the calendar asks which one you mean. --- *Sources: [Microsoft — Schedule a meeting in Microsoft Teams](https://support.microsoft.com/en-us/office/schedule-a-meeting-in-microsoft-teams-943507a9-8583-4c58-b5d2-8ec8265e04e5){rel=""nofollow""}; [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""}; [Zoom — Generating meeting agenda with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0081706){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Google Meet — Start or schedule a Google Meet video meeting](https://support.google.com/meet/answer/9302870){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Use huddles in Slack](https://slack.com/help/articles/4402059015315-Use-huddles-in-Slack){rel=""nofollow""}; [Slack — Meeting agenda template](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Each table cell names the month its fact was checked — the earliest checked August 2026, the latest checked October 2026. The steps for setting recurrence in Google Calendar and Outlook describe the shape both calendars share; the exact labels differ by version and are on the vendors' help pages. Vendors change plans, features and language lists over time; check their pages for the current state.* # Remote work policy: template, sections, example — and the one channel the policy lives in (2026) - **A remote work policy is the written rules for working away from the office:** who may, from where, when they are reachable, how the team talks, who pays, how data stays safe. - **A policy nobody can find is a rumour.** In Teams, Zoom, Google Workspace and Slack it is a document in one language. - **InterMIND keeps the policy and every question about it in each member's language,** in one channel next to those tools. Guests join free by link, no account; you pay only for active members. A remote work policy is the written set of rules an organization applies to work done away from its office: who is allowed to work remotely and how often, from which places and countries, during which hours they must be reachable, how the team communicates and meets, who pays for the desk, the laptop and the connection, how company data is handled outside the building, and how the policy itself is changed. It is a short document — two to four pages for a company of ten to two hundred — and its purpose is not to permit remote work but to make it predictable: the same answer to "can I work from my parents' place in June?" whoever asks and whoever is asked. This guide is the craft first — what a remote work policy is and isn't, the ten sections a usable one carries, how to write one that the team actually follows — then a template you can copy, a filled-in example for a company of forty across three countries, and the mechanics: where the policy and its review live in the tools your team already uses, and what happens to the questions it provokes. Because the policy's real test is not the day it is signed. It is the Tuesday a new colleague in another city, reading in another language, asks the one question the policy was supposed to answer. ## What a remote work policy is — and what it isn't Five documents surround remote work, and they are routinely confused: | | Answers | Grain | One line looks like | Who reads it | | ------------------------- | ------------------------------------------------------------------------ | ------------------------------ | ---------------------------------------------------------------------------------------- | -------------------------------------- | | **Remote work policy** | The organization's rules for working away from the office | A rule, for everyone it covers | "Members are reachable in the team channel between 10:00 and 15:00 CET on working days." | Everyone, once; new members on day one | | **Hybrid work policy** | The same rules where the default is a split between office and elsewhere | A rule plus a rhythm | "Tuesdays and Thursdays are office days for the Milan team." | Everyone in a team with an office | | **Remote work agreement** | What this one person and the company agreed under the policy | One person | "Ana works from Lisbon, Portuguese contract, 100% remote from 1 November." | The person, their manager, HR | | **Working guidelines** | How the team does its everyday work under the policy | Habits, not rules | "Post your status by 09:30; a thread per blocker." | The team, every week until it is habit | | **Employee handbook** | Everything the organization promises and expects | A reference | Leave, expenses, conduct, data protection, remote work | Everyone, when they need it | The policy is the rule layer: short, rarely changed, approved by whoever can bind the company. The agreement is the policy applied to one person and signed; the guidelines are the team's habits and change whenever the work does. A policy that tries to be all three — the rule, the contract and the daily habits — gets long, goes stale in a month and stops being read. A remote work policy is also not a statement that remote work is allowed. "Employees may work remotely with their manager's approval" is a sentence, not a policy. The policy is what follows: from where, when, with what, at whose cost, and what happens when it does not work. ## What to include: the ten sections A usable remote work policy carries ten sections. Most templates online are a subset of this list; the ones most often missing are the eighth, the ninth and the tenth. 1. **Purpose and scope.** Why the policy exists in one sentence, and who it covers: employees, contractors, both; which countries' contracts; whether it applies to the whole company or named teams. 2. **Eligibility and arrangements.** Which roles can work remotely, and in which of three arrangements — fully remote, hybrid with set office days, or occasional with manager approval. Say who decides and how a request is made and answered. 3. **Place of work.** The registered place of work for each person, the countries work may be done from and for how long, and the rule for working from a country other than the contract's — because tax, social security and insurance follow the place where the work is done, not where the company sits. This is the section to write with a lawyer or an accountant per country; the policy's job is to say what the rule is and who checks it. 4. **Working hours and availability.** Core hours when everyone is reachable, in which time zone; expected response times by channel; how working hours are recorded where the law requires it; the right to be unreachable outside them. 5. **Communication and meetings.** Which channel is for what — the team channel for work, direct messages for the personal, email for the outside world; which meetings are mandatory and how a person who could not attend reads what was decided; where the written record of the team lives. This is the section that decides whether the other nine are ever read again. 6. **Equipment and expenses.** What the company provides — laptop, screen, headset, chair — what it reimburses — connectivity, a coworking desk, part of a home office — at what rate and how often, and what happens to the equipment when the person leaves. 7. **Security and data.** The devices that may hold company data; the sign-in the company requires; what may not be done on public networks or shared computers; where documents are stored and where they are not; whom to call within what time when a device is lost. 8. **Health, safety and workspace.** The minimum the company expects of the place work is done — a desk, a chair, light, a door that closes for calls — what the company checks and how, and the insurance that applies when an accident happens at home. 9. **Performance and presence.** That work is judged by what is finished and written down, not by the hours a status light is green; how goals are set and reviewed for a person the manager rarely sees; which written updates replace the visibility an office gives for free. 10. **Review and changes.** The owner of the policy, the date it is next reviewed, how a change is proposed and approved, and where the current version lives and the old ones are kept. A policy without this section is the version somebody printed in 2023. What stays out: the organization's leave policy, expense policy and code of conduct, each of which the remote policy links to rather than restates; the team's daily habits — stand-up time, status format — which belong in the working guidelines; and anything that applies to one person, which belongs in that person's agreement. ## How to write one: before, during, after **Before you write, collect the questions.** Post one message in the team's channel: "We are writing the remote work policy — reply with the question you most want it to answer." The questions that arrive are the policy's table of contents in the words of the people who will read it; a policy that answers them is read, a policy that answers the questions HR had is filed. Collect for a week. Then write the ten sections, each as short as the questions allow, and send the draft to the same channel with a date by which comments close. **While you write, decide, don't describe.** Every section ends in a rule a stranger can apply: "reachable 10:00–15:00 CET", not "we expect reasonable availability"; "up to 30 days a year from another EU country, notified two weeks before", not "working abroad is possible by arrangement". A rule that depends on who is asked is not written yet. Where the answer genuinely differs by country — place of work, hours recording, home-office allowance — write the rule per country in a table rather than a paragraph that tries to cover all of them. **After it is approved, put it where the team reads — and keep it there.** The policy goes to the channel the team already works in, pinned, with the three decisions people asked about most quoted in the message that announces it. The same day: the review date goes in the calendar, the agreement template goes to the people who need one, and the old version, if there was one, is marked superseded and kept. A policy that lives in one HR folder is a policy the team does not have; the questions keep coming, and each one is answered from memory, differently. How a distributed team then runs its week — the written status by a set time, the meetings that stay and the ones that go — is in [how to improve team productivity](https://intermind.com/blog/how-to-improve-team-productivity); the rhythm of the meetings themselves is in [meeting cadence](https://intermind.com/blog/meeting-cadence). ## A remote work policy template > **\[Company] — Remote work policy**:br**Version:** \[1.0] · **Owner:** \[name, role] · **Approved:** \[date] · **Next review:** \[date] :br**Applies to:** \[employees / contractors / both], under \[country] contracts, in \[all teams / named teams] > > **1. Purpose and scope**:br > \[One sentence: why the policy exists.] This policy covers work done away from \[office address]. It links to the \[leave policy], \[expense policy], \[data protection policy] and \[code of conduct], which apply unchanged. > > **2. Eligibility and arrangements**:br > Roles eligible: \[list, or "all roles except …"]. Arrangements: **fully remote** — \[who]; **hybrid** — \[office days per week, which days, set by whom]; **occasional** — \[up to N days a month, approved by the manager in the channel]. A request is made \[where] and answered within \[N] working days. > > **3. Place of work**:br > Each person's registered place of work is the one in their agreement. Work from another place in the same country: \[allowed / notify manager]. Work from another country: \[up to N days per calendar year, notified N weeks ahead, only from countries listed here]; longer stays require \[a new agreement]. \[Name] confirms the tax and insurance position before approval. > > **4. Working hours and availability**:br > Core hours: \[10:00–15:00] \[time zone], working days. Response time: team channel \[within 2 hours in core hours]; direct message \[same day]; email \[next working day]. Hours are recorded \[how, where the law requires]. Outside working hours nobody is expected to read or answer. > > **5. Communication and meetings**:br > The team channel is where work happens; \[the written status is posted by \[day, time]]. Mandatory meetings: \[list, cadence]. A person who cannot attend reads the meeting's recap in the channel \[by when]. Decisions not written in the channel were not made. > > **6. Equipment and expenses**:br > The company provides: \[laptop, screen, headset, …]. The company reimburses: \[connectivity N per month / coworking desk up to N / home-office allowance N per year], claimed \[how, how often]. Equipment is returned within \[N] days of leaving. > > **7. Security and data**:br > Company data lives only on \[company-managed devices], signed in with \[the company sign-in]. Not allowed: \[shared computers, public networks without VPN, storing files outside \[the named tools]]. A lost or stolen device is reported to \[name / address] within \[N] hours. > > **8. Health, safety and workspace**:br > The minimum workspace: \[a desk, a chair, daylight, a quiet place for calls]. The company \[checks how: a self-assessment once a year / on request]. Accidents during working hours at the registered place of work are covered by \[insurer / scheme]. > > **9. Performance and presence**:br > Work is assessed on \[outcomes agreed in writing, reviewed every N weeks], not on hours online. \[The written status] replaces the status meeting. Presence indicators are not a measure of work. > > **10. Review and changes**:br > This policy is reviewed by \[owner] on \[date] and after \[a change in law, a new country, an incident]. Changes are proposed \[in the channel], approved by \[who] and announced \[where]. The current version is \[pinned in the team channel]; previous versions are kept \[where]. > > **Revision history:** \[date — version — what changed — approved by] ## A filled-in example: forty people, three countries An illustrative policy for a design and localization agency of forty, headquartered in Milan, with a studio of twelve in Bucharest and nine people working from home in Portugal and Spain. The numbers are examples; the shape is the point. > **Studio Alba — Remote work policy** · v2.1 · Owner: Chiara R., COO · Approved: 6 Oct 2026 · Next review: 6 Apr 2027 :br**Applies to:** employees on Italian, Romanian, Portuguese and Spanish contracts; contractors by their agreement. > > **1.** The policy exists so that a person in any of our four countries knows the same rules as a person in Milan. It covers work done away from Via Torino 12, Milan, and from Strada Lipscani 4, Bucharest. > > **2.** All roles are eligible except reception. **Hybrid** for Milan and Bucharest staff: Tuesday and Thursday are studio days, set per team by the team lead each quarter. **Fully remote** for Portugal and Spain. **Occasional** extra remote days are asked for in the team channel and answered by the lead the same day. > > **3.** Registered place of work: the address in each agreement. Work from another EU country: up to 30 calendar days a year, notified in the channel two weeks ahead; longer than 30 days needs a new agreement. Outside the EU: not permitted. Chiara confirms the position with the accountant for each country before approving a stay over 14 days. > > **4.** Core hours 10:00–15:00 CET; Lisbon colleagues 09:00–14:00 local. Team channel: answered within two hours in core hours. Direct messages: same day. Client email: next working day. Hours are recorded in the time tool where the contract's law requires it (Italy, Spain). Nobody reads the channel after 18:00 their time. > > **5.** Each team's channel is where its work happens. Friday status by 16:00 CET in the shape posted in the channel. Mandatory: the Monday team meeting (30 min) and the monthly all-hands; everyone else reads the recap in the channel by the next morning. A decision that is not in the channel was not made. > > **6.** Provided: laptop, screen, headset; a chair on request. Reimbursed: €40 a month for connectivity; a coworking desk up to €150 a month for fully remote staff who ask; both claimed quarterly through the expense tool. Equipment is returned within 10 days of leaving. > > **7.** Company data on company laptops only, signed in with the company Google account; client files in the project's channel or the client's shared drive, nowhere else. No public Wi-Fi without the VPN. A lost device is reported to Chiara within 4 hours, by any means. > > **8.** Minimum: a desk, a chair with back support, daylight, a door that closes for calls. A self-assessment form once a year; the company pays for a chair where the form says the one at home will not do. Accidents at the registered place of work in working hours are covered by the national scheme of the contract's country. > > **9.** Goals are set in writing every six weeks with the lead and reviewed in the one-on-one. The Friday status is the visibility; the green dot is not. > > **10.** Reviewed by Chiara every six months and after any new country or incident. Changes proposed in the #studio channel, approved by the two directors, announced in the same channel with the changed lines quoted. Current version pinned in #studio; previous versions in the policy folder. > > **Revision history:** 6 Oct 2026 — v2.1 — section 3: 30 days abroad, was 20 — directors. Notice what the example has that most policies lack: a time zone next to every hour, a named person next to every approval, a number next to every allowance, and a section 10 that says where the policy is and who will change it. That is the whole craft. ## Where the policy lives in the tools you already use The policy itself is a document, and it lives wherever the team's documents live — a Word file in a shared library, a Google Doc, a page in a wiki, a canvas. The questions it provokes and the review that changes it are a meeting, and each platform has a place for what that meeting leaves behind, and each stops at a different point. Documented behaviour only, from the vendors' own pages, with the month each page was checked: | Platform | Where the review is noted | What of the review comes back after the meeting | | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | *Notes* in the meeting controls during the call — a Loop component that any attendee or organizer can edit, with tasks assigned by tagging people; or *Add an agenda* in the meeting's Details when scheduling | Saved automatically and reachable from the Teams calendar and the meeting recap; what is in the notes is what a person typed; external attendees cannot access or edit them (checked October 2026) | | **Zoom Workplace** | Meeting summary with AI Companion is generated from the meeting, in three sections — quick recap, summary, next steps — on paid Zoom Workplace plans; a person's own notes are a separate document | The summary is sent by email, listed on the Summaries page of the web portal and can be posted to the meeting's group chat in Team Chat; participants receive it when the host chose to share it, only the host can edit it, and unauthenticated users do not receive the email (checked August 2026) | | **Google Workspace** | The Calendar event's description, or a Google Doc linked from it; on eligible Workspace editions and Google AI plans, *Take notes for me* can be switched on in Calendar when the event is created | The notes arrive as a Google Doc after the meeting, shared with all guests, organization guests or hosts only, per the setting; the feature supports one language at a time — multiple languages spoken in the same meeting are not supported (checked October 2026) | | **Slack** | A canvas from a template, shared in the channel, with sections for objectives, next steps and action items with due dates; a huddle in the channel has "a dedicated message thread to share notes, links, and files" | The canvas stays in the channel as a document; what was said in the huddle is not in it unless someone types it (checked October 2026) | Two things are the same everywhere. The policy is a document in the one language it was written in, and the colleague who reads another language reads that one or a copy someone made; and what the review changed gets into the document only if a person types it in afterwards, in that same language. For a team in one office, in one language, the table is the whole answer. The next section is one way the job gets done where it is not. ## The one channel the policy lives in InterMIND is a communication space where a team's work lives in a channel, so the remote work policy has an obvious home: the channel of the team it covers. Posted as a note — a rich-text message with headings and numbered sections, editable later from its own menu — it is read by each member in their own language, with the original and a diff of what changed a toggle away, and pinned so the current version is the first thing a new colleague finds. Uploaded as a file instead — a PDF or a Word document from the HR folder — it opens for each reader translated into their language on paid plans, and on every plan its card carries an AI summary in the reader's language, each point linked to the paragraph it came from, so the two-minute version exists before anyone has written it. If the master copy stays in a document tool, its updates land in the channel by email: the channel's host gives it an address of its own, and a message sent there appears as a regular message with the sender named and attachments kept. The questions the policy provokes stay with it. A member in Bucharest asks in Romanian under the pinned note; the lead in Milan reads it in Italian and answers in Italian; the colleague in Lisbon reads both in Portuguese — the channel's chat is translated per reader, and the thread of questions and answers becomes the policy's own commentary, searchable later. A question from the road is a voice note from the phone, up to ten minutes, transcribed within seconds and read by each teammate as text in their own language. The "occasional remote day" request of section 2, the "30 days abroad" notice of section 3, the Friday status of section 5 — all of them are messages in the same channel, with an author and a time. The review meeting starts from that channel. During the call, the current version goes on everyone's screen next to the video tiles with *Share to conference* — a note, or a Google Docs or OneDrive document linked in the chat — and each participant scrolls it independently and reads it in their own language; a shared note is edited live by the sharer while the room watches the changed section take shape. When the call ends, the recap is written from the meeting itself — a summary, the points marked agreed, open or disputed, the action items with owners, each line keeping its timestamp — and the documents shared during the session contribute their summaries alongside what was said. It arrives by email, as a message in the channel and as a link in the calendar event, and every signed-in member reads it **in their own language**: the record is translated per reader, not written once in the language the room happened to use. Any member can edit it, every edit keeps author and revision history, and the channel keeps the recap of every past session — so the review that produced v2.1 is one click from the note that is v2.1. An ad-hoc meeting by link leaves only its recap, in each participant's Inbox, and its chat is wiped when the call ends; a policy and its history belong in a channel. The people a remote work policy covers are not always employees. A contractor in Spain, a freelancer who works two days a week, a distributor's project manager who follows the same communication rules: an external member of the channel joins by email onto a free account and reads the policy and its history like everyone else; a person without an account is a guest of one meeting — a candidate, a supplier for one review — who joins by link, from a phone, at no cost, hears the meeting live in their own language, and gets no record afterwards. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing) — joined a meeting, wrote in a chat or asked the assistant; members who go quiet keep their access at no cost, and people from outside the team in a channel or a meeting are not counted. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. Remote work policies as a craft survive every tool: somebody still has to decide the hours, name the countries, put a number next to the allowance and write down who changes the rule. What doesn't have to survive is the second job — keeping a translated copy of every version by hand, and answering the same question from memory, in one language, for people who read others. ## FAQ **What is a remote work policy?** A remote work policy is the written set of rules an organization applies to work done away from its office: who may work remotely and in which arrangement, from which places and countries, during which hours they must be reachable, how the team communicates and meets, what equipment and expenses the company covers, how company data is handled outside the office, what the workspace at home must provide, how performance is assessed, and how the policy itself is reviewed and changed. **What should be included in a remote work policy?** Ten sections: purpose and scope; eligibility and the arrangements offered; place of work, including the rule for other countries; working hours, availability and response times; communication and meetings, including where the written record lives; equipment and expenses; security and data; health, safety and workspace; performance and presence; and review and changes, with the owner, the next review date and where the current version is kept. **How do you write a remote work policy?** Collect the questions the team wants answered, in the channel where it already talks, for a week. Write the ten sections so that each ends in a rule a stranger can apply — hours with a time zone, allowances with a number, approvals with a name — and put country-specific rules in a table. Send the draft to the same channel with a date for comments, get it approved by whoever can bind the company, then pin it where the team reads, put the review date in the calendar, and keep the old version marked superseded. **What is the difference between a remote work policy and a work from home policy?** A work from home policy covers one place — the employee's home, usually in the same city and country as the office. A remote work policy covers any place away from the office: home, a coworking space, another city, another country, each with its own rules on hours, tax and insurance. Most organizations that started with a work-from-home policy end up rewriting it as a remote work policy once the first person moves. **What is a hybrid work policy?** A remote work policy in which the default arrangement is a split between the office and elsewhere: set office days per week or per team, who sets them, and how the remote days follow the same rules as fully remote work. It is usually a section inside the remote work policy rather than a separate document, because the rules on hours, data and equipment are the same for both. **Is there a remote work policy template in Word or Google Docs?** The template in this guide is plain text with bold labels, so it pastes into a Word document, a Google Doc, a Notion page, a Slack canvas or a chat note without reformatting. The format matters more than the file: whatever holds the policy needs the owner and the review date in the header, a rule a stranger can apply in each section, and a tenth section that says where the current version lives and who changes it. **How often should a remote work policy be reviewed?** On a date written in the header — every six or twelve months is usual — and earlier when one of four things happens: a person starts working from a new country, a law on remote work or hours recording changes in a country the policy covers, an incident the policy did not prevent, or three exceptions to the same rule in a row. The review is a short meeting with the team leads, and it ends in a new version with one line in the history or a confirmation with a new review date. **Does a small company need a remote work policy?** A company of ten with two people working from another country needs one more than a company of a thousand in one building: the questions — which country's rules apply, when is everyone reachable, who pays for the desk — arrive on day one, and without a policy each is answered from memory, differently. For a small company the policy is two pages, written in a week, and it lives in the team's channel rather than in a handbook. --- *Sources: [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Use huddles in Slack](https://slack.com/help/articles/4402059015315-Use-huddles-in-Slack){rel=""nofollow""}; [Slack — Meeting agenda template (canvas)](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Microsoft, Google and Slack pages checked October 2026; the Zoom meeting-summary page checked August 2026. Vendors change plans, features and language lists over time; check their pages for the current state. The policy sections and the example are illustrative, not legal advice; the rules on place of work, hours recording and insurance differ by country.* # Sales follow-up email: templates for after the call, and how to make the write-up send itself (2026) - **Same day, four things, one ask.** What you heard in the prospect's words, what was decided, the next step with a date, one request, then a cadence. - **The write-up is the slow part,** and why follow-ups go out late and vague; a CRM files the email from a trusted sender on a recipient it recognizes. - **InterMIND keeps the whole call as a recap:** takeaways and action items, emailed when the session ends and copied to your CRM. Guests join free by link, no account; you pay only for active members. A **sales follow-up email** is the message a seller sends after a call or meeting to restate what was discussed, confirm what was decided, and fix the next step — with a date — before the conversation goes cold. It is the part of the sale that happens in writing, and in most pipelines it is where deals quietly stall: the call went well, the email was written two days later from memory, and the next step was "I'll be in touch". This guide has three parts. What the email needs and five templates for the situations that come up. When to send it and how often. And the part that takes the time — the write-up of the call — which can be produced for you and filed in your CRM on its own, using nothing more than a meeting link and a BCC address. --- ## What a sales follow-up email needs Four things, in this order. Everything else is optional. 1. **What you heard.** Two or three lines restating the prospect's situation and problem in their words. This is the line that proves you listened, and it is the one prospects forward internally. 2. **What was decided.** Anything agreed on the call, one sentence each. "Agreed" and "still open" are different lines. 3. **The next step, with a date.** A demo on Thursday, a proposal by Friday, a call with their ops lead next week. A next step without a date is a wish. 4. **One ask.** Confirm the date, send the document, introduce the colleague. One — a follow-up with three asks gets none of them. Keep it short enough to read on a phone without scrolling. The recording, the deck and the full notes are links, not attachments. --- ## Five sales follow-up email templates ### 1. After a discovery call > **Subject:** Recap and next step — \[Company] / \[Your company] > > Hi \[Name], > > Thanks for the time today. What I took away: > > - You're running \[process] across \[teams], and it breaks when \[problem] — roughly \[frequency], at a cost of \[impact]. > - You've tried \[what they tried]; it didn't hold because \[reason]. > - A decision would involve \[names/roles], and you'd want it in place by \[timeline] because \[driver]. > > Based on that, I think this is something we solve well — specifically \[one line]. > > Next step: a demo on \[date, time] with \[name] in the room, focused on \[the problem]. I'll send the invite now; reply if the time doesn't work. > > \[Your name] ### 2. After a demo > **Subject:** \[Product] for \[problem] — what we showed and what's next > > Hi \[Name], > > Thanks for having \[names] join. The parts that mattered for \[problem]: > > - \[Feature/flow 1] — how it handles \[their scenario]. > - \[Feature/flow 2] — \[their question], answered. > > Still open: \[question they raised] — I'll confirm with \[team] by \[date]. > > You mentioned \[decision process]. Would a proposal covering \[scope] by \[date] be the useful next step, or do you want a second session with \[role] first? > > \[Your name] ### 3. When they've gone quiet > **Subject:** Re: \[previous subject] > > Hi \[Name], > > When we spoke on \[date], \[problem] was costing you \[impact], and you wanted it solved by \[timeline]. I haven't heard back since the \[demo/proposal] — usually that means priorities moved, or something in what I sent didn't fit. > > Either is fine. If it's the second, tell me what didn't fit and I'll adjust; if it's the first, tell me when to check back and I'll leave you alone until then. > > \[Your name] ### 4. After "send me some information" > **Subject:** The information you asked for — and the one question it doesn't answer > > Hi \[Name], > > As promised: \[link to the one document that answers their question]. It covers \[what]. > > The one thing it can't answer is how this applies to \[their specific situation from the call]. That takes about twenty minutes with \[role] — would \[date option 1] or \[date option 2] work? > > \[Your name] ### 5. After a meeting where a decision-maker was missing > **Subject:** Summary for \[missing person's name] — \[Company] / \[Your company] > > Hi \[Name], > > A short version you can forward to \[missing person]: > > - **The problem:** \[one line in their words]. > - **What we'd change:** \[one line]. > - **What it costs / saves:** \[number, if you have one]. > - **What's been agreed so far:** \[next step and date]. > > If it's easier, I can walk \[missing person] through it directly — \[date option]. Otherwise I'll follow up after \[agreed next step]. > > \[Your name] --- ## When to send a sales follow-up email, and how often **The same day.** The first follow-up goes out while the call is still fresh on both sides — ideally within the hour. Every day of delay makes the summary vaguer and the prospect's memory of the call fainter. **Then on a schedule, not on a feeling.** A rule of thumb that circulates among sales teams is the "2-2-2 rule": follow up after two days, then two weeks, then two months. The numbers are less important than the principle — each follow-up is planned when the previous one is sent, not when you happen to remember. **Each follow-up adds something.** A restated question, a relevant document, a new date option. "Just checking in" adds nothing and trains the prospect to ignore the thread. **Stop with a clean exit.** After the planned sequence, one final message that leaves the door open ("tell me when to check back") — and then stop. The prospect who comes back six months later comes back to the thread that ended politely. --- ## The part that takes the time: the write-up Every template above starts with the same block — *what you heard*. Writing it well takes longer than the rest of the email combined, because it means reconstructing the call from notes taken while also running the call. Skipped write-ups are the reason follow-ups go out two days late and say nothing specific. If the call runs in InterMIND, the write-up is generated when the session ends: a recap with a title, an overview, key takeaways, sectioned points with timestamps, action items, open questions and topics, emailed to the registered participants. If the conversation produced nothing summarizable, no email is sent at all. The summary can be corrected on the recap page — every edit is a revision with a word-level diff against the AI original — and the corrected text is what the recap message shows afterwards. The follow-up email then starts from the recap's takeaways and action items instead of from memory. The "what you heard" block is a paste and a trim. One boundary worth knowing: for ad-hoc meetings, only the latest session's recap is kept, mirroring how their chat is deleted after each call; a channel keeps the recap of every past session. --- ## Getting the follow-up into the CRM without logging it by hand Most CRMs accept email at an inbound address. Put it in the BCC field and the message is logged on the record the CRM matches against the other recipients. The vendors document the mechanics and the conditions: - **HubSpot** — the logging address is copied from Settings → Objects → Activities → Email Log & Track. A logged email "will automatically be associated to the recipient's contact record, its primary associated company record, and the five most recent open deal records associated to the contact"; if no contact matches the recipient, one is created. The sender must be a HubSpot user, a connected work email or a configured alias. Two documented limits: "when a recipient is BCCed in an email, the email will not create a new record, and if the recipient exists as a contact, the email will not be logged on their existing record" — matching is on the To/CC recipients, not on BCC'd ones — and the email with headers and attachments cannot exceed 40 MB. - **Pipedrive** — Smart Bcc gives the account a universal address, and "each lead and deal in your company's Pipedrive account has its own unique Bcc address." "If the address used to forward an email is linked to a contact person in Pipedrive, the email being forwarded will be linked to that contact person," and if no contact matches, "a new person contact will be created automatically." A documented requirement: "either DKIM or SPF must be correctly configured in your domain settings" for the sync to work. Available on all Pipedrive plans. - **Zoho CRM** — the BCC Dropbox "provides a unique email address for each user in your Zoho CRM account." The recipient is matched by a configurable search pattern (Contacts only, Leads only, or Contacts then Leads, with the option to create a record when nothing matches). A documented condition: "only those email address(es) that are added to the verified email address list will be associated to the leads/contacts in Zoho CRM" — the sender has to be pre-verified. Association can take up to 3 minutes; attachments are capped at 10 MB. Read together, the three describe the same contract: the CRM files the email on the record of a **To/CC recipient it recognizes**, and it accepts the email only from a **sender it trusts** — a verified address, an authenticated domain, a connected user. ### How the InterMIND recap meets that contract The recap email is designed to pass both checks: - **Participants stay in the To field.** Their addresses are what the CRM matches against, so the write-up lands on the prospect's record, not in an unfiled inbox. - **The CRM address goes in the Recap copy field**, on the meeting's row on the Meetings page or in a channel's display settings. Up to 10 confirmed addresses live in your personal address book and can be reused across meetings and channels. Available on every plan. - **Each new address is confirmed by a delivery test.** InterMIND sends a test email shaped like a real recap; someone opens it *inside the receiving tool* and clicks its confirmation link within 1 hour. Until then the address is pending and no copies are sent. The test exists because of the sender-trust condition above: a CRM that accepts mail over SMTP and then silently drops an unverified sender would otherwise look like it was working. If the test never arrives, the fix is to allow `noreply@intermind.com` as a sender in the receiving tool and pick the address again. The copy the CRM receives is the same email the participants get: the summary text plus links to the full recap and transcript. Those links still require signing in as a meeting member — the CRM holds the summary, not a door into the meeting. --- ## When the call was in two languages A follow-up email after an international call has one extra job: it is often the only written record the prospect will have. Two facts about the recap decide how to handle that. The emailed recap is a **single snapshot in the meeting's source language**. The recap page it links to serves the summary in the reader's own language — but that page requires sign-in and meeting membership, so it is the path for your team, not for a prospect who joined once from a link. A prospect who joined without an account receives nothing after the call at all; there is no delivery channel for them. So the follow-up email you write *is* the prospect's record. Open the recap in your language, write the "what you heard" block from its takeaways, and send it the same day — the prospect's side of the call was in their language, and the email is where the two sides' understanding is reconciled in writing. --- ## FAQ **How do I follow up after a sales call?** The same day, in writing, with four things: what you heard (in the prospect's words), what was decided, the next step with a date, and one ask. Then on a planned schedule — each follow-up adds something new and the sequence ends with a clean exit rather than trailing off. **How do I write a follow-up email after a call?** Start from the write-up of the call, not from memory: two or three lines restating the prospect's situation and problem, one line per decision, the next step with its date, and a single request. Keep it readable on a phone; link the deck and recording rather than attaching them. The five templates above cover discovery, demo, silence, "send me information", and a missing decision-maker. **What is the 2-2-2 rule in sales?** A rule of thumb for follow-up cadence that circulates among sales teams: follow up two days after the last contact, then two weeks later, then two months later. It is a scheduling principle rather than a measured law — the useful part is that each follow-up is planned when the previous one is sent. **How long should a sales follow-up email be?** Short enough to read on a phone without scrolling: a greeting, three or four bullet points, one next step, one ask. Detail lives in linked documents. Length is a symptom of a missing write-up — when you know exactly what was said, the email is short. **Can the call summary be sent automatically?** If the call runs in InterMIND, yes: when the session ends, a recap with an overview, key takeaways, action items and open questions is emailed to the registered participants, and it can be corrected on the recap page afterwards. A participant who joined without an account does not receive it — the follow-up email you send is their record. **How does the follow-up get into the CRM without logging it manually?** By BCC to the CRM's inbound address. HubSpot, Pipedrive and Zoho each document one: the email is filed on the record of a To/CC recipient the CRM recognizes, provided the sender is one it trusts. In InterMIND, the CRM address goes in the meeting's Recap copy field; the address is confirmed once by a test email opened inside the CRM, and from then on every recap of that meeting is filed on the prospect's record automatically. --- ## Try it - **[Start a meeting and copy its link](https://intermind.com/chats)** — the recap and the Recap copy field are on the meeting's row. - **[See what a recap contains](https://intermind.com/features/recap)** — a worked example of the summary, transcript and history. - **[Read the discovery call guide](https://intermind.com/blog/discovery-call)** — the call these templates follow up on. - **[See the book-a-demo flow](https://intermind.com/blog/book-a-demo)** — the demo the second template follows up on, and how the write-up reaches the CRM. --- *Sources: vendor documentation — HubSpot, [Log email in your CRM with the BCC or forwarding address](https://knowledge.hubspot.com/connected-email/log-email-in-your-crm-with-the-bcc-or-forwarding-address){rel=""nofollow""}; Pipedrive, [A guide to Smart Bcc emailing](https://support.pipedrive.com/en/article/smart-email-bcc){rel=""nofollow""}; Zoho CRM, [BCC Dropbox](https://help.zoho.com/portal/en/kb/crm/connect-with-customers/email/articles/bcc-dropbox){rel=""nofollow""}. Quoted conditions and limits are as stated on those pages. checked September 2026.* # Turkish voice translator: the verb arrives last, and that decides which one you need - **It depends on the shape of the exchange.** Phone app for a phrase, earbuds for one equipped counterpart, live meeting translation for a call with several people. - **Turkish puts the verb last.** Negation, ability and tense sit on that final word, so streaming systems commit early or wait; only a per-pair score shows how well. - **InterMIND keeps the whole meeting in each member's language,** Turkish to any of its 23 voice languages without English in the middle. Guests join free by link, no account; you pay only for active members. Most "voice translator" guides are written from English, where the verb shows up second and a system can start rendering a sentence almost as soon as it starts. Turkish does not work that way. *"Yarın fabrikaya gideceğim"* — I'll go to the factory tomorrow. *"Yarın fabrikaya gitmeyeceğim"* — I won't. *"Yarın fabrikaya gidemeyeceğim"* — I won't be able to. Three different messages that share their first four words; the difference lives in suffixes on a verb that is the last thing you hear. That is the whole reason "which Turkish voice translator" is a different question from "which voice translator." Below: what Turkish actually does to a translation pipeline, the three products that share the name, and the one measurement that separates a real answer from a language count. ## What Turkish does to a translation pipeline Two properties, both ordinary in Turkish and both awkward for streaming translation: - **Subject–object–verb order.** The predicate closes the clause. Negation (*-me-*), ability (*-ebil-*) and tense all attach to it. Until that verb lands, the clause is genuinely undecided — a system that emits as it hears has to either commit early and risk saying the opposite, or wait. - **Agglutination.** *Görüşemeyeceğimizi* is one word carrying "that we will not be able to meet." A pipeline that translates token by token has nothing useful to emit until the suffix chain completes. Neither is exotic — hundreds of millions of people speak SOV languages, and Turkish is among the most regular of them. But both mean that latency and accuracy on Turkish are *architectural* outcomes, not a checkbox. This is why "supports 100+ languages" is an empty claim for this pair: the count says nothing about whether the system waits for the verb, and nothing about how long that wait feels in a real meeting. The honest version of this claim is a measurement. We publish per-language-pair translation scores on real production traffic every month, with the methodology written down, at [`/benchmark`](https://intermind.com/benchmark) — Turkish pairs included, so you can read the number instead of taking our word for the architecture. ## The three products behind one search ### 1. Phone-app voice translators Open the app, tap the mic, speak; it transcribes, translates, plays back. Google Translate documents a live speech-to-speech mode on Android ([Google Translate Help](https://support.google.com/translate/answer/6142474){rel=""nofollow""}, checked September 2026); Apple Translate and Microsoft Translator cover the same shape. Turkish is where this design is at its most comfortable — because the app already waits. You finish the sentence, it processes the finished sentence, the verb is in the buffer. For a phrase, that is exactly right, and it is free. The cost only appears when the exchange keeps going: you speak → it processes → it answers → the other person replies into the same phone. Two people passing one device works for a taxi. Stretch it to a supplier review with three people and interruptions, and the relay becomes the meeting. ### 2. Earbud and device translators Apple documents Live Translation with AirPods ([Apple Support](https://support.apple.com/en-us/123185){rel=""nofollow""}, checked September 2026); Google documents translation on Pixel Buds ([Pixel Buds Help](https://support.google.com/googlepixelbuds/answer/7573100){rel=""nofollow""}, checked September 2026). You wear them, the other person speaks, you hear a translation in your ear. Note the shape rather than the quality: **one-to-one, one direction at a time, on your device.** Reciprocity needs matching hardware on the other side. Both vendors publish their own language lists and change them over time — check the current page before assuming Turkish is covered in the direction you need. Past two people, or past the people who happen to own the gear, the model stops applying regardless. ### 3. Live meeting translation The third kind is a different architecture, not a larger app. The *room* is multilingual: each participant speaks their own language and hears everyone else in theirs, simultaneously, for the whole call. Nobody passes a phone; nobody pairs earbuds. Translation is a property of the meeting. For Turkish this is also the only shape where the verb-final problem is solved once, centrally, instead of separately in every participant's pocket — and where you can ask for a per-pair number before you commit. The category guide, with what "real time" must mean and what to ask a vendor, is here: [real-time meeting translation](https://intermind.com/blog/real-time-meeting-translation). ## Which one do you actually need? | The exchange | The right tool | Why | | --------------------------------------------------------- | ------------------------ | -------------------------------------------------------------------------------- | | One phrase — a menu, an address, a question to a stranger | Phone app, free | It waits for your sentence anyway; the verb is in the buffer before it starts | | One counterpart, face to face, hardware on both sides | Translator earbuds | Most comfortable version of the relay; still one direction at a time | | A call or meeting, several people, both directions | Live meeting translation | Per-listener audio; nobody shares a device; the whole room is translated at once | | A document, a contract, an offer | File translation | Layout and clause numbering survive; not a voice problem at all | The trap is using a phrase tool for a conversation. It technically works — at half the speed and half the humanity, with everyone waiting on the relay instead of talking. In a Turkish workday that conversation is usually the weekly call with the customer in Germany, the quality review with a supplier in Bursa, the standup split between İzmir and London: nobody is passing a phone around in any of them. ## Turkish pairs are often not with English A tool that anchors every translation on English covers exactly one shape of Turkish workday. Turkish ↔ German, Turkish ↔ Russian and Turkish ↔ Italian are ordinary business pairs in this market, and routing them through English adds a second translation step — and a second place to lose the verb. InterMIND translates directly between any two of its 23 voice languages, Turkish included, with no English in the middle. That is an architectural statement, so it comes with the same caveat as everyone else's: read the pair's score at [`/benchmark`](https://intermind.com/benchmark) before you rely on it. ## Where InterMIND fits InterMIND is the third kind, built as meeting translation from the start — one person opens the room and sends the link, the others join free, without an account, each in their own language: - **23 languages live in voice, chat and shared notes** — Turkish to and from any of them, each participant choosing their own listening language, simultaneously, live. - **Nothing to install, nothing for participants to pay** — they [join by link, free](https://intermind.com/blog/free-for-participants); the host's plan covers the room. - **Documents too** — drop a PDF or DOCX into the meeting and each reader gets it in their language (30 languages for files). - **The meeting persists** — chat history, the recap and the documents stay readable in each signed-in member's own language, [a week later included](https://intermind.com/blog/the-meeting-a-week-later). - **Room size follows the host's plan** ([pricing](https://intermind.com/pricing)), each participant on their own listening language — [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation). ## Hear it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; hear a room translated live, per listener. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair monthly quality on real traffic, methodology public. - New to the category? Start with [real-time meeting translation: how it works](https://intermind.com/blog/real-time-meeting-translation). - The same three-way split, written for another market: [Italian](https://intermind.com/blog/traduttore-vocale), [French](https://intermind.com/blog/traducteur-vocal), [Spanish](https://intermind.com/blog/traductor-de-voz), [Portuguese](https://intermind.com/blog/tradutor-de-voz), [German](https://intermind.com/blog/sprachuebersetzer). --- ## FAQ **What is the best Turkish voice translator?** It depends on the shape of the exchange, not on a ranking. For single phrases, the free phone apps (Google Translate, Apple Translate, Microsoft Translator) handle Turkish. For one face-to-face counterpart with matching hardware, translator earbuds are the most comfortable relay. For a call or meeting with several people, you need live meeting translation, where every participant hears the whole room in their own language at the same time. **Does Turkish word order make real-time translation harder?** Yes, measurably. Turkish is subject–object–verb, and negation, ability and tense are suffixes on that final verb, so a clause is not decided until its last word. Systems that emit token by token either commit early or wait for the verb. Because the effect is pair-specific, a vendor's total language count tells you nothing about it — ask for the Turkish pair's score. Ours is published monthly on real traffic at [/benchmark](https://intermind.com/benchmark). **Can Turkish be translated directly to German or Russian, without English in the middle?** That depends on the architecture. Tools that anchor translation on English cover Turkish ↔ English shapes and route everything else through a second step. InterMIND translates directly between any two of its 23 voice languages, Turkish ↔ German and Turkish ↔ Russian included. **Do the other participants need an account or a subscription?** No. The host provides the space; participants join by link and get translation at no cost to them. What needs a free account is what comes *after* the call — the recap, the chat history and the documents in your own language are delivered to signed-in members. --- *Sources: [Google Translate — live speech-to-speech translation](https://support.google.com/translate/answer/6142474){rel=""nofollow""}, [Apple — Live Translation with AirPods](https://support.apple.com/en-us/123185){rel=""nofollow""}, [Google Pixel Buds — translation](https://support.google.com/googlepixelbuds/answer/7573100){rel=""nofollow""}, checked September 2026. Vendors change features and language lists over time — check their pages for the current state. InterMIND numbers are verified against the production product.* # Simultaneous interpreter: human, RSI platform, or AI — what your multilingual meeting needs (2026) - **Three ways, three cost structures.** A booth interpreter, an RSI platform with remote interpreters, or AI simultaneous translation; only the third has marginal costs that fit an ordinary meeting. - **Ask what comes back in your language after the audio.** Chat, notes and documents are not stated in most vendors' documentation, and where the data runs is a procurement gate. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes, documents and the summary, both directions. Guests join free by link, no account; you pay only for active members. A "simultaneous interpreter" is a profession: a person rendering speech into another language *while* it is being spoken — no pauses, no relay. What most people searching the term actually need is the outcome, and in 2026 there are three very different ways to get it — the interpreter in a booth, the RSI platform with remote interpreters, and AI simultaneous translation — with three cost structures that have nothing in common. This guide separates the three, then compares named tools on a verifiable basis: what each vendor's public documentation states, with the source and the date we checked. We build one of them ([InterMIND](https://intermind.com){rel=""nofollow""}) — we'll say where it fits and where it doesn't. --- ## The three ways to get simultaneous interpretation ### 1. The interpreter in the booth Two interpreters per language pair, a soundproof booth, receivers for the room. This is how institutions and large conferences do it. The quality comes from professionals who understand context, irony, and jargon — the cost comes from the same place: qualified humans, booked by the day, per language pair, plus equipment. The weekly working meeting is simply not what this model is designed for. ### 2. RSI: the human interpreter, remote Remote-simultaneous-interpretation platforms (Interprefy, KUDO, Boostlingo) deliver human interpreters' audio — sometimes with an AI option alongside — to participants' phones or headsets, on site or in a video call. The format remains an *event*: one speaker, an audience, languages fixed in advance, interpreters booked. ### 3. AI simultaneous translation No interpreter here: a speech-recognition → machine-translation → speech-synthesis cascade renders the speech in each listener's language within seconds, with nothing to book. Only this form has marginal costs that fit an ordinary meeting — the category's tipping point. The question shifts accordingly: *what* does the tool translate, beyond the voice? --- ## The questions that actually separate tools An honest comparison doesn't ask "is the translation good?" — every vendor says yes. It asks three things: **One speaker, or everyone at once?** Event tools optimize *one stage → one audience*, often one-directional. A working meeting is N people speaking, typing, reading, and replying at once — each in their own language, both directions. A tool that serves conferences well can be unusable for a four-person standup. **After the audio: what else comes back in your language?** A meeting isn't just speech: it's the chat, the shared notes, the document dropped mid-session, the record you keep. Most tools translate the spoken moment and stop there — the translation evaporates the instant the talking ends. Ask every candidate literally: *after the audio, what comes back in my language?* **Where does it run, and what gets stored?** For anything regulated — legal, medical, HR, finance — this is not a footnote but a procurement gate: is the audio stored, and does meeting content leave your jurisdiction? Our own answer: the live session retains nothing, and nothing derived from a meeting touches a US-hosted model — documented in [the GDPR audit](https://intermind.com/blog/gdpr-audit-what-we-closed) and [GDPR-compliant video conferencing](https://intermind.com/blog/gdpr-compliant-video-conferencing). --- ## The tools, on the record Every claim below comes from the vendor's public documentation, checked August 2026 (links at the end). "Not stated" means we found no claim in the public docs — ask the vendor if the point matters to you. ### For events with interpreters (RSI) - **Interprefy** — its documentation states 190+ languages and 6,000+ combinations with human interpreters, and 80 languages for its AI translation (audio and captions). ([InterMIND vs Interprefy, feature by feature.](https://intermind.com/compare/interprefy)) - **KUDO** — RSI platform with an AI option: the KUDO AI Speech Translator page states translated audio and captions in 60+ languages, alongside human-interpreter delivery. - **Boostlingo** — interpreter network: its site states 10K qualified interpreters and 275+ languages on demand, plus AI captions. ### For multilingual working meetings - **Wordly** — AI-only translation for meetings and events: its documentation states 60+ languages and 3,000+ language pairs, with attendees choosing text, audio, or both; its FAQ states translated transcripts and session summaries. Chat, shared-notes, and document translation are not stated in its public documentation (checked August 2026). ([InterMIND vs Wordly, feature by feature.](https://intermind.com/compare/wordly)) - **DeepL Voice** — the product page states live captions in 40+ languages inside Microsoft Teams, Zoom, and Google Meet; voice-to-voice output is listed as "coming soon" (checked August 2026). - **InterMIND** — what we build: the *whole* meeting comes back in each participant's language, both directions. Voice — 23 languages, rendered in the **speaker's own voice**, live ([how the cascade works](https://intermind.com/blog/inside-the-translation-pipelines)); chat and shared notes — translated live, per participant, in the same 23 languages; documents dropped in-meeting (PDF, DOCX, PPTX, XLSX) — returned in 30 languages, formatting intact ([the honest per-surface count](https://intermind.com/blog/how-many-languages-do-you-support)); the post-meeting summary — generated in your language, on EU-hosted models with zero retention of meeting data ([the GDPR audit](https://intermind.com/blog/gdpr-audit-what-we-closed)). Quality is published, not claimed: the production cascade is scored monthly against FLORES-200, full per-pair distribution, at [/benchmark](https://intermind.com/benchmark). ### Inside the platforms you already use - **Zoom** — translated captions in 36 languages (Business Plus/Enterprise or a paid add-on); a Voice translator that renders translated audio (AI Companion, US-cluster accounts, desktop app 7.0+); plus audio channels for up to 20 human interpreters you source yourself. ([Full breakdown.](https://intermind.com/blog/zoom-live-translation)) - **Microsoft Teams** — translated captions in 31 languages (Teams Premium or Copilot); an Interpreter agent that translates speech into speech and can simulate the speaker's voice (Copilot license); channels for 16 language pairs of human interpreters. ([Full breakdown.](https://intermind.com/blog/teams-live-translation)) - **Google Meet** — translated captions (Workspace Business Standard and above) and Gemini speech translation "in a voice like yours" (qualifying plans). ([Full breakdown.](https://intermind.com/blog/google-meet-live-translation)) --- ## The table: how much of the meeting comes back in your language? Every cell reflects what the vendor's own public documentation states, checked August 2026. | Tool | Translated audio (live) | Translated captions | Chat | Shared notes | Documents in-meeting | After the meeting | | ------------------- | -------------------------------------------------- | ------------------------------------------------------ | ------------------------------ | --------------------------- | -------------------------------------- | ---------------------------------- | | **Interprefy** | Yes — interpreters (190+ languages) or AI (80) | Yes (AI, 80 languages) | Not stated | Not stated | Not stated | Not stated | | **KUDO** | Yes — interpreters or AI (60+) | Yes (60+) | Not stated | Not stated | Not stated | Not stated | | **Wordly** | Yes (AI; 60+ languages, 3,000+ pairs) | Yes | Not stated | Not stated | Not stated | Translated transcripts + summaries | | **DeepL Voice** | "Coming soon" (per product page) | Yes (40+ languages, in Teams/Zoom/Meet) | Not stated | Not stated | Separate DeepL product | Not stated | | **Zoom** | Yes — Voice translator (AI Companion, US cluster) | Yes (36 languages; Business Plus/Enterprise or add-on) | Manual per-message translation | Not stated | Not stated | Not stated | | **Microsoft Teams** | Yes — Interpreter agent (Copilot license) | Yes (31 languages; Premium/Copilot) | Per-message, optional auto | Not stated | Not stated | Not stated | | **Google Meet** | Yes — Gemini speech translation (qualifying plans) | Yes (Business Standard+) | Not stated | Not stated | Not stated | Not stated | | **InterMIND** | Yes — 23 languages, speaker's own voice | Yes (23, per viewer) | Automatic per viewer (23) | Yes — live, per viewer (23) | Yes — PDF/DOCX/PPTX/XLSX, 30 languages | Summary + digest, in your language | Two honest notes on our own row: the counts differ per surface (voice/chat/notes 23, documents 30, website 17 languages — [the breakdown and why](https://intermind.com/blog/how-many-languages-do-you-support)); and voice quality is something you check on [/benchmark](https://intermind.com/benchmark), not in this table. --- ## The decision shortcut - **Conference with an audience + human interpreters required** → Interprefy, KUDO, Boostlingo. - **Working meeting, several people, both directions, AI** → Wordly, DeepL Voice, [InterMIND](https://intermind.com){rel=""nofollow""} — and here, test three things specifically: the rendered voice (generic or the speaker's own), coverage beyond the audio (chat, notes, documents, the record), and quality that is *published* rather than claimed. - **Captions are enough** → your existing Zoom/Teams/Meet, with the license gates from the table. --- ## FAQ **What is the best software for simultaneous interpretation in meetings?** Depends on the format. Event with an audience and interpreters: Interprefy (80 AI languages, 190+ with interpreters), KUDO (60+), or Boostlingo. Working meeting where everyone speaks, types, and reads in their own language, both directions: Wordly states 60+ languages as audio and text; InterMIND translates voice (23 languages, in the speaker's own voice), chat and notes (23), and documents (30) per participant. Captions only: Zoom (36 languages), Teams (31), or Meet, depending on plan. **What is the difference between a simultaneous interpreter and simultaneous translation?** "Simultaneous interpreting" is the professional term for real-time spoken rendering — a profession with booths, two-person teams, and standards. "Simultaneous translation" is the everyday term for the same outcome, whether a human or a machine delivers it. Strictly, *translation* concerns text and *interpreting* speech — we unpacked the distinction and the types of interpreting [here](https://intermind.com/blog/interpretation-vs-translation). **Can Zoom, Teams, or Google Meet interpret simultaneously?** Yes, with plan gates. Zoom: translated captions in 36 languages (Business Plus/Enterprise or add-on) and translated audio via the Voice translator (AI Companion, US cluster). Teams: captions in 31 languages (Premium/Copilot) and the speech-to-speech Interpreter agent (Copilot license). Meet: translated captions (Business Standard+) and Gemini speech translation on qualifying plans. Per-platform detail: [Zoom](https://intermind.com/blog/zoom-live-translation), [Teams](https://intermind.com/blog/teams-live-translation), [Meet](https://intermind.com/blog/google-meet-live-translation). **Is there AI simultaneous translation that keeps the speaker's own voice?** Most AI tools render every speaker as the same synthetic narrator. A few state output close to the original voice: Teams' Interpreter agent can "simulate" the speaker's voice, Google Meet states "a voice like yours," and InterMIND renders the translation in the speaker's own voice via zero-shot synthesis, in 23 languages — [how that works](https://intermind.com/blog/own-voice-translation). **Can AI simultaneous translation be GDPR-compliant?** The question resolves into three things you can ask any vendor: Is the audio stored or used for training? Where do the models that process meeting content run? And what happens to the derived material — transcript, summary, record? Our own answers are public: the live session retains nothing, and meeting content touches only EU-hosted models with zero data retention — documented in [the GDPR audit](https://intermind.com/blog/gdpr-audit-what-we-closed) and [GDPR-compliant video conferencing](https://intermind.com/blog/gdpr-compliant-video-conferencing). --- ## See it for yourself For the multilingual working meeting, the fastest test — for any tool, ours included — is to put your own meeting through it: talk, then check whether the chat, the notes, and the document came back in your language too. - **[Try the live demo](https://intermind.com/demo)** — InterMIND's production voice cascade, on your own audio, in any of 23 languages. - **[Read the benchmark](https://intermind.com/benchmark)** — monthly FLORES-200 scores, full per-pair distribution, no cherry-picking. - **[How to evaluate a real-time meeting translator](https://intermind.com/blog/real-time-meeting-translation)** — the vendor-neutral foundation behind this guide. --- *Sources: [Interprefy — AI translation languages](https://knowledge.interprefy.com/what-languages-can-interprefy-ai-translate-from-and-to){rel=""nofollow""}, [Interprefy — platform](https://www.interprefy.com/){rel=""nofollow""}, [KUDO — AI Speech Translator](https://kudo.ai/solutions/kudo-ai-speech-translator/){rel=""nofollow""}, [Boostlingo](https://boostlingo.com/){rel=""nofollow""}, [Wordly — translator languages](https://www.wordly.ai/translator-languages){rel=""nofollow""}, [Wordly — FAQ](https://www.wordly.ai/faq){rel=""nofollow""}, [DeepL — Voice](https://www.deepl.com/en/products/voice){rel=""nofollow""}, [Zoom — viewing captions in another language](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0060844){rel=""nofollow""}, [Zoom — Voice translator](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""}, [Zoom — Language Interpretation](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0064768){rel=""nofollow""}, [Microsoft — live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Microsoft — Interpreter in Teams](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft — language interpretation in Teams](https://support.microsoft.com/en-us/office/use-language-interpretation-in-microsoft-teams-meetings-b9fdde0f-1896-48ba-8540-efc99f5f4b2e){rel=""nofollow""}, [Google Meet — translated captions](https://support.google.com/meet/answer/10964115){rel=""nofollow""}, [Google Meet — Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, checked August 2026. Vendors expand plans and language lists over time; check their pages for the current state. InterMIND facts: [per-surface language breakdown](https://intermind.com/blog/how-many-languages-do-you-support), [live benchmark](https://intermind.com/benchmark).* # Simultaneous interpretation: what it is, how it works, and when AI can do it - **Translation delivered while the speaker is still talking.** Listeners hear their own language seconds behind; a booth needs two interpreters per language, booked ahead, billed per day. - **AI is the second cost collapse, with a limit.** RSI kept the day rates; AI makes interpretation a feature of the meeting software, while courts and certified depositions stay with accredited humans. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes and documents, with per-pair quality published. Guests join free by link, no account; you pay only for active members. **Simultaneous interpretation is translation delivered while the speaker is still talking.** Listeners hear the speech in their own language with a delay of a few seconds at most, and the meeting never stops to wait for the interpreter. It's how the UN runs its sessions, how multilingual conferences keep one agenda instead of three, and — since AI joined the field — increasingly how ordinary working meetings run too. This guide explains the whole category in plain language: how the traditional version works and what it costs, how it differs from consecutive interpretation, what "remote simultaneous interpretation" (RSI) changed, what AI can and can't do yet, and how to get simultaneous interpretation into the tools you already use. > Comparing vendors instead? Start with the [buyer's guide to AI translation tools for conferences and meetings](https://intermind.com/blog/best-ai-conference-translation-tools). --- ## What simultaneous interpretation actually involves Professional simultaneous interpreting is one of the most cognitively demanding jobs in language work. The interpreter listens to the source language, converts meaning (not words) on the fly, and speaks the target language — all at once, continuously, while the speaker keeps going. The industry has built serious infrastructure around that difficulty: - **Interpreters work in pairs**, one active and one supporting, swapping roughly every 30 minutes — sustained simultaneous work degrades fast beyond that. - **A soundproof booth** (or interpreting console) isolates the interpreter, with the room's audio in their headphones and their output routed to listeners' receivers. - **One booth and one pair per language.** A three-language event means three booths and six interpreters. - **Booking runs days to weeks ahead**, longer for rare pairs, and billing is per interpreter, per language, per day — plus equipment. None of that is a flaw. It's what delivering professional-grade live interpretation costs. The consequence is simply that simultaneous interpretation became an *event-day* service: budgeted, scheduled, and reserved for the sessions that justify it. ## Simultaneous vs consecutive interpretation The other classic mode is **consecutive interpretation**: the speaker says a few sentences, pauses, and the interpreter renders them in the target language. It needs no equipment and shines in small, controlled settings — a medical consultation, a notarized signing, a site visit. | | Simultaneous | Consecutive | | --------------------- | ----------------------------------------- | --------------------------- | | **Timing** | Parallel with the speaker | Alternates with the speaker | | **Meeting length** | Unchanged | Roughly doubles | | **Equipment** | Booth/console + receivers (or a platform) | None | | **Best at** | Conferences, working meetings, broadcasts | Short two-party exchanges | | **Languages at once** | Many (one channel per language) | Usually one pair | There are niche variants — *whispered* interpretation (chuchotage) for one or two listeners, *liaison* for back-and-forth negotiation — but nearly every real decision is simultaneous vs consecutive, and for anything with an agenda and more than a handful of people, simultaneous wins on time alone. (All the modes and delivery formats, plus how interpretation differs from translation, are laid out in [our definitional guide](https://intermind.com/blog/interpretation-vs-translation).) ## Remote simultaneous interpretation (RSI): the first cost collapse **RSI moves the interpreter out of the on-site booth and into the cloud.** The event's audio streams to interpreters working remotely; their translated audio streams back to each listener's phone, laptop, or headset. Platforms like Interprefy and KUDO built the category, and it took off when events went hybrid. What RSI eliminates: booth rental, receiver hardware, interpreter travel, and part of the lead time. What it keeps: the human interpreters themselves, their per-day rates, and the per-event operational setup. RSI made professional interpretation *cheaper to deliver* — it didn't change *who* does the interpreting or the booking model. (We compare the leading RSI service directly in [InterMIND vs Interprefy](https://intermind.com/compare/interprefy).) ## AI simultaneous interpretation: the second cost collapse The newer shift replaces the interpreting pipeline itself: **speech recognition → machine translation → speech synthesis**, running continuously, per listener, live. No booth, no booking, no per-day rate — interpretation becomes a *feature of the meeting software*, which changes what it can be used for. The weekly sync between Berlin, São Paulo, and Tokyo was never going to book two interpreters per language; with AI it doesn't have to. Three things distinguish AI interpretation done seriously (we build one of these tools, so we'll say plainly what to demand from any of them, [ours included](https://intermind.com/features/simultaneous-interpretation)): 1. **Per-pair quality you can verify.** "Supports 60 languages" says nothing about *your* DE↔EN. Ask for published, per-language-pair quality measured on real traffic — [here's ours, updated monthly](https://intermind.com/benchmark) — or [hear the live demo](https://intermind.com/demo) and judge. 2. **Whose voice comes out.** Most tools narrate every speaker with one synthetic voice. The better experience keeps each speaker's own voice via zero-shot synthesis — a discussion, not a transcript read aloud. ([How that works.](https://intermind.com/blog/own-voice-translation)) 3. **How much of the meeting is covered.** A meeting is voice *plus* chat, shared notes, and documents. If only the audio is translated, the room still splits into languages the moment someone types. ([The full argument.](https://intermind.com/blog/best-ai-conference-translation-tools)) And the honest limit, stated without hedging: **courts, treaty negotiations, certified depositions, and any setting where the interpretation is the legal record still belong to accredited human interpreters.** AI's territory is the enormous space below that bar — the meetings, webinars, and conferences that never got interpretation at all because booths and day rates priced them out. ## Simultaneous interpretation in Zoom, Teams, and Google Meet The platforms you already use sit at three different points: - **Interpretation channels (Zoom, Teams):** built-in audio channels for interpreters you bring and pay yourself. The platform solves delivery, not interpreting. How-to and limits: [Zoom](https://intermind.com/blog/zoom-live-translation), [Teams](https://intermind.com/blog/teams-live-translation). - **Translated captions:** all three platforms can subtitle a meeting in another language on the right plan. Reading is not hearing — captions work for a webinar, poorly for a discussion. Details per platform: [Zoom](https://intermind.com/blog/zoom-live-translation), [Teams](https://intermind.com/blog/teams-live-translation), [Google Meet](https://intermind.com/blog/google-meet-live-translation). - **Built-in AI speech translation:** early and partial (Meet's Gemini speech translation is the furthest along). Language pairs and plan gating decide whether your meeting qualifies. If you need every participant to *hear* the meeting in their own language, both directions, without booking anyone — that's the job [AI simultaneous interpretation](https://intermind.com/features/simultaneous-interpretation) does in the browser, and the platform comparisons above show exactly where each built-in option stops. ## Choosing, in one pass - **Certified, high-stakes, on the record** → accredited human interpreters, on-site or via RSI. - **Large formal event, human quality, hybrid audience** → an RSI platform ([vs Interprefy](https://intermind.com/compare/interprefy)); AI event delivery is the budget alternative ([vs Wordly](https://intermind.com/compare/wordly)). - **Working meetings, webinars, everyday multilingual calls** → AI interpretation built into the meeting: [every listener picks a language](https://intermind.com/features/simultaneous-interpretation), the meeting runs at full speed, and the chat, notes, and documents come back translated too. - **Occasional light need on one platform** → try that platform's captions first ([Zoom](https://intermind.com/blog/zoom-live-translation) / [Teams](https://intermind.com/blog/teams-live-translation) / [Meet](https://intermind.com/blog/google-meet-live-translation)) and upgrade when reading stops being enough. --- ## FAQ **What does simultaneous interpretation mean?** Interpretation delivered in parallel with the speaker — listeners hear the translation while the speech is still happening, typically a few seconds behind, so the meeting doesn't pause for translation. **How many interpreters does simultaneous interpretation need?** Two per language pair, swapping every \~30 minutes, per industry standard. A three-language conference typically staffs six interpreters plus equipment. **What does simultaneous interpretation cost?** Human: per interpreter, per language, per day — a one-day two-language event commonly runs into thousands of dollars with equipment. AI: a software subscription; the marginal cost of an interpreted meeting is zero. ([Pricing.](https://intermind.com/pricing)) **Is simultaneous interpretation possible in Zoom?** Yes, two ways: Zoom's interpretation channels with human interpreters you book yourself, or AI translation. Zoom's own AI features are captions-first — the full picture is in [our Zoom guide](https://intermind.com/blog/zoom-live-translation). **Can AI replace simultaneous interpreters?** In certified high-stakes settings — no, and vendors who claim otherwise should worry you. In everyday meetings, webinars, and conferences, AI now does the job well enough to be verified rather than assumed: check [per-pair published quality](https://intermind.com/benchmark) or [test it live](https://intermind.com/demo). --- ## Hear it, don't read about it Simultaneous interpretation is an audio experience, and no article settles whether the quality clears your bar. - **[Run the live demo](https://intermind.com/demo)** — hear a live meeting interpreted into another language on the production pipeline — no signup needed. - **[Read the benchmark](https://intermind.com/benchmark)** — monthly per-language-pair scores on real traffic, full distribution. - **[The feature, in detail](https://intermind.com/features/simultaneous-interpretation)** — how AI simultaneous interpretation works in an InterMIND meeting. - Choosing between a booked interpreter, an RSI platform and AI? [Simultaneous interpreter: human, RSI platform, or AI](https://intermind.com/blog/simultandolmetscher) — and the same three, priced and scoped for meetings, in [simultaneous translation: booth, RSI, or AI](https://intermind.com/blog/traduction-simultanee). — The Mind.com Team --- *Sources: [Chmiel — Boothmates forever? On teamwork in a simultaneous interpreting booth](https://akjournals.com/abstract/journals/084/9/2/article-p261.xml){rel=""nofollow""} (two interpreters per booth, \~30-minute turns), [Interprefy — platform](https://www.interprefy.com/){rel=""nofollow""}, [KUDO AI Speech Translator](https://kudo.ai/solutions/kudo-ai-speech-translator/){rel=""nofollow""}, [Zoom — Enabling and configuring translated captions](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0059081){rel=""nofollow""}, [Google Meet — Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, checked August 2026. Vendors change plans and language lists over time — check their pages for the current state.* # Slack alternatives for teams that work across languages (2026) - **Most lists compare the wrong axes.** For a multilingual channel: who reads it in their own language, who hears the call in theirs, how history reads later. - **Slack's own baseline:** message translation on request from Business+, visible only to you; nothing listed for huddle audio; stored history stays in the original language. - **InterMIND keeps the whole space in each member's language,** chat, calls, files and the recap as the default; a Slack export imports as channels. Guests join free by link, no account; you pay only for active members. Search "Slack alternatives" and the lists agree with each other: number of integrations, the 90-day history cap on the free plan, huddle quality, price per seat. Useful if Slack's bundle is your problem. Useless if your actual problem is that **your team's channels carry more than one language** — the standup thread, the customer channel, the decision typed at 11 pm in a language half the team reads slowly — because on those lists every alternative is the same product: a space that assumes everyone shares a language. This is the other comparison. If you're leaving Slack (or deciding not to) because a Kraków engineer, a São Paulo account manager and a Jakarta support lead share one channel, three axes decide the purchase — and none of them is the emoji picker: 1. **Messages: does each member read the channel in their own language — automatically, or one message at a time on request?** 2. **Calls: does every participant hear the huddle or meeting in their own language, or does someone hold a plan that the rest don't?** 3. **Afterwards: what does the history look like a month later — and in whose language?** One more fact is recorded beside them, not ranked: where it lives — can you name the jurisdiction the messages, files and recordings sit in? Here is Slack's own baseline on those questions, then the alternatives people actually evaluate — Microsoft Teams, Google Chat, Zoom Team Chat, and the self-hosted set Mattermost, Rocket.Chat, Element and Nextcloud Talk — then us, with one table across all of them. Every competitor fact comes from the vendor's public documentation, checked August 2026, linked in the footer. --- ## The baseline: what you'd be leaving Slack's documentation is unusually precise about its fences: - **Messages:** "Translate message" is an AI feature on the **Business+ and Enterprise+** plans. You set a translation language in your preferences and translate a message on request; "translations are only visible to you, so other people will always see the original message." Free and Pro have no translation feature. - **Calls:** huddles carry audio, video and screen sharing — group huddles on Business+ and Enterprise+, 1:1 on Free and Pro. The AI feature guide lists translation for messages, not for huddle audio. - **Afterwards:** on the Free plan you choose between keeping messages for one year or deleting them after 90 days; "on paid plans, data is kept for the lifetime of your workspace by default", with custom retention for owners. Exporting is an owner/admin action — public channels on Free and Pro, private channels and DMs on Business+ with approval — as JSON in a ZIP; members can't export their own messages. - **Where it lives:** data residency is a **Business+ and Enterprise+** feature, with Frankfurt, Paris, Stockholm, Zurich and London documented for Europe; messages, canvases, files and the search index are covered, member profiles and usage analytics are not. A Data Processing Addendum is available, executed via a form. So a Slack channel where three languages meet is workable from Business+ up — each reader translates on request — while the stored channel stays in the language each message was written in, and the calls stay untranslated. If that shape fits your team, staying is a defensible choice. The question is what the alternatives change. ## Microsoft Teams The alternative on every list, and the one with the most language machinery: - **Messages:** a chat or channel message is translated on request or automatically — "Teams can automatically translate received messages" — in 100+ languages, on desktop and mobile, with no plan or license named for it; an admin can switch it off. The article doesn't state that translated text is saved. - **Calls:** translated captions in 31 languages need the **organizer's Teams Premium or Microsoft 365 Copilot license**; the **Interpreter agent** — synthetic translated speech in 10 languages — is licensed **per listener** and metered at 20 hours per user per month, in scheduled meetings only. Captions aren't saved; recordings keep original audio. Details: [Teams live translation](https://intermind.com/blog/teams-live-translation). - **Afterwards:** each message stays in the language it was written in; retention policies can delete chats for everyone in a conversation, and there's no Export button for members — admins export through Graph APIs or eDiscovery ([how to export a Teams chat](https://intermind.com/blog/export-teams-chat)). - **Where it lives:** Teams data "resides in the geographic region associated with your Microsoft 365 or Office 365 organization"; country residency is for new tenants only; the EU Data Boundary covers Microsoft 365 tenants signed up in EU/EFTA, with documented exceptions. Against Slack, Teams moves message translation from Business+ to everyone, and puts the call layer behind Copilot seats. The full comparison from the other side: [Microsoft Teams alternatives](https://intermind.com/blog/microsoft-teams-alternatives). ## Google Chat (with Meet) - **Messages:** **Automatic Translation** converts incoming messages "to your preferred language set in your Google account settings"; "this feature requires an eligible Google Workspace or Google AI plan", and "translated messages are only visible to you". It covers the languages of Google's Neural Machine Translation model. - **Calls:** Meet's speech translation runs **between English and five languages, one language pair per meeting**, as a **90-minute beta**, unavailable in recordings. Details: [Google Meet live translation](https://intermind.com/blog/google-meet-live-translation). - **Afterwards:** history per the admin's retention settings, in the original language. - **Where it lives:** data regions — **the United States or Europe** — on Business Standard and Plus, Enterprise, Frontline and Education editions; Chat messages, attachments and room names are covered. Against Slack, Google Chat trades on-request translation for automatic translation on the reader's side — on an eligible plan — and adds an English-anchored call layer. ## Zoom Team Chat (with Meetings) - **Messages:** translated on request — "click the ellipsis icon… Click Translate. The message will be replaced by the translation", *Show Original* to revert — in 38 languages. Prerequisites: message translation enabled by the admin, and **Advanced Chat Encryption disabled**. - **Calls:** translated captions in 36 languages on Business Plus and Enterprise-tier plans (add-on otherwise); the **Voice translator** — synthetic translated audio in five languages — via the Live Translation add-on, desktop only. Details: [Zoom live translation](https://intermind.com/blog/zoom-live-translation). - **Where it lives:** Zoom's **EU Infrastructure** "hosts accounts for EU Education and Enterprise customers", covering Meetings, Webinar, Chat and Phone; within it, Zoom "does not transfer outside of or access data from outside this infrastructure unless a prior agreement with a customer is in place". Against Slack, Zoom's shape is Slack's shape with different numbers: per-reader translation on view, voice behind an add-on, residency behind the enterprise tier. ## Mattermost The open-source, self-hosted answer on most Slack-alternative lists — its own product page is titled that way — and since spring 2026 it has a translation feature: - **Messages:** **Automatic channel translation** (beta, introduced in v11.5) on **Enterprise Advanced**: back-end is **LibreTranslate** ("a self-hosted, open-source machine translation engine") or **Agents** ("the Mattermost Agents plugin with a configured LLM backend"); an admin sets the *Languages allowed*, and "a worker picks up the post and translates it sequentially into each configured target language". A user's target language "is determined by their Mattermost display language". - **Calls:** calls are a Mattermost feature; the auto-translation documentation covers channel posts. - **Afterwards / where it lives:** translated posts are produced on your own server; Professional and Enterprise are self-hosted annual seat licenses, prices on request; a single-tenant Mattermost Cloud Enterprise exists. Against Slack, Mattermost moves both the jurisdiction question and the translation question onto your own hardware — at the Enterprise Advanced tier, in beta, with you running the engine. ## Rocket.Chat - **Messages:** with Auto-Translate enabled per room, "messages you receive in that room will be automatically translated into your selected language"; "each user receives translations based on their own selected language". Providers: **DeepL, Google Translate, Microsoft Translator, LibreTranslate**, with credentials the workspace administrator supplies — so message text transits the provider you chose, unless it's LibreTranslate on your own host. - **Calls:** through integrations documented for the Starter plan — Jitsi, BigBlueButton, Pexip, Google Meet, Zoom. - **Afterwards / where it lives:** the **Starter** plan is free, "self-managed, self-hosted", "for technical evaluation or small teams of up to 50 users"; paid tiers are Commercial, Government and Defense — on-premises, private cloud or air-gapped — priced on request; the former Pro plan was retired on April 29, 2026. Against Slack, Rocket.Chat gives each member their own reading language inside the room as a standard feature, at the cost of running the server and holding a translation-provider key. ## Element (Matrix) - **Messages and calls:** "the entire platform is end-to-end encrypted by default", including **Element Call** voice and video. No message or voice translation is documented (checked August 2026) — end-to-end encryption by design leaves no server-side place for one. - **Where it lives:** **Community** is free — "free of charge frontend and backend", self-hosted; **Enterprise** is priced per seat per month, self-hosted; **Sovereign** is priced per deployment and air-gapped. Against Slack, Element answers the fourth question as completely as software can — and answers the first two with the original language only. ## Nextcloud Talk "A fully self hosted, on-premises audio/video and chat communication service": - **Calls:** the **live\_transcription** app provides live transcription and translation in Talk calls — "the transcription is done on your own server… while the translation is done using a translation task processing provider" — with Nextcloud 33, the High-Performance Backend, and an NVIDIA GPU with at least 10 GB VRAM or a 4-thread x86\_64 CPU. - **Messages:** translation goes through Nextcloud's translation API, backed by the **translate / translate2** apps on your server. - **Where it lives:** "ideal for on-premises private cloud deployments or hosting with a trusted, local provider". Against Slack, Nextcloud puts all of it on your own hardware, including the GPU that does the transcribing. ## InterMIND We build for exactly the case the lists skip — a channel whose members read and speak different languages — so here is our side of the same four questions, stated the same way: - **Messages:** the space is translated for each member as its default behavior — chat and shared notes in **23 languages**, documents in **30**. No per-message *Translate*, no Business+ gate: a member who reads Polish reads the channel in Polish. ([Why the numbers differ per pipeline.](https://intermind.com/blog/how-many-languages-do-you-support)) - **Calls:** every participant picks their language on joining and **hears every speaker in it, simultaneously**, in the speaker's own voice — no English anchor, no per-meeting pair, no per-listener license. **Participants pay nothing and need no account** — a link is enough. ([Why participation is free.](https://intermind.com/blog/free-for-participants)) - **Afterwards:** the meeting persists as a channel — chat history readable in each member's language, the recap delivered to signed-in members in theirs, documents in the same space. Your own chats export as a ZIP and restore, on plans with data export — no admin, no approval. ([How much of your meeting still exists a week later](https://intermind.com/blog/the-meeting-a-week-later) · [Meeting recap](https://intermind.com/blog/meeting-recap)) - **Where it lives:** **EU at every runtime hop** — translation on our own engine on dedicated servers in France, orchestration in Paris, database in Frankfurt, EU-resident storage; the recap on the AI gateway the organization selects, in an EU region (Azure OpenAI EU Data Zone by default), with zero data retention; a DPA signed per customer. ([Where one InterMIND meeting actually runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs)) - **Moving over:** the standard Slack export ZIP imports as InterMIND channels — history included, each member reads it in their own language; shared files stay as links, direct messages are not imported. ([Moving from Slack](https://intermind.com/migrate-from-slack)) - **Inside Slack meanwhile:** the InterMIND app for Slack starts a meeting with `/intermind` and posts the recap back in the thread — it requests no scope that reads messages. ([How it works](https://intermind.com/blog/intermind-for-slack-how-it-works)) Quality is published monthly, per language pair, on real traffic — [/benchmark](https://intermind.com/benchmark) — because "our translation is great" is exactly the claim you shouldn't take from any vendor. --- ## The comparison, in one table | | Messages in each member's language | Calls: everyone hears their own language? | Who pays for translation | History a month later | Where it can live | | ---------------------- | ---------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- | ------------------------------------------------ | ----------------------------------------------------------------------------------------------- | ---------------------------------------------------------------- | | **Slack** | On request, visible only to you; Business+ and Enterprise+ | Not listed for huddles | Business+ plan | Original text; Free keeps 90 days or one year; export by owners/admins only | Business+ residency: Frankfurt, Paris, Stockholm, Zurich, London | | **Microsoft Teams** | On request or auto on view, 100+ languages; no license named | Interpreter agent, 10 languages, per licensed listener, 20 h/month; captions 31 (organizer Premium/Copilot) | Organizer + each listener (Copilot) for voice | Original text; retention policies delete for everyone; no member export | Tenant region; EU Data Boundary for EU/EFTA tenants | | **Google Chat + Meet** | Automatic, visible only to you; eligible Workspace or Google AI plan | Meet: English ↔ 5, one pair per meeting, 90-min beta | Eligible plan per user | Original text per retention policy | US or Europe data regions on Business Standard+ | | **Zoom Team Chat** | On request, 38 languages, replaced on view; Advanced Chat Encryption off | Voice translator, 5 languages, add-on, desktop; captions 36 | Host plan tier or add-on | Original text | Zoom EU Infrastructure for EU Enterprise/Education accounts | | **Mattermost** | Auto, server-side into each allowed language (beta); target = display language | Not covered by the auto-translation docs | Enterprise Advanced + your LibreTranslate or LLM | Translated posts on your server | Self-hosted; single-tenant cloud on request | | **Rocket.Chat** | Auto per room, each user's language; DeepL / Google / Microsoft / LibreTranslate via admin key | Via integrations | Your provider key; Starter free to 50 users | Your server, per configured provider | Self-hosted, dedicated cloud, or air-gapped | | **Element** | Not documented | Element Call, end-to-end encrypted, original language | — | Original, end-to-end encrypted | Self-hosted; Community free | | **Nextcloud Talk** | Via the translate apps on your server | Live transcription on your server + translation via a task provider (GPU/CPU) | Your hardware | On your server | On-premises or a local provider | | **InterMIND** | Yes — 23 languages chat and notes, 30 documents, as the default | Yes — every participant hears every speaker in their language, 23 languages | Host's plan only; participants free, no account | Channel history in each member's language; recap to signed-in members; ZIP export by the member | EU at every runtime hop: France, Paris, Frankfurt | --- ## How to choose (including when not to switch) - **Your team writes and calls in one language.** Stay on Slack — or leave for the reasons the other lists cover. A multilingual space solves a problem you don't have. - **Translation on request is enough, and you're on Business+ anyway:** Slack documents it, per reader, with the original stored and residency in a named EU city. No switch needed. - **You want message translation for everyone without a plan gate:** Teams documents it in 100+ languages with no license named; Google Chat does it automatically on an eligible plan; Rocket.Chat does it per room on your server with your provider key. The call layer differs on each. - **Nothing may leave your own servers, and you have people to run them:** Rocket.Chat (free to 50 users), Mattermost Enterprise Advanced (beta auto-translation on your LibreTranslate or LLM), Nextcloud Talk (transcription on your own GPU), or Element if end-to-end encryption outranks translation entirely. - **Free:** Rocket.Chat Starter and Element Community are free to self-host; Slack's Free plan keeps 90 days or one year of history without translation; InterMIND is free for every participant — guests join by link, the host's plan covers the room, and the [live demo](https://intermind.com/demo) needs no signup. - **The channel itself is multilingual** — members replying to each other in three languages, guests without your licenses, a team that needs to reread last month's decision in their own language, and a compliance officer who wants a jurisdiction they can name: that's the case we built [InterMIND](https://intermind.com/chats) for. ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener in any of 23 languages. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, monthly translation quality on real traffic, with the methodology public. - **[Compare feature-by-feature](https://intermind.com/compare)** — InterMIND against each platform, every competitor cell sourced. --- ## FAQ **What is the best Slack alternative for a multilingual team?** It depends on which axis is broken for you. If reading messages in your own language on request is enough, Slack already does that on Business+, Teams does it for everyone, and Google Chat does it automatically on an eligible plan. If the *call* must reach every participant in their language, the documented options narrow fast: Teams' Interpreter (10 languages, per-listener Copilot license), Meet's speech translation (English ↔ 5, one pair), Zoom's Voice translator (5 languages, add-on), Nextcloud on your own GPU, or InterMIND (23 languages, every participant, host's plan covers everyone). **What are some good alternatives to Slack?** Microsoft Teams, Google Chat, Zoom Team Chat for bundled platforms; Mattermost, Rocket.Chat, Element and Nextcloud Talk for self-hosted ones; InterMIND for a space translated for every member. The fences that matter for a team across languages are in the table above — plan gates, per-reader vs for-everyone, what the stored history looks like, and where it lives. **Who is Slack's biggest competitor?** On the bundled side, Microsoft Teams — it's the alternative every list opens with, and the one whose documentation covers the most language machinery (message translation for everyone, meeting translation per Copilot seat). On the self-hosted side, Mattermost and Rocket.Chat both title their product pages as Slack alternatives and both now document automatic channel translation. **What are some free alternatives to Slack?** Rocket.Chat Starter (self-hosted, up to 50 users, auto-translate with your own provider key), Element Community (self-hosted, end-to-end encrypted, no translation), and Nextcloud Talk (self-hosted). Slack's own Free plan keeps 90 days or one year of history and has no translation. InterMIND is free for participants — guests join by link without an account; the host's plan covers the room. **Does Slack translate messages?** On Business+ and Enterprise+: set a translation language in your preferences, then translate a message on request; "translations are only visible to you, so other people will always see the original message." Free and Pro plans don't include it. Huddle audio isn't listed as translated. **Can I export my Slack history when I leave?** Exporting is an owner or admin action, not a member's: public channels on Free and Pro, private channels and DMs on Business+ with approval, as JSON in a ZIP. On the Free plan, messages older than 90 days (or one year, depending on the setting) are already gone. In InterMIND, a member exports their own chats as a ZIP on plans with data export, and restores them later. --- *Sources: [Slack — Pricing](https://slack.com/pricing){rel=""nofollow""}, [Slack — Guide to AI features in Slack](https://slack.com/help/articles/25076892548883-Guide-to-AI-features-in-Slack){rel=""nofollow""}, [Slack — Customize data retention in Slack](https://slack.com/help/articles/203457187-Customize-data-retention-in-Slack){rel=""nofollow""}, [Slack — Export your workspace data](https://slack.com/help/articles/201658943-Export-your-workspace-data){rel=""nofollow""}, [Slack — Data residency for Slack](https://slack.com/help/articles/360035633934-Data-residency-for-Slack){rel=""nofollow""}, [Slack — Data Processing Addendum](https://slack.com/terms-of-service/data-processing){rel=""nofollow""}, [Microsoft — Translate a message in Microsoft Teams](https://support.microsoft.com/en-us/teams/chat/translate-a-message-in-microsoft-teams){rel=""nofollow""}, [Microsoft — Interpreter in Teams meetings and calls](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft — Use live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Microsoft Learn — Location of data in Microsoft Teams](https://learn.microsoft.com/en-us/microsoftteams/location-of-data-in-teams){rel=""nofollow""}, [Microsoft Learn — What is the EU Data Boundary?](https://learn.microsoft.com/en-us/privacy/eudb/eu-data-boundary-learn){rel=""nofollow""}, [Microsoft Learn — Learn about retention for Teams](https://learn.microsoft.com/en-us/purview/retention-policies-teams){rel=""nofollow""}, [Google Chat — Use Automatic Translation in Chat](https://support.google.com/chat/answer/15711193?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}, [Google Meet — Learn about Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, [Google Workspace — Choose a geographic location for your data](https://knowledge.workspace.google.com/admin/compliance/choose-a-geographic-location-for-your-data){rel=""nofollow""}, [Zoom — Translating messages in Chat](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058113){rel=""nofollow""}, [Zoom — Enabling and configuring translated captions](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0059081){rel=""nofollow""}, [Zoom — Using the Voice translator for meetings](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""}, [Zoom — European Union public sector sovereignty controls explainer](https://library.zoom.com/advanced-enterprise-services/public-sector-sovereignty-controls/european-union-public-sector-sovereignty-controls-explainer){rel=""nofollow""}, [Mattermost — Pricing](https://mattermost.com/pricing/){rel=""nofollow""}, [Mattermost — Set up Auto-translation (Beta)](https://docs.mattermost.com/administration-guide/manage/admin/autotranslation.html){rel=""nofollow""}, [Rocket.Chat — Our plans](https://docs.rocket.chat/docs/our-plans){rel=""nofollow""}, [Rocket.Chat — Auto-Translate messages](https://docs.rocket.chat/docs/auto-translate-messages){rel=""nofollow""}, [Element — Pricing](https://element.io/pricing){rel=""nofollow""}, [Nextcloud Talk](https://nextcloud.com/talk/){rel=""nofollow""}, [Nextcloud — Live Transcription and Translation in Nextcloud Talk](https://docs.nextcloud.com/server/stable/admin_manual/ai/app_live_transcription.html){rel=""nofollow""}, [Nextcloud — Local Machine translation 2 (translate2)](https://docs.nextcloud.com/server/31/admin_manual/ai/app_translate2.html){rel=""nofollow""}. Vendors change plans, prices, language lists and beta status over time; check their pages for the current state. All facts checked August 2026.* # SOP template: format, example, review cycle — and the SOP every member reads in their own language (2026) - **An SOP template is a header and eight sections:** ID, version, owner, review date; then purpose, scope, roles, numbered steps, exceptions, records, references, revision history. - **A procedure stays true while it is reviewed;** in Teams, Zoom, Google Workspace and Slack the SOP is a document in one language, updated by hand after the review. - **InterMIND keeps the procedure and every review of it in each member's language,** next to those tools rather than instead of them. Guests join free by link, no account; you pay only for active members. A standard operating procedure, or SOP, is the written way a recurring job is done in your organization: the steps in order, who takes each one, what each step produces, and what to do when the normal path is blocked. An SOP template is the fixed skeleton those words go into, so that the fortieth procedure looks like the first and a person who has read one can read them all. The template is the easy part; most of this guide is about what goes in it and what keeps it true after the day it is written. This guide is the craft first — what an SOP is and isn't, the standard format, how to write one that people actually follow, a template you can copy, two filled-in examples — then the mechanics: how the review cycle works, where the SOP and its review live in the tools your team already uses, and what the person who reads it in another language gets. Because the SOP's real test is not the day it is approved. It is the Tuesday a new colleague opens it alone, at the counter, with a customer waiting. ## What an SOP is — and what it isn't Five kinds of document describe how work gets done, and the SOP is the one in the middle: | | Answers | Grain | One line looks like | Who reads it | | -------------------- | --------------------------------------------------- | --------------------------------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ | | **Policy** | What we do and don't do, and why | A rule | "Every complaint is answered within two working days." | Everyone, once; auditors | | **Process** | How the work flows across roles and teams | Stages and hand-offs | "Intake → triage → resolution → closure" | Managers; whoever designs the work | | **SOP** | How one job is done, step by step, by a named role | One procedure, one role at a time | "3. Reception logs the complaint in the register with the date, the channel and the customer's language." | The person doing the job, every time until it is habit | | **Work instruction** | How one step is done on one machine, screen or form | One step | "In the register, choose *Channel → Phone* and paste the call reference." | The person at that screen | | **Checklist** | Was everything done | Ticks | "☐ Register entry made ☐ Acknowledgement sent" | The person at the end of the shift | The distinctions matter because they decide the length. An SOP that explains the policy behind each step is a manual nobody opens at the counter; an SOP that goes down to which button to click is rewritten every time the software changes. The SOP says *what* is done, by *whom*, in *what order*, with *what result*; the policy above it says why, and the work instruction below it says exactly how on this screen. An SOP is also not a description of how the job is usually done. It is the agreed way — which is why it has an owner, a version and a review date, and why a step that nobody follows is a step to delete or a conversation to have, not a sentence to leave in. ## What to include: the standard format A usable SOP carries a header and eight sections. Most templates online carry the header and the steps and stop, which is why most SOPs are out of date within a year and nobody knows it: **The header** — the identity of the document, five fields on one line: an **ID** people can cite ("SOP-CS-04"), a **version** ("v2.1"), the **owner** — one named person, not a department — the **effective date** and the **next review date**. A document without a review date is reviewed when something goes wrong. 1. **Purpose.** One or two sentences: what this procedure achieves and what goes wrong without it. "Every complaint is logged, acknowledged and resolved the same way, so a customer gets the same answer whoever picks up the phone." 2. **Scope.** When this SOP applies and when it does not. "Complaints from customers about a product or a delivery. Not: warranty claims (SOP-CS-07), not: supplier complaints." 3. **Roles and responsibilities.** Each role that appears in the steps, with what it is accountable for. Roles, not names: names change; the SOP shouldn't have to. 4. **Definitions and prerequisites.** Terms a new person might not know, and what must be in place before step 1 — access to the register, the template, the escalation list. 5. **The procedure.** Numbered steps, one action per step, in the order they happen, each starting with the role and a verb: "Reception logs…", "The team lead reviews…". Where it helps, three columns — *who*, *does what*, *result or record* — so each step ends in something a second person could check. 6. **Exceptions and escalation.** The branches: what to do when the customer is not in the system, when the amount exceeds the limit, when the owner is away. Each exception names a person or a role, not "ask someone". 7. **Records and outputs.** What exists at the end that didn't at the start — the register entry, the sent email, the signed form — and where it is kept. This is the section an auditor reads, and the one that tells you whether the procedure was followed. 8. **References and revision history.** The policy it implements, the related SOPs and work instructions; then one line per version — date, what changed, who approved it. The history is the part that stops the same mistake being reintroduced under a new version number. **Four formats for the procedure section.** *Simple steps* — a numbered list — for a job of under ten steps with no branches. *Hierarchical* — numbered steps with lettered sub-steps — when a step has its own sequence inside it. *Flowchart* when the branches matter more than the sequence: a decision diamond is easier to follow than "if… otherwise… unless". *Checklist* for a routine done daily by the same people, where the question is not "how" but "did we". Many SOPs use two: a hierarchical procedure, and a one-page checklist derived from it for the shift. What stays out: justification (the policy's job), screenshots of every click (the work instruction's job), and anything a person could not act on. "Treat the customer with respect" is a value, not a step. ## How to write one: observe, draft, test, publish **Observe the person who does the job, and write down what they actually do.** Not what the manager thinks happens — what happens, including the workaround with the spreadsheet. The person who does the job every day is the co-author; the SOP that is written about them instead of with them is the one that lives in a folder while the real procedure lives in their head. Ask at each step: what do you do if this fails? **Draft in the template, steps first.** Write the procedure section before the purpose: the steps show you where the scope ends and which roles exist. One action per step, role plus verb, present tense. If a step needs a paragraph, it is two steps or a work instruction. Keep the whole thing short enough to read in five minutes; the detail lives in the linked instructions. **Test it on someone who has never done the job.** Give them the SOP and nothing else, and watch where they stop. Every stop is a missing step, a missing definition or a missing exception. One test with a new person is worth three reviews by experienced ones, who fill the gaps without noticing them. **Publish where the team reads, and set the date.** An SOP in a folder with forty others is found by the people who already know the job. It belongs where the team that runs the procedure already talks, with the owner's name and the review date visible, so that the question "is this still current?" is answered by the header, not by asking around. Then put the review date in the calendar — the SOP that is written and never reviewed is the one that is confidently followed after it stopped being true. ## An SOP template > **\[SOP ID] — \[Procedure name]**:br**Version:** \[n.n] · **Owner:** \[role, name] · **Effective:** \[date] · **Next review:** \[date] > > **1. Purpose**:br > \[One or two sentences — what this procedure achieves, and what goes wrong without it.] > > **2. Scope**:br**Applies to:** \[situations, products, sites] · **Does not apply to:** \[what is covered elsewhere, with the SOP ID] > > **3. Roles**:br**\[Role]** — \[what it is accountable for in this procedure] :br**\[Role]** — \[what it is accountable for] > > **4. Definitions and prerequisites**:br**\[Term]** — \[meaning] :br**Before step 1:** \[access, tools, templates, lists needed] > > **5. Procedure**:br**5.1** \[Role] \[does what] → *\[result or record]*:br**5.2** \[Role] \[does what] → *\[result or record]*:br**5.3** \[Role] \[does what] → *\[result or record]*:br > \[a. sub-step] \[b. sub-step] > > **6. Exceptions and escalation**:br**If \[condition]:** \[what to do, who decides] :br**If \[condition]:** \[what to do, who decides] :br**Anything not covered here:** \[role] decides and the case is raised at the next review. > > **7. Records**:br > \[What exists at the end — register entry, email, form — and where it is kept, for how long.] > > **8. References and revision history**:br**Implements:** \[policy] · **Related:** \[SOP IDs, work instructions] :br**v\[n.n] — \[date] — \[what changed] — approved by \[name]**:br**v\[n.n] — \[date] — \[what changed] — approved by \[name]** The template pastes into a Word file, a Google Doc, a Notion page, a Slack canvas or a chat note without reformatting. The two fields most often left blank are the owner and the next review date; they are the two that decide whether the document is still true in a year. ## Two filled-in examples ### Handling a customer complaint — service team, hierarchical > **SOP-CS-04 — Customer complaint handling**:br**Version:** 2.1 · **Owner:** Service lead, Marta R. · **Effective:** 1 Oct 2026 · **Next review:** 1 Apr 2027 > > **1. Purpose** — Every complaint is logged, acknowledged and resolved the same way, so a customer gets the same answer whoever takes the call, in the customer's language. :br**2. Scope** — Complaints from customers about a product, a delivery or an invoice, by phone, email or chat. Not: warranty claims (SOP-CS-07); not: supplier complaints (SOP-PR-02). :br**3. Roles** — **Reception:** logs and acknowledges. **Service agent:** investigates and answers. **Service lead:** approves anything above the credit limit, decides escalations. :br**4. Prerequisites** — Access to the complaints register; the acknowledgement template in the customer's language; the current credit limit (see the register header). > > **5. Procedure**:br**5.1** Reception logs the complaint in the register → *entry with date, channel, customer, product, the customer's language, and a complaint ID*:br**5.2** Reception sends the acknowledgement within one working day → *acknowledgement email with the complaint ID, in the customer's language*:br**5.3** The service agent investigates: :br > a. checks the order, delivery and invoice records; :br > b. calls or writes to the customer if a fact is missing; :br > c. records the finding and the proposed remedy in the register → *finding and remedy, dated*:br**5.4** If the remedy is a credit under the limit, the agent issues it; above the limit, the service lead approves within one working day → *credit note or written approval*:br**5.5** The agent answers the customer within five working days of 5.1 → *answer in the customer's language, referencing the complaint ID*:br**5.6** Reception closes the entry → *status Closed, date, remedy* > > **6. Exceptions** — **Customer not in the system:** log with the contact details given, flag *unverified*, continue. **Customer threatens legal action:** stop at 5.3, hand to the service lead the same day. **Owner away:** the deputy named in the register header approves. :br**7. Records** — The register entry (kept 5 years), the acknowledgement and the answer (in the customer's file), the credit note (finance). :br**8. References** — Customer policy §4; SOP-CS-07; work instruction WI-CS-04a "The complaints register". :br**v2.1 — 1 Oct 2026 — step 5.2 deadline changed from two days to one; acknowledgement now in the customer's language — approved by Marta R.**:br**v2.0 — 15 Mar 2026 — credit limit and approval step added — approved by Marta R.** ### Opening the clinic — reception, daily checklist > **SOP-FD-01 — Opening the clinic**:br**Version:** 1.3 · **Owner:** Practice manager, Tomás A. · **Effective:** 1 Sep 2026 · **Next review:** 1 Mar 2027 > > **1. Purpose** — The clinic is ready for the first patient at 08:00, every day, whoever opens. :br**2. Scope** — Weekday opening by the receptionist on the early shift. Not: weekend opening (SOP-FD-02). :br**3. Roles** — **Opening receptionist:** everything below. **Practice manager:** called on any failed item. > > **5. Procedure — by 07:45, in this order**:br > ☐ Alarm off, doors unlocked, lights and heating on :br > ☐ Reception computer on, appointment system open, today's list printed :br > ☐ Phone line switched from the night message to live :br > ☐ Waiting room checked: chairs, water, the day's notices in both languages :br > ☐ Treatment rooms 1–3: consumables above the minimum line on the cabinet :br > ☐ Card terminal on and test transaction cleared :br > ☐ The day's first three patients called if any has a note *confirm* > > **6. Exceptions** — **Any item cannot be completed:** call the practice manager before 07:50; do not open the doors to patients until the manager has answered. **Appointment system down:** use the printed list from the evening before (SOP-FD-05). :br**7. Records** — The ticked checklist, initialled and dated, in the opening folder; kept three months. :br**v1.3 — 1 Sep 2026 — notices in both languages added to the waiting-room item — approved by Tomás A.** Notice what the two have in common: every step starts with a role and a verb and ends in something a second person could check; the exceptions name a person; the header says who owns it and when it is next looked at; and the last lines record what changed and why. That is the whole craft. Everything else in this guide is about keeping the document true after the day it was signed. ## The review cycle: how a procedure stays true An SOP is a claim about how work is done, and the work moves. The review cycle is what keeps the claim honest. It has four parts. **A date, and triggers that beat the date.** Every SOP has a next review date in its header — six or twelve months is usual, shorter for anything regulated or safety-related. Four events bring the review forward: an incident the procedure did not prevent; a change in the tool, form or supplier the steps depend on; a change in the rule or regulation the SOP implements; and three deviations in a row — three people doing a step differently from the document is a vote, not a discipline problem. **A short review meeting with the people who do the job.** Twenty minutes, the owner and two or three people who run the procedure, the current version on everyone's screen. The agenda is always the same: > **SOP-\[ID] review — \[date]**:br**1. Deviations since the last review:** where did we do it differently, and why — 5 min :br**2. Incidents and complaints the procedure touched** — 5 min :br**3. Steps to change, add or delete** — one line each, with the reason — 7 min :br**4. Decision:** reissue as v\[n.n] on \[date], or confirm unchanged with a new review date — 3 min :br**Actions:** who edits, who approves, who tells whom, by when **A new version, with the old one kept.** The edit goes into the revision history as one line — date, what changed, who approved — and the version number moves: a changed step is a minor version (2.0 → 2.1), a changed scope or a new role is a major one. The previous version is marked *superseded* and kept, not deleted: an auditor, or a colleague explaining what happened in March, needs the procedure as it was then. A decision taken in the review that changes a rule, not just a step, belongs in the [decision log](https://intermind.com/blog/decision-log-template) as well, with the SOP ID in the entry. **The people who do the job hear about it.** A reissued SOP that nobody announced is the old SOP with a new number. The change goes to the people who run the procedure, in the place they already read, with the three lines that changed quoted — and the new review date goes in the calendar the same day. ## Where the SOP and its review live in the tools you already use The procedure itself is a document, and it lives wherever the team's documents live — a Word file in a shared library, a Google Doc, a page in a wiki, a canvas. The review is a meeting, and each platform has a place for what the review meeting leaves behind, and each stops at a different point. Documented behaviour only, from the vendors' own pages, with the month each page was checked: | Platform | Where the review is noted | What of the review comes back after the meeting | | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | *Notes* in the meeting controls during the call — a Loop component that any attendee or organizer can edit, with tasks assigned by tagging people; or *Add an agenda* in the meeting's Details when scheduling | Saved automatically and reachable from the Teams calendar and the meeting recap; what is in the notes is what a person typed; external attendees cannot access or edit them (checked October 2026) | | **Zoom Workplace** | Meeting summary with AI Companion is generated from the meeting, in three sections — quick recap, summary, next steps — on paid Zoom Workplace plans; a person's own notes are a separate document | The summary is sent by email, listed on the Summaries page of the web portal and can be posted to the meeting's group chat in Team Chat; participants receive it when the host chose to share it, only the host can edit it, and unauthenticated users do not receive the email (checked August 2026) | | **Google Workspace** | The Calendar event's description, or a Google Doc linked from it; on eligible Workspace editions and Google AI plans, *Take notes for me* can be switched on in Calendar when the event is created | The notes arrive as a Google Doc after the meeting, shared with all guests, organization guests or hosts only, per the setting; the feature supports one language at a time — multiple languages spoken in the same meeting are not supported (checked October 2026) | | **Slack** | A canvas from a template, shared in the channel, with sections for objectives, next steps and action items with due dates | The canvas stays in the channel as a document; what was said in the call is not in it unless someone types it (checked October 2026) | Two things are the same everywhere. The SOP is a document in the one language it was written in, and the colleague who reads another language reads that one or a copy someone made; and what the review changed gets into the document only if a person types it in afterwards, in that same language. ## How the procedure — and every review of it — comes back in each member's language InterMIND is a communication space where a team's work lives in a channel, so the SOP has an obvious home: the channel of the team that runs the procedure. Posted as a note — a rich-text message with headings and numbered lists, editable later from its own menu — it is read by each member in their own language, with the original and a diff of what changed a toggle away, and pinned so the current version is the first thing a new colleague finds. Uploaded as a file instead — a PDF or a Word document — it opens for each reader translated into their language on paid plans, and on every plan its card carries an AI summary in the reader's language, each point linked to the paragraph it came from, so the five-minute read exists before anyone has written it. If the master copy stays in a document tool, its updates land in the channel by email: the channel's host gives it an address of its own, and a message sent there appears as a regular message with the sender named and attachments kept. The review meeting starts from that channel. During the call, the current version goes on everyone's screen next to the video tiles with *Share to conference* — a note, or a Google Docs or OneDrive document linked in the chat — and each participant scrolls it independently and reads it in their own language; a shared note is edited live by the sharer while the room watches the changed step take shape. When the call ends, the recap is written from the meeting itself — a summary, the points marked agreed, open or disputed, the action items with owners, each line keeping its timestamp — and the documents shared during the session contribute their summaries alongside what was said. It arrives by email, as a message in the channel and as a link in the calendar event, and every signed-in member reads it **in their own language**: the record is translated per reader, not written once in the language the room happened to use. Any member can edit it, every edit keeps author and revision history, and the channel keeps the recap of every past session — so the review that produced v2.1 is one click from the note that is v2.1, and a member's own assistant — Claude, ChatGPT, Copilot or Gemini, connected through the MCP connector — can search recaps, transcripts, chats and the text of shared files in one question, "what did we change in the complaints procedure in October?", and read the document itself; this runs for organizations with AI features on. The people who run a procedure are not always employees. A distributor's staff, a contractor, a locum: an external member of the channel joins by email onto a free account and reads the SOP and its history like everyone else; a person without an account is a guest of one meeting — they join the review call by link, from a phone, at no cost, hear it live in their own language, and get no record afterwards. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing) — joined a meeting, wrote in a chat or asked the assistant; members who go quiet keep their access at no cost. - **[Open a complete recap](https://intermind.com/features/recap)** — a real record rendered by the same code that writes yours. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. SOPs as a craft survive every tool: somebody still has to watch the job being done, write the steps as actions, and ask the new person where they got stuck. What doesn't have to survive is the second job — keeping a translated copy of every version by hand, and retyping what the review changed, in one language, for people who read others. ## FAQ **What is an SOP template?** An SOP template is the fixed skeleton a standard operating procedure is written into: a header with the ID, version, owner, effective date and next review date, followed by the standard sections — purpose, scope, roles, definitions and prerequisites, the numbered procedure, exceptions and escalation, records, and references with a revision history. The template makes every procedure in the organization look the same, so a person who has read one can find their way in all of them. **What are the 5 parts of an SOP?** The five parts most templates agree on are the title block or header, the purpose, the scope, the roles and responsibilities, and the procedure itself. A complete SOP adds three more — exceptions and escalation, records, and references with a revision history — and it is usually the missing ones that make a procedure fail: no one knows what to do when the normal path is blocked, and no one knows what changed since the last version. **How do you write an SOP?** Observe the person who does the job and write down what actually happens, including the branches. Draft the procedure section first — one action per step, role plus verb, present tense — then fill in scope, roles and exceptions from what the steps revealed. Test it on someone who has never done the job and fix every place they stop. Publish it where the team already reads, with the owner and the next review date in the header, and put that date in the calendar. **What is the format of an SOP?** A header line — ID, version, owner, effective date, next review date — and eight numbered sections: purpose, scope, roles, definitions and prerequisites, procedure, exceptions and escalation, records, references and revision history. The procedure section takes one of four shapes: simple numbered steps, hierarchical steps with sub-steps, a flowchart when the branches matter more than the order, or a checklist for a daily routine. **What is the difference between an SOP and a work instruction?** An SOP describes one job end to end at the level of roles and steps — who does what, in what order, with what result. A work instruction describes one of those steps on one screen, machine or form, down to the field and the button. The SOP says "Reception logs the complaint in the register"; the work instruction shows the register, the fields, and the drop-down values. Keeping them separate is what lets the SOP survive a software change. **What is the difference between an SOP and a policy?** A policy is the rule and the reason: what the organization does and does not do. An SOP is how a role carries the rule out, step by step. "Every complaint is answered within two working days" is a policy; the eight steps from logging to closure are the SOP that implements it. A policy changes rarely and by decision; an SOP changes whenever the work does, and its revision history says when. **Is there an SOP template in Word or Google Docs?** The template in this guide is plain text with bold labels, so it pastes into a Word document, a Google Doc, a Notion page, a Slack canvas or a chat note without reformatting. The format matters more than the file: whatever holds the SOP needs the header with the owner and the review date, numbered steps that begin with a role and a verb, a named person for each exception, and a revision history — and it needs to live where the people who do the job already read. **How often should SOPs be reviewed?** On a date written in the header — every six or twelve months is usual, and shorter where the procedure is regulated or safety-related — and earlier when one of four things happens: an incident the procedure did not prevent, a change in the tool or form the steps depend on, a change in the rule it implements, or three deviations in a row. The review is a twenty-minute meeting with the people who do the job, and it ends in a new version with one line in the history or a confirmation with a new review date. --- *Sources: [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Meeting agenda template (canvas)](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Microsoft, Google and Slack pages checked October 2026; the Zoom meeting-summary page checked August 2026. Vendors change plans, features and language lists over time; check their pages for the current state.* # Azure AI Speech vs Google Chirp 3 vs Amazon Transcribe on 153 voice notes: why InterMIND runs speech-to-text on your organization's own cloud gateway (2026) - **Because the gateway is already on your sub-processor list.** Voice notes go to Azure AI Speech, the default gateway's speech service, in InterMIND's Sweden tenant. - **The numbers do not argue against it.** On 153 clips in 17 languages: Azure 9% word error rate, Google Chirp 3 and Amazon Transcribe 10%; on Vertex AI or Bedrock, notes are not transcribed yet. - **InterMIND keeps the whole channel in each member's language,** voice notes included, as text each teammate reads. Guests join free by link, no account; you pay only for active members. A voice note in an InterMIND channel becomes a text message that every teammate reads in their own language. The first step of that is speech-to-text, and the question a host's own IT or a client's reviewer asks is not "how accurate is it" but "whose service is it, and where does the audio go". The short answer: Azure AI Speech, the speech service of the default AI gateway, in InterMIND's own Azure tenant in Sweden Central — and the speech services of the two other gateways an organization can choose, measured on the same clips so the choice is a number, not a preference. This post shows the numbers behind that choice — the same 153 clips through Azure AI Speech, Google Cloud Speech-to-Text and Amazon Transcribe on the same day — and the two facts about each API that matter more than a percentage point of accuracy. ## The rule comes first: one gateway per organization Every AI feature in InterMIND — meeting recaps, document summaries, the writing assistant, Ask AI and Mia in the meeting — runs on one language-model gateway the organization selects: Azure OpenAI in the EU Data Zone by default, Google Vertex AI on the EU multi-region endpoint or Amazon Bedrock in Frankfurt by choice, each in InterMIND's own tenant. We explained the reasoning in [Meeting AI on your own cloud gateway](https://intermind.com/blog/meeting-ai-on-your-own-cloud-gateway): for most organizations that gateway is already on the approved sub-processor list, so an AI feature adds no new company to the list. Speech-to-text for voice notes follows the same rule on the default gateway today, and each of the three gateways has a speech service next to its language models — which is what this post measures: | Gateway | Speech service | Region used in this test | How the API takes a recording | | ----------------------------------- | --------------------------------------- | ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Azure OpenAI** (Microsoft) | Azure AI Speech, fast transcription API | Sweden Central | One request for a file up to 5 hours and 500 MB ([fast transcription docs](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create){rel=""nofollow""}, checked September 2026) | | **Google Vertex AI** (Google Cloud) | Cloud Speech-to-Text v2, Chirp 3 model | `eu` multi-region | Synchronous recognition is limited to 60 seconds and 10 MB; longer audio goes through batch or streaming recognition ([sync limits](https://docs.cloud.google.com/speech-to-text/v2/docs/sync-recognize){rel=""nofollow""}, [Chirp 3](https://docs.cloud.google.com/speech-to-text/v2/docs/chirp_3-model){rel=""nofollow""}, checked September 2026) | | **Amazon Bedrock** (AWS) | Amazon Transcribe, streaming | eu-central-1 (Frankfurt) | A streaming session over HTTP/2 or WebSocket; input is PCM, FLAC or Ogg-Opus ([streaming docs](https://docs.aws.amazon.com/transcribe/latest/dg/streaming.html){rel=""nofollow""}, checked September 2026) | The recogniser is told the speaker's own language in every case — the language a member set in their profile — because automatic language identification proved unreliable on short clips in our testing: a four-second Russian note came back as English. That is how the product calls Azure today, and the test calls the other two the same way. ## What we measured **The set.** 153 clips in 17 languages: 136 dialogue turns — two business dialogues (a contract negotiation and a daily stand-up) spoken by the product's two synthetic voices in ten languages — plus 17 formal passages, the FLORES-200 business sentences of our [public translation benchmark](https://intermind.com/benchmark/methodology) read by a synthetic voice, one per language and 71 to 109 seconds long. The dialogue turns are 3 to 30 seconds, the length of a real voice note. **The metric.** Word error rate (WER) against the reference text — the fraction of words substituted, inserted or deleted — after normalizing case, punctuation and whitespace; Chinese and Japanese are compared per character. Character error rate was recorded alongside and tells the same story. **The harness.** One script, one machine, one hour on 2026-09-16, each engine over all 153 clips. Azure and Amazon Transcribe took each clip whole. Google's synchronous recogniser takes at most 60 seconds, so the 17 formal clips were cut at silences into pieces under 55 seconds and the transcripts joined; the 136 dialogue clips went whole. Amazon Transcribe wants audio at a real-time pace, so the harness fed it four times faster than real time; its latency figure below is therefore a floor set by the feed, not the service. **What this is not.** Synthetic voices in quiet audio, not field recordings from a phone in a car. One day, one run per clip. It is a comparison on the audio our own translation pipeline is tested on, in the languages our users write in — not a leaderboard. ## Results: word error rate per language Mean WER on the clips of each language; every engine returned a transcript for all 153 clips. | Language | Clips | Azure AI Speech | Google Chirp 3 | Amazon Transcribe | | ------------------------------ | ----- | --------------- | -------------- | ----------------- | | Arabic | 13 | 32% | 46% | 26% | | Chinese | 13 | 3% | 3% | 8% | | Czech | 1 | 1% | 2% | 3% | | Dutch | 1 | 2% | 2% | 3% | | English | 21 | 2% | 5% | 2% | | French | 13 | 5% | 11% | 12% | | German | 13 | 7% | 9% | 13% | | Hindi | 13 | 10% | 10% | 12% | | Hungarian | 1 | 9% | 7% | 8% | | Italian | 1 | 1% | 1% | 3% | | Japanese | 13 | 6% | 5% | 5% | | Korean | 1 | 9% | 11% | 11% | | Polish | 1 | 1% | 1% | 2% | | Portuguese (Brazil) | 13 | 5% | 4% | 6% | | Russian | 21 | 14% | 10% | 14% | | Spanish | 13 | 6% | 5% | 6% | | Turkish | 1 | 4% | 3% | 4% | | **All 153 clips** | 153 | **9%** | **10%** | **10%** | | Dialogue turns only | 136 | 9% | 11% | 10% | | Formal passages only | 17 | 4% | 5% | 5% | | Processing time ÷ audio length | | 0.10 | 0.22 | 0.41 (feed-bound) | Languages with a single clip (the formal passage only) are shown for completeness; a one-clip figure is a data point, not a rate. ## What the numbers say - **On the whole set the three services are within one point of each other:** 9%, 10% and 10%. Every one of the 153 clips came back with a transcript from every engine — coverage of the 17 languages is complete on all three. - **The differences are per language, and they go both ways.** Azure had the lowest error rate on French (5% against 11% and 12%) and German (7% against 9% and 13%), and tied for lowest on English (2%, with Amazon Transcribe) and Chinese (3%, with Google). Amazon Transcribe had the lowest on Arabic (26% against 32% and 46%). Google had the lowest on Russian (10% against 14% and 14%), Portuguese, Hungarian and Turkish. - **Arabic is hard for all three.** The best result on the Arabic dialogue clips is one word in four wrong. That is consistent with what we saw on the translation side, where we withdrew Arabic from the meeting language picker in August 2026 until quality clears our bar ([how many languages we support](https://intermind.com/blog/how-many-languages-do-you-support)). - **Processing time is well under real time on all three.** A 30-second note takes about three seconds on Azure and about seven on Google in this harness; the Amazon figure is dominated by the paced feed. ## Why Azure AI Speech stays the default Three reasons, in the order that decided it. **1. The default gateway is Azure.** An organization that has not chosen a gateway runs its AI features on Azure OpenAI in the EU Data Zone, so its voice notes are transcribed by Azure AI Speech in the same tenant. No additional sub-processor, no additional region. Microsoft states that Azure Speech does not store or process data outside the region of the Speech resource ([regions page](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/regions){rel=""nofollow""}, checked September 2026); our resource is in Sweden Central, which is listed for fast transcription. **2. The API shape fits a voice note.** A voice note in InterMIND can be up to ten minutes long ([voice notes](https://intermind.com/docs/chat/voice-notes)). Azure's fast transcription takes the whole recording in one request. Google's synchronous recognition stops at 60 seconds, so a ten-minute note needs batch recognition through a storage bucket or a streaming session; Amazon Transcribe streams, but takes PCM, FLAC or Ogg-Opus rather than the formats phones and browsers record in, so the audio is transcoded first. Both are solvable — the harness solves them — but they are more moving parts in the path of every note. **3. The numbers do not argue against it.** At 9% against 10% and 10%, no engine on this set is enough better to justify moving voice notes off the default gateway. If Google or Amazon had come in at half the error rate, this post would say so. ## What this means for organizations on Vertex AI or Bedrock If your organization selected Google Vertex AI or Amazon Bedrock as its gateway, your AI features run there. Voice notes in those organizations currently arrive as a recording without a transcript: we have measured Google Cloud Speech-to-Text and Amazon Transcribe, as this post shows, but have not wired them into the product yet. The permissions and the integration code exist; this post is updated when they are in the path of every note. Until then, a voice note in a Vertex AI or Bedrock organization is a playable recording; an organization that switches its gateway to Azure gets transcripts on the notes sent from then on. ## FAQ **Which speech-to-text service does InterMIND use?** For voice notes in chat, Azure AI Speech (fast transcription API) in InterMIND's own Azure tenant in Sweden Central — the speech service of the default AI gateway. Live speech in meetings is a different path: it runs on InterMIND's own media engine, the Mind API, hosted at OVH in France, and never touches a cloud speech service ([where one meeting runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs)). **Is Azure AI Speech more accurate than Google Speech-to-Text or Amazon Transcribe?** On our set of 153 voice-note clips in 17 languages, measured on the same day with the same harness, Azure AI Speech had a mean word error rate of 9%, Google Cloud Speech-to-Text (Chirp 3) 10% and Amazon Transcribe 10%. Per language the order changes: Azure was lowest on French, English and Chinese, Amazon Transcribe on Arabic, Google on Russian. On a different set of recordings the ranking can differ; the table above is the evidence for ours. **What is word error rate, and how was it computed here?** Word error rate is the number of substituted, inserted and deleted words divided by the number of words in the reference text. We normalize case, punctuation and whitespace before comparing, and compare Chinese and Japanese per character because those scripts do not separate words with spaces. A rate of 9% means roughly one word in eleven differs from the reference. **Does a voice note's audio leave the EU?** No. The recording is stored in InterMIND's object storage in the EU, and the speech service that transcribes it runs in an EU region: Sweden Central on Azure, the `eu` multi-region on Google Cloud, Frankfurt on AWS. The full list of parties and regions is on the [subprocessors page](https://intermind.com/legal/subprocessors) and the [trust page](https://intermind.com/trust). **Why not recognise speech client-side, in the app, so the audio never leaves the phone?** We measured that too, in September 2026. Chrome's built-in recogniser with local processing recognised 0 of 17 formal clips across the product languages, and the language coverage of client-side recognisers is far narrower than the 17 languages in the table above. Client-side recognition is a direction we re-measure as the platforms improve; today the gateway path is the one that works for every member in every language. **Can our organization choose which speech service transcribes its voice notes?** Not separately: the AI gateway is what an organization admin selects on the Integrations page. On the default gateway, voice notes are transcribed by Azure AI Speech. On Vertex AI and Amazon Bedrock, voice notes are not transcribed yet — see the section above. **How long can a voice note be, and does the API limit it?** Up to ten minutes. Azure's fast transcription accepts files up to 5 hours and 500 MB in one request, so a note is transcribed in a single call. Google's synchronous recognition accepts 60 seconds and 10 MB, which is why the harness cut the long clips into pieces at silences. **Why does the recogniser get told the speaker's language instead of detecting it?** Because a voice note is short. On a four-second clip, automatic language identification can return the wrong language — a Russian test note came back as English; a member's profile language is right nearly every time. The recogniser gets that language, and only when it is unknown does it get the room's languages as candidates. **Is the meeting audio transcribed by the same service?** No. Live speech in a meeting is recognised and translated on InterMIND's own engine (the Mind API) on the media server that carries the call, hosted at OVH in France — see [where one meeting runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs). The cloud gateway sees text, never the audio of a call ([meeting AI on your own gateway](https://intermind.com/blog/meeting-ai-on-your-own-cloud-gateway)). **Will you publish the results again?** The harness runs on one command, and every engine's permissions are in place, so the table can be re-measured when a vendor ships a new model. When it changes the picture, this post is updated with the date. --- ## See it for yourself - **[Read how voice notes work](https://intermind.com/docs/chat/voice-notes)** — recording, the ten-minute limit, and where the audio goes. - **[See the subprocessors list](https://intermind.com/legal/subprocessors)** — vendor, country, purpose and region for every party that processes your data. - **[Try the live demo](https://intermind.com/demo)** — the production translation pipeline on your own audio, no signup. --- *Sources: Microsoft — Azure AI Speech fast transcription ([learn.microsoft.com](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create){rel=""nofollow""}) and Speech regions table ([learn.microsoft.com](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/regions){rel=""nofollow""}); Google Cloud — Chirp 3 model ([docs.cloud.google.com](https://docs.cloud.google.com/speech-to-text/v2/docs/chirp_3-model){rel=""nofollow""}), synchronous recognition limits ([docs.cloud.google.com](https://docs.cloud.google.com/speech-to-text/v2/docs/sync-recognize){rel=""nofollow""}) and supported languages ([docs.cloud.google.com](https://docs.cloud.google.com/speech-to-text/v2/docs/speech-to-text-supported-languages){rel=""nofollow""}); AWS — Amazon Transcribe streaming ([docs.aws.amazon.com](https://docs.aws.amazon.com/transcribe/latest/dg/streaming.html){rel=""nofollow""}), endpoints and quotas ([docs.aws.amazon.com](https://docs.aws.amazon.com/general/latest/gr/transcribe.html){rel=""nofollow""}) and supported languages ([docs.aws.amazon.com](https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html){rel=""nofollow""}); all checked September 2026. Measurement: InterMIND speech bench, 2026-09-16, 153 clips, 17 languages.* # Language translator: how a voice translator actually works, and where it stops - **Four different tools share the name.** Text translators for writing, phone apps relaying a phrase at a time, earbuds for one person facing you, live meeting translation for a whole conversation. - **Same pipeline, different timing and audience.** A tool that waits until you finish leaves gaps, and a phone app translates for the two people holding it, not a room. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, notes and documents, per listener, live. Guests join free by link, no account; you pay only for active members. "Language translator" is a word that covers four quite different tools. A **text translator** (DeepL, Google Translate) turns typed text from one language into another. A **phone voice translator** listens, then reads a translation back. **Earbud translators** whisper a translation into your ear. And **live meeting translation** runs a whole conversation in several languages at once, each participant hearing it in their own. They all get called the same thing, and they are not interchangeable. This guide separates them, explains how the voice ones work under the hood, and names the line where each one stops. --- ## The four kinds, briefly ### Text translator The workhorse for anything written: paste a paragraph, get it back in another language. Built for documents, emails, a website. It doesn't touch speech, and it's one block at a time — not a conversation. ### Phone voice translator Open an app, speak, and it plays back (or shows) the translation, then the other person answers into the same phone. Perfect for a phrase — a menu, a direction, a hotel desk. The mechanic is a **relay**: speak → transcribe → translate → speak back, one turn at a time. It works because the exchanges are short and you pass the device back and forth. ### Earbud translator AirPods with Live Translation, Pixel Buds, dedicated translator earbuds. You wear them and hear the other person translated in your ear. Nicer than staring at a screen — but it's **one-to-one, and needs matching gear on both sides.** Built for a traveler and a local, not for a room of people. ### Live meeting translation The different one. Here the *room* is multilingual: everyone speaks their own language and hears everyone else in **their** language, live, for the whole meeting. No passing a phone, no matching earbuds. It's the only one of the four that holds a real conversation together. --- ## How a voice translator actually works Under the hood, a spoken-language translator is a short pipeline: 1. **Speech recognition** turns what you said into text. 2. **Translation** converts that text into the target language. 3. **Speech synthesis** (for the voice kind) speaks the result. Two things decide whether it feels live or clunky: - **When it translates.** If it waits for you to finish, then translates, you get consecutive interpretation with a synthetic voice — you feel every gap. If it keeps pace as you talk, it feels live. - **Who it translates for.** A phone app translates *for the two people holding it*. Live meeting translation translates the *whole room for everyone*, each into their own language, simultaneously — that's a harder problem and a different architecture. The full version of how the live kind works is in our foundational guide, [*Real-time meeting translation: how it works, and how to evaluate one*](https://intermind.com/blog/real-time-meeting-translation), and the engineering detail is in [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines). --- ## Which one do you actually need? - **Something written?** — a text translator. - **A phrase, one exchange with a stranger?** — a phone voice translator. Don't over-buy. - **Face-to-face with one person, both of you equipped?** — earbuds. - **A conversation — a call, a meeting, several people, back-and-forth?** — live meeting translation, because the others turn every exchange into a relay and every extra person into a broken assumption. --- ## Where InterMIND fits InterMIND is the fourth kind: a language translator for live conversations, built as real-time meeting translation. It starts with one person: you open the room and send the link; the others join free, without an account, each in their own language. - **23 languages live on voice**, chat and shared notes — any mix, no English anchor, no regional gate, no five-language beta. ([The full end-to-end translation stack](https://intermind.com/features/realtime-translation) is its own page.) - **Per-listener audio, live.** Each participant hears the meeting in their own picked language at the same time — five people, five languages, one call. - **Webinars and conferences included** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant on their own listening language: [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation). - **Documents too** — drop a PDF or DOCX into the meeting and each viewer gets it in their language, 30 languages on files. - **Quality you can audit.** Per-language-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark), with the methodology written down. A text translator is right for a document. A phone app is right for a phrase. Earbuds are right for one person in front of you. When it's a *conversation*, that's the job InterMIND was built for. --- ## Try it - **[Try the live demo](https://intermind.com/demo)** — *hear* a real meeting translated live, per listener, in any of 23 languages — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month translation quality on real traffic, methodology included. - Start with the category guide: [*Real-time meeting translation*](https://intermind.com/blog/real-time-meeting-translation). - Comparing specific language pairs? See the voice-pair guides for [English ↔ Italian](https://intermind.com/blog/traduttore-inglese-italiano-vocale), [French ↔ Italian](https://intermind.com/blog/traduttore-francese-italiano-vocale), [Spanish ↔ Italian](https://intermind.com/blog/traduttore-spagnolo-italiano-vocale), [Italian ↔ Russian](https://intermind.com/blog/traduttore-italiano-russo-vocale), [Romanian ↔ Italian](https://intermind.com/blog/traduttore-rumeno-italiano-vocale) and [Hindi ↔ English](https://intermind.com/blog/hindi-to-english-voice-translator). - The same three-way split, written for another market: [Italian](https://intermind.com/blog/traduttore-vocale), [French](https://intermind.com/blog/traducteur-vocal), [Spanish](https://intermind.com/blog/traductor-de-voz), [Portuguese](https://intermind.com/blog/tradutor-de-voz), [Turkish](https://intermind.com/blog/sesli-cevirmen). - Booked interpreters instead of software? [Simultaneous interpreter: human, RSI platform, or AI](https://intermind.com/blog/simultandolmetscher) sets the three next to each other. --- ## FAQ **How does a voice translator work?** It's a three-step pipeline: speech recognition turns what you said into text, machine translation converts the text, and speech synthesis speaks the result. Whether it feels live depends on *when* it translates (as you talk vs. after you pause) and *who* it translates for (two people holding a phone vs. a whole room). **What's the difference between a phone translator app and live meeting translation?** A phone app is a relay — speak, wait, pass the device — built for one phrase at a time. Live meeting translation runs the whole conversation in several languages at once, each participant hearing every speaker in their own language, simultaneously. **Do translator earbuds work for a group conversation?** Earbud translation (AirPods Live Translation, Pixel Buds) is one-to-one and generally needs matching gear or a shared screen on the other side. For a call or meeting with several people it breaks down — that's the job of live meeting translation. The earbud case in full: [what AirPods Live Translation does well, and where a meeting needs more](https://intermind.com/blog/airpods-live-uebersetzung). — The Mind.com Team --- *Sources: [Apple — Live Translation with AirPods](https://support.apple.com/en-us/123185){rel=""nofollow""}, [Google — Translate with Pixel Buds](https://support.google.com/googlepixelbuds/answer/7573100){rel=""nofollow""}, checked August 2026. Vendors change features and language lists over time — check their pages for the current state.* # Stand-up meeting: format, daily agenda, async variant — and what the channel does between stand-ups (2026) - **A short daily meeting of one team.** Fifteen minutes at most: what each person finished, will finish by tomorrow and is blocked by; blockers are named, not solved. - **The hard part is between stand-ups.** Teams, Zoom, Google Workspace and Slack leave one document per meeting in the room's language, not the reader's. - **InterMIND keeps the whole channel in each member's language,** chat, notes and every recap, next to Teams or Slack rather than instead of them. Guests join free by link, no account; you pay only for active members. A stand-up meeting is a short daily meeting of one team, held at the same time every working day, in which each person says three things: what they finished since yesterday, what they will do until tomorrow, and what is blocking them. Fifteen minutes is the ceiling, not the target. The name comes from the habit of standing for it so that nobody settles in — a stand-up that is comfortable has already run too long. It exists to surface blockers early, not to solve them, and not to report to a manager: the audience is the team, and the output is a short list of blockers with a name next to each. This post is the format: what a stand-up is and what it isn't, the six rules that keep it one, the three questions and the version that works better, a daily agenda you can copy, three filled-in variants, and the asynchronous stand-up for a team that is never awake at the same hour. The last section is about the part most guides skip — the twenty-three hours and forty-five minutes between two stand-ups, where the blocker either gets cleared or gets repeated tomorrow — and what the tools a team already runs on do with that list. ## What a stand-up is — and what it isn't | | Stand-up | Status meeting | Weekly team meeting | | ------------------------- | ------------------------------------------------ | ----------------------------------- | --------------------------------------- | | **Purpose** | Surface blockers while they are cheap | Tell the manager where things stand | Decide, align, announce | | **Length** | 15 minutes or less | 30–60 minutes | 30–60 minutes | | **Cadence** | Every working day, same time | Weekly or on request | Weekly | | **Who speaks** | Everyone, one minute each | Each person to the manager | Owners of the agenda items | | **Who it is for** | The team — the people who can unblock each other | The person who asked for it | The team and whoever needs the decision | | **What it leaves behind** | A list of blockers, each with a name | A report | Decisions and action items | The two failure modes are the two columns to the right. A stand-up that drifts into a status meeting is the one where each person addresses the lead instead of the team, and the rest of the room waits for its turn. A stand-up that drifts into a team meeting is the one where two people start solving a blocker in front of six who cannot help — the first "let's take that offline" is the facilitator's whole job. A related term: the **daily scrum** is the stand-up as Scrum defines it — a 15-minute event for the Developers of one Scrum Team, held every day of the Sprint to inspect progress toward the Sprint Goal and produce a plan for the next day. The 2020 edition of the Scrum Guide prescribes no format for it at all; the Developers choose whatever structure they want. "Stand-up" is the general form any team uses, Scrum or not; everything below applies to both. ## The format: six rules 1. **Same time, same place, every working day.** The point of a daily meeting is that nobody has to schedule it. Pick the earliest hour everyone is reliably present and do not move it for a visitor. 2. **Fifteen minutes is the ceiling.** Eight people at one minute each is eight minutes; the rest is for naming who pairs on what. A team that regularly needs the full fifteen is too large for one stand-up, or is solving things in it. 3. **One team.** The people who can unblock each other. If half the room never has anything to say to the other half, it is two stand-ups. 4. **Each person: since yesterday, until tomorrow, blocked by.** Finished, not "worked on"; the next concrete thing, not the whole week; and the blocker with the name of who could clear it, if known. 5. **Blockers are named, not solved.** Two sentences to describe it, then it goes to the list with the two names who will talk after. Anything that takes more than two sentences is a conversation, and conversations happen after the stand-up. 6. **It leaves a list behind.** The blockers of today, with an owner each, somewhere the whole team reads — and the list of yesterday checked against it: cleared, still open, or dropped. ## The three questions — and the version that works better The classic three questions are *What did I do yesterday? What will I do today? What is blocking me?* They are a fine starting shape and they have one known problem: the first two are answered to the manager. "Yesterday I worked on the export, today I'll continue on the export" is a report, carries no information for anyone else in the room, and takes a minute of eight people's time. Two adjustments fix most of it: **Anchor to outcomes, not activity.** "Since yesterday I finished X; until tomorrow I will finish Y; I am blocked on Z by W." *Finished* and *will finish* force a concrete claim that is true or false the next morning; "worked on" is never false. **Walk the board, not the people.** Instead of going round the room, go down the work items in priority order and let whoever holds each one say what it needs to be done. People with nothing on the board say nothing; the item that is stuck gets named by the work, not by who is embarrassed to raise it. For a team with a visible board this is the single most effective change; for a team without one, the round-robin with outcome wording is close enough. A rule in either shape: the person speaking addresses the team, and the facilitator — rotating, one week each — stands at the side, not the front. ## How to run one: before, during, after **Before (two minutes, the facilitator):** the board is current, and the facilitator has yesterday's blocker list open. Not the whole backlog — the list from the last stand-up, so that each item can be checked in one word. **During (fifteen minutes, the team):** start on time with whoever is there. Go round, or walk the board. One minute each; the facilitator says "and the blocker?" to anyone who finished without one and "offline" to any two people who start solving. Check yesterday's blockers: cleared, open, dropped — one word each. Parking lot for anything that is not a blocker but needs a slot: a decision, a question for someone absent. End by reading the list: blocker, who, who is helping, by when. **After (five minutes, the facilitator):** the blocker list goes where the team reads, with an owner for each item and the parking-lot items given a time. The pairs talk. Tomorrow's stand-up starts from this list — which is why it has to live somewhere findable, not in the facilitator's head. ## A daily stand-up agenda template Copy the block, replace the brackets, and keep it to one screen — a stand-up agenda that needs scrolling is a team-meeting agenda. > **Team stand-up — \[day], \[time] — 15 min — \[facilitator this week]**:br**Purpose:** surface today's blockers; nothing else. :br**1. Yesterday's blockers** — facilitator — 2 min :br > \[blocker from yesterday] — \[owner] — cleared / open / dropped :br > \[blocker from yesterday] — \[owner] — cleared / open / dropped :br**2. Round** — each person — 1 min each — *information*:br > Since yesterday: \[finished]. Until tomorrow: \[will finish]. Blocked by: \[what, and who could clear it]. :br**3. Blockers that need two people** — pairs named — 3 min — *taken offline*:br > \[blocker] — \[who has it] + \[who helps] — \[when they talk] :br**4. Parking lot** — facilitator — 2 min :br > \[not a blocker, needs a slot] — \[when, where] :br**Leaves behind:** today's blocker list with a name per item, posted in the team channel before \[time + 20 min]. ## Three variants with the agenda filled in ### 1. A software team of eight, one time zone > **Team stand-up — Tuesday 09:30 — 15 min — Priya**:br**1. Yesterday's blockers** — staging certificate (Tom) — cleared; design review for the export screen (Lena) — open, review moved to today 11:00 :br**2. Round** — eight people, walking the board from the top: three items in review, two in progress, one blocked :br**3. Blockers that need two people** — the export screen cannot ship without the API change (Lena + Tom, 11:30) :br**4. Parking lot** — release date for the mobile build, needs Marco back on Thursday :br**Leaves behind:** two open blockers, two pairs, one parked item with a date. ### 2. A distributor's sales team in two countries > **Daily huddle — 08:45 CET / 09:45 EET — 15 min — Ana**:br**Purpose:** surface what is stopping a deal or a delivery today. :br**1. Yesterday's blockers** — the Bucharest warehouse confirmation (Radu) — cleared; price list for the new line (Ana) — open, finance promised noon :br**2. Round** — six people: each names the one deal or delivery they will move today and what it is waiting on :br**3. Blockers that need two people** — a client's customs paperwork is in a language only Radu reads (Radu + Sofia, 10:00) :br**4. Parking lot** — the trade-fair stand, Friday's team meeting :br**Leaves behind:** two open items, one pair, posted in the channel in each member's language. ### 3. A team across three time zones — the asynchronous variant > **Async stand-up — every working day by 10:00 UTC — #team-daily**:br**Purpose:** the same three parts, written or spoken, one message per person. :br**1. Each person, by 10:00 UTC:** since yesterday / until tomorrow / blocked by — one message, text or a one-minute voice note :br**2. Blockers:** anyone who can help replies in the thread of that message, not in a new one :br**3. Yesterday's list:** the facilitator checks it against the new messages — cleared / open / dropped — and posts today's list by 10:20 UTC :br**4. Twice a week, 14:00 UTC:** a fifteen-minute live call for the blockers a thread could not clear :br**Leaves behind:** the same list as the live version, in the same place, with the threads under it. ## The asynchronous stand-up: written or spoken, by a set time A live stand-up needs everyone awake, present and free at the same hour. A team across more than two time zones, a team with part-time members, field staff who are driving at nine, a clinic whose front desk cannot leave the desk — these teams either skip the stand-up or hold it with half the team. The asynchronous version keeps the format and drops the requirement of a shared hour. The rules that keep an async stand-up a stand-up: **one message per person, by a set time**, in one agreed channel — not a form, not a document everyone edits, because a message has an author, a time and a thread. **The same three parts** in the same order, so that a message can be read in ten seconds. **A thread per blocker**, so that the offer to help lands under the problem and the rest of the channel stays readable. **The facilitator closes it** at the set time with the list — the one output a stand-up has — and checks yesterday's list in the same message. And **a live call on a fixed cadence**, twice a week or once, for the blockers that a thread did not clear: the async stand-up is a replacement for the hour, not for ever speaking. Spoken works as well as written when the team allows it. A one-minute voice note from a phone, recorded on the way in, is often more honest than a sentence typed at a desk — people say the blocker they would have edited out — and a channel that transcribes the note keeps it searchable and lets the rest of the team read it rather than listen. What the async version loses is the moment when someone hears a blocker and says "I had that last week". The thread-per-blocker rule and the fixed live slot are the two ways to get it back; a team that drops both has a daily report, not a stand-up. ## Where the stand-up lives in the tools you already use A stand-up is a recurring meeting on the calendar plus a place where the blocker list is posted. Documented behaviour only, from the vendors' own pages; each cell names the month its fact was checked. | Platform | Where the stand-up happens | What stays between stand-ups | | -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Microsoft Teams** | A recurring meeting; *Notes* in the meeting controls during the call, or *Add an agenda* in the meeting's Details when scheduling — a Loop component that any attendee or organizer can edit, with tasks assigned by tagging people (checked October 2026) | The notes are saved automatically and reachable from the Teams calendar and the meeting recap; external attendees cannot access or edit them (checked October 2026). The recap — recording, transcript, shared files, notes, agenda and follow-up tasks — is available after meetings that were recorded or transcribed; the AI parts require Teams Premium or a Microsoft 365 Copilot license, and the recap is generated in the language the meeting was held in (checked August 2026) | | **Zoom Workplace** | A recurring meeting; AI Companion can draft the agenda when the meeting is scheduled (checked October 2026) | Meeting summary with AI Companion — quick recap, summary, next steps — on paid Zoom Workplace plans; sent by email, listed on the Summaries page and postable to the meeting's group chat in Team Chat. Participants receive it when the host chose to share it, only the host can edit it, and unauthenticated users do not receive the email. The documentation does not state that a summary can be produced in a different language per participant (checked August 2026) | | **Google Workspace** | A recurring Calendar event with a Meet link; on eligible Workspace editions and Google AI plans, *Take notes for me* is switched on in Calendar when the event is created (checked October 2026) | The notes arrive as a Google Doc after the meeting, shared with all guests, organization guests or hosts only, per the setting; the feature supports one language at a time — multiple languages spoken in the same meeting are not supported (checked October 2026) | | **Slack** | A huddle in the team channel, with "a dedicated message thread to share notes, links, and files"; or the written stand-up as messages in the channel (checked October 2026) | A canvas from the meeting-agenda template stays in the channel; it holds what someone types into it, and what was said in a huddle is not in it unless a person writes it (checked October 2026) | Each of the four produces one document or one summary per meeting, in the language it was written or held in; none of the pages cited states that a reader gets it in a language of their own. Where that matters to the team, the next section is one way the job gets done; where it does not, the table above is the whole answer and any of the four will do. ## What the channel does between stand-ups In InterMIND a stand-up is a channel's meeting. A channel is a persistent room: its chat is kept between sessions, its meeting link is permanent, and the recurrence is set once, in Google Calendar or Outlook, on an event that carries that link — so the same room opens every morning, with its chat and its recaps. Today's blocker list is a message in the channel; yesterday's is one scroll up; the one from three Tuesdays ago is in search. And the whole space stays in each member's language: a message typed in Spanish is read in Romanian by the colleague in Bucharest and in Spanish by the sender, with the original one click away — the chat, the notes, the recap and the files, not one meeting at a time. During the stand-up, the facilitator can put the list on everyone's screen: a note in the channel, **Share to conference** from its message menu, and it opens for every participant in their own language while the sharer edits it live — cleared, open, dropped, typed in as the round goes. The same works for a recap message from yesterday. After the stand-up, the recap: a summary of what was said and the action items with an owner each, every item tied to the moment in the transcript where it was taken on. It goes by email to each signed-in participant, as a message into the channel chat and as a link in the calendar event, in the reader's own language rather than the language the stand-up was held in. The channel keeps the recap of every past session, not only the latest, so the list of two weeks ago is a search away. In an organization with team status pages on, the open items of earlier sessions are judged when the next recap is written: reported finished, marked done; discussed but not finished, marked not done with the reason in the words of the meeting; not brought up, left open — the check of yesterday's list, done on the organization's status page rather than from the facilitator's memory — and at the start of the next session Mia names the open items and their owners. Team status pages are a preview feature: an organization's admin switches them on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). The async variant lives in the same channel. A voice note is the microphone button in the channel composer — from the web or the phone app, up to ten minutes, transcribed within seconds — and each teammate reads it in their own language, with a play button for the original; it is searched, quoted and forwarded like any text message. A channel also has its own email-in address, created by the host, so an update from someone who is in a vehicle, on a ward or in a system that only sends email lands in the channel under the sender's name. And a copy of every recap can go by email to up to ten addresses — a CRM inbox, a client's project address — set once per channel in its settings, on every plan. A stand-up is members-only. A channel needs membership: a colleague outside the team's workspace is added by email invitation onto a free account and becomes a member who reads the channel in their language. Someone who needs to be in one session only — a client for one morning, a contractor for one hand-over — joins an ad-hoc meeting by link, from a phone, without an account, hears the meeting in their language and gets nothing afterwards; the chat of that call is wiped when it ends. The host provides the space and, on a paid plan, pays only for the [members active in the previous 28 days](https://intermind.com/pricing) — joined a meeting, wrote in a chat, asked Mia. A member on leave for a month keeps access and costs nothing that month; the stand-up they come back to is in the channel, with its lists. - **[Open a complete recap](https://intermind.com/features/recap)** — summary, action items with the moment each was taken on, transcript. - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener. One habit survives any tool: the stand-up ends when the list is read aloud, and the list is posted before anyone goes back to work. ## FAQ **What is a stand-up meeting?** A short daily meeting of one team, held at the same time every working day and capped at fifteen minutes, in which each person says what they finished since yesterday, what they will do until tomorrow, and what is blocking them. Its purpose is to surface blockers early so the people who can clear them know the same morning; it is not for solving them and not a status report to a manager. It leaves behind a list of blockers with a name next to each. **What are the three questions in a stand-up meeting?** The classic three: *What did I do yesterday? What will I do today? What is blocking me?* A version that reports less and informs more replaces activity with outcomes — "since yesterday I finished X, until tomorrow I will finish Y, I am blocked on Z by W" — or walks the board by work item instead of going round the people, so that the stuck item is named by the work and not by whoever is holding it. **How long should a stand-up meeting be?** Fifteen minutes is the ceiling; most run eight to twelve. The arithmetic is one minute per person plus two or three for yesterday's list and for naming who pairs on each blocker. A team that regularly needs the full fifteen is either too large for one stand-up or is solving problems in it; the fix is to split the team or to move the conversation after the meeting, not to lengthen it. **Why is it called a stand-up meeting?** Because the team stands for it. The habit came from software teams in the 1990s who found that standing kept the meeting short — nobody settles into a chair and opens a laptop — and the name stuck even for teams that hold it sitting or on a call. The property it names is the length, not the posture: a stand-up held on video is still a stand-up if it is fifteen minutes and leaves a blocker list. **What is the difference between a stand-up and a daily scrum?** The daily scrum is the stand-up as defined by Scrum: a 15-minute event for the Developers of one Scrum Team, every day of the Sprint, to inspect progress toward the Sprint Goal and plan the next day. The 2020 edition of the Scrum Guide prescribes no format — no three questions — and leaves the structure to the Developers. "Stand-up" is the general form: any team, any method, same length, same purpose. Every stand-up guide applies to a daily scrum; the daily scrum adds the Sprint Goal as the thing every update refers to. **How do you run a stand-up meeting?** Same time every day, start with whoever is there, a rotating facilitator at the side. Check yesterday's blockers in one word each — cleared, open, dropped. Then the round or the board walk, one minute per person, with the facilitator asking "and the blocker?" of anyone who finished without one and saying "offline" to any two people who start solving. Park anything that needs a slot but is not a blocker. End by reading the list: blocker, who has it, who helps, when they talk — and post it where the team reads before anyone goes back to work. **What is an asynchronous stand-up?** The same three parts posted as one message per person, text or voice, by a set time in one agreed channel, instead of said aloud at the same hour. The rules that keep it a stand-up: the same order every day, a reply thread per blocker so help lands under the problem, a facilitator who closes it at the set time with the day's list and the check of yesterday's, and a short live call on a fixed cadence for the blockers a thread could not clear. Teams across time zones, part-time members and field staff use it; the risk is that it quietly becomes a daily report nobody reads, which the thread rule and the live slot are there to prevent. **Should the manager attend the stand-up?** As a member of the team, yes — with a one-minute update like everyone else and the same rule not to solve things in it. As an audience, no: a stand-up where each person addresses the manager is a status meeting at eight people's cost. If the manager's presence turns the round into reporting, the usual fixes are walking the board instead of the people and rotating the facilitator among the team, so that the manager is one voice in the round and not the reason for it. --- *Sources: [Scrum Guide — 2020 edition](https://scrumguides.org/scrum-guide.html){rel=""nofollow""}; [Microsoft — Take meeting notes in Microsoft Teams](https://support.microsoft.com/en-us/office/take-meeting-notes-in-microsoft-teams-3eadf032-0ef8-4d60-9e21-0691d317d103){rel=""nofollow""}; [Microsoft — Recap in Microsoft Teams](https://support.microsoft.com/en-us/teams/meetings/recap-in-microsoft-teams){rel=""nofollow""}; [Zoom — Using Meeting Summary with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058013){rel=""nofollow""}; [Zoom — Generating meeting agenda with AI Companion](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0081706){rel=""nofollow""}; [Google — Calendar & Meet settings for "Take notes for me"](https://support.google.com/meet/answer/16909639?hl=en){rel=""nofollow""}; [Google Meet — "Take notes for me" in Google Meet](https://support.google.com/meet/answer/14754931?hl=en&co=GENIE.Platform%3DDesktop){rel=""nofollow""}; [Slack — Use huddles in Slack](https://slack.com/help/articles/4402059015315-Use-huddles-in-Slack){rel=""nofollow""}; [Slack — Meeting agenda template](https://slack.com/templates/meeting-agenda){rel=""nofollow""}. Vendors change plans, features and language lists over time; check their pages for the current state. Each table cell names the month its fact was checked — the earliest checked August 2026, the latest checked October 2026.* # Team communication tools for distributed teams (2026): what the space does for each member - **For a distributed team the space is the office.** Three axes: who reads it in their own language, who hears the call in theirs, how history reads a month later. - **Every platform documents translation as a view.** Teams and Google Chat per reader, Slack and Zoom on request, WhatsApp on device, Telegram on Premium; history stays in the original language. - **InterMIND keeps the whole space in each member's language,** chat, meetings, files and the recap, by default. Guests join free by link, no account; you pay only for active members. Search "best team communication tools" or "internal communication tool" and you get the same ranking twenty times: number of integrations, free-tier caps, video quality, whether it plugs into Office or Google. Fine if you're picking a chat app for a team that sits in one office. A distributed team has a different relationship with the tool: the space *is* the office. The channel is where decisions get made at 11 pm in one time zone and read at 9 am in another; the history is the only record; and — for more teams than the lists admit — the members don't all write in the same language. This comparison is about what the space does for each member, not what it does for the admin. Scope: the tool your team talks in daily — chat, calls, and the history they leave. Employee-newsletter and intranet platforms are a different category and aren't here. Three axes decide it, and the table records one more fact beside them: 1. **Messages: does each member read the space in their own language — automatically, or one message at a time on request?** 2. **Meetings: does every participant hear the call in their own language, or does someone hold a license that the rest don't?** 3. **Afterwards: what does the history look like a month later — and in whose language?** The fact beside them, not ranked: where it lives — can you name the place (and jurisdiction) the messages, files and recordings sit in? Ten tools in three groups — the bundled platforms (Microsoft Teams, Slack, Google Chat with Meet, Zoom Team Chat), the messengers teams actually run on in much of the world (WhatsApp, Telegram), and the self-hosted set (Mattermost, Rocket.Chat, Element, Nextcloud Talk) — then us, with one table across all of them. Every competitor fact comes from the vendor's public documentation, checked August 2026, linked in the footer. --- ## The bundled platforms ### Microsoft Teams - **Messages:** a chat or channel message is translated on request (*Translate* above the message) or automatically — "Teams can automatically translate received messages" — in a list of 100+ languages, on desktop and mobile. No plan or license is named for this; an admin can switch it off. The article does not state that translated text is saved. - **Meetings:** translated captions in 31 languages need the **organizer to hold Teams Premium or Microsoft 365 Copilot**; the **Interpreter agent** (synthetic translated speech, 10 languages) is licensed **per listener** and metered at **20 hours per user per month**, in scheduled meetings only. Captions aren't saved; recordings keep original audio. Walkthrough: [Teams live translation](https://intermind.com/blog/teams-live-translation). - **Afterwards:** each message stays in the language it was written in; translation is a view. - **Where it lives:** in "the geographic region associated with your Microsoft 365 or Office 365 organization"; country-level residency (France, Germany, Italy, Norway, Poland, Sweden, Switzerland and others) is for **new tenants only** — existing EU tenants stay in the EMEA region. ### Slack - **Messages:** "Translate message" is an AI feature on **Business+ and Enterprise+**. You set a translation language in your preferences and translate a message on request; "translations are only visible to you, so other people will always see the original message." - **Meetings:** huddles — group huddles on Business+ and Enterprise+, 1:1 on Free and Pro. The AI feature guide lists translation for messages, not for huddle audio (checked August 2026). - **Afterwards:** the Free plan keeps **90 days of message history**; paid plans keep it all. Stored text is the original. - **Where it lives:** data residency on **Business+ and Enterprise+**: Frankfurt, Paris, Stockholm, Zurich, London documented for Europe; messages, canvases, files and the search index are covered, member profiles and usage analytics are not. ### Google Chat (with Meet) - **Messages:** "Translate for me" detects and translates messages **automatically, in-line**, in 120+ languages, as a per-user setting — with the **Gemini Business or Enterprise add-on, or the AI Meetings and Messaging add-on**. - **Meetings:** Meet's speech translation runs **between English and five languages, one pair per meeting**, as a **90-minute beta**, unavailable in recordings. Translated captions (text) cover more languages on Business Standard and above. Details: [Google Meet live translation](https://intermind.com/blog/google-meet-live-translation). - **Afterwards:** history per the admin's retention settings, in the original language; translation is what a reader sees. - **Where it lives:** data regions — **the United States or Europe** — on Business Standard and Plus, Enterprise, Frontline and Education editions; Chat messages, attachments and room names, and Meet recordings and transcripts are covered. Users on other editions "aren't covered by data region policies". ### Zoom Team Chat (with Meetings) - **Messages:** translated on request — "click the ellipsis icon… Click Translate. The message will be replaced by the translation", *Show Original* to revert — in 38 languages. Prerequisites: message translation enabled by the admin and **Advanced Chat Encryption disabled**. - **Meetings:** translated captions in 36 languages on Business Plus and Enterprise-tier plans (add-on otherwise); the **Voice translator** — synthetic translated audio in five languages — via the Live Translation add-on, desktop only. Walkthrough: [Zoom live translation](https://intermind.com/blog/zoom-live-translation). - **Where it lives:** Zoom's **EU Infrastructure** "hosts accounts for EU Education and Enterprise customers" and covers Meetings, Webinar, Chat and Phone; Zoom "does not transfer outside of or access data from outside this infrastructure unless a prior agreement with a customer is in place", with exceptions for legal requirements, trust-and-safety and service notifications. ## The messengers teams actually run on In much of the world the team's real communication tool is the one already on everyone's phone. Two of them have documented translation. ### WhatsApp (and the Business app) - **Messages:** since September 2025, "if you see a message in a different language, you can now simply long-press and tap 'Translate'" — in 1:1 chats, groups and Channel updates. **Android** users "will also be able to choose to turn on automatic translation for an entire chat thread", with six languages at launch (English, Spanish, Hindi, Portuguese, Russian, Arabic); **iPhone** uses Apple's translation in 19+ languages. "Translations occur on your device where WhatsApp cannot see them." Voice notes and calls aren't covered by the announcement. WhatsApp's own transcription of voice notes is a separate feature — [how it works and where it stops](https://intermind.com/blog/transcrever-audio-whatsapp). - **Meetings:** calls are end-to-end encrypted; no translation is documented for them. - **Afterwards:** "we do not retain your messages in the ordinary course of providing our Services to you. Once your messages are delivered, they are deleted from our servers." The history lives on each member's phone and in whatever backup they keep — which is also the answer to where it lives. - **Where it lives:** on the devices. The **WhatsApp Business app** "is built with the small business owner in mind" — a phone-first tool, not a tenant with an admin console. ### Telegram - **Messages:** "All users can translate individual messages by selecting them and tapping 'Translate'." **Premium** users "can translate entire chats, groups and channels in real time by tapping the Translate bar at the top" — listed in the Premium FAQ as "Real-time Chat and Channel Translation". The announcements don't size the language list. - **Meetings:** voice chats and video calls exist; no translation is documented for them. - **Afterwards:** cloud chats are kept on Telegram's servers and appear on every device; the translated view is per reader. - **Where it lives:** Telegram's cloud. If your team's decisions are made in Telegram groups, they can be mirrored into an InterMIND channel — where each member reads them in their own language — through the [InterMIND Telegram bot](https://intermind.com/blog/telegram-ingest-how-it-works); Telegram's Business chatbot feature (used for one-on-one chats) is available to Premium subscribers. ## The self-hosted set ### Mattermost - **Messages:** **Automatic channel translation** (beta, introduced in v11.5) on **Enterprise Advanced**: back-end is **LibreTranslate** ("a self-hosted, open-source machine translation engine") or **Agents** ("the Mattermost Agents plugin with a configured LLM backend"); an admin sets the *Languages allowed*, and "a worker picks up the post and translates it sequentially into each configured target language". A user's target language "is determined by their Mattermost display language". - **Meetings:** calls are a Mattermost feature; the auto-translation documentation covers channel posts. - **Afterwards / where it lives:** translations are produced on your own server, per configured language; Professional and Enterprise are self-hosted seat licenses, prices on request; a single-tenant Mattermost Cloud Enterprise exists. ### Rocket.Chat - **Messages:** Auto-Translate per room — "messages you receive in that room will be automatically translated into your selected language"; "each user receives translations based on their own selected language". Providers: **DeepL, Google Translate, Microsoft Translator, LibreTranslate**, with credentials supplied by the workspace administrator — so message text transits the provider you chose, unless it's LibreTranslate on your own host. - **Meetings:** through integrations — Jitsi, BigBlueButton, Pexip, Google Meet, Zoom. - **Afterwards / where it lives:** the **Starter** plan is free, "self-managed, self-hosted", "for technical evaluation or small teams of up to 50 users"; paid tiers are Commercial, Government and Defense (on-premises, private cloud or air-gapped), priced on request. The former Pro plan was retired on April 29, 2026. ### Element (Matrix) - **Messages and meetings:** "the entire platform is end-to-end encrypted by default", including **Element Call**. No message or voice translation is documented (checked August 2026). - **Where it lives:** **Community** — "free of charge frontend and backend", self-hosted; **Enterprise** per seat per month, self-hosted; **Sovereign** per deployment, air-gapped. ### Nextcloud Talk - **Meetings:** the **live\_transcription** app — "the transcription is done on your own server… while the translation is done using a translation task processing provider"; requires Nextcloud 33, the High-Performance Backend, and an NVIDIA GPU with at least 10 GB VRAM or a 4-thread x86\_64 CPU; 27 transcription languages listed. - **Messages:** translation goes through Nextcloud's translation API, backed by the **translate / translate2** apps on your server or another registered provider. - **Where it lives:** "a fully self hosted, on-premises audio/video and chat communication service" — "ideal for on-premises private cloud deployments or hosting with a trusted, local provider". ## InterMIND We build for the case the lists skip — a distributed team whose members read and speak different languages — so here is our side of the same four questions, stated the same way: - **Messages:** the space is translated for each member as its default behavior — chat and shared notes in **23 languages**, documents in **30**. No *Translate* button, no add-on: a member who reads Polish reads the channel in Polish. The numbers differ per pipeline on purpose — [there is no single honest answer](https://intermind.com/blog/how-many-languages-do-you-support). - **Meetings:** every participant picks their language on joining and **hears every speaker in it, simultaneously**, in the speaker's own voice. **Participants pay nothing and need no account** — guests join by link; the host's plan covers the room. ([Why participation is free](https://intermind.com/blog/free-for-participants).) - **Afterwards:** the meeting persists as a channel — chat history readable in each member's language, the recap delivered to signed-in members in theirs, documents in the same space. Messages your team leaves in Telegram can flow into the same channel. The audit of this axis: [how much of your meeting still exists a week later](https://intermind.com/blog/the-meeting-a-week-later). - **Where it lives:** **EU at every runtime hop** — translation on our own engine on dedicated servers in France, orchestration in Paris, database in Frankfurt, EU-resident storage; the recap on the AI gateway the organization selects, in an EU region (Azure OpenAI EU Data Zone by default), with zero data retention; document translation through one named EU sub-processor (DeepL). Vendor by vendor: [where one InterMIND meeting actually runs](https://intermind.com/blog/where-one-intermind-meeting-actually-runs). Quality is published monthly, per language pair, on real traffic — [/benchmark](https://intermind.com/benchmark) — because "our translation is great" is exactly the claim you shouldn't take from any vendor. --- ## The comparison, in one table | | Messages in each member's language | Meetings: everyone hears their own language? | Who pays for translation | History a month later | Where it lives | | ----------------------------- | ---------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- | --------------------------------------------------------------------------- | ---------------------------------------------------------------------- | | **Microsoft Teams** | On request or auto on view, 100+ languages; not stated as saved | Interpreter agent, 10 languages, per licensed listener, 20 h/month; captions 31 languages (organizer Premium/Copilot) | Organizer + each listener (Copilot) for voice; chat translation names no license | Original language per message | Microsoft region of the tenant; country residency for new tenants only | | **Slack** | On request, visible only to you; Business+ / Enterprise+ | Not listed for huddles | Business+ plan | Original text; Free keeps 90 days | Business+ residency: Frankfurt, Paris, Stockholm, Zurich, London | | **Google Chat + Meet** | Auto, in-line, 120+ languages; Gemini or AI Meetings & Messaging add-on | English ↔ 5, one pair per meeting, 90-min beta | Gemini add-on per user | Original text per retention policy | US or Europe data regions on Business Standard+ | | **Zoom Team Chat + Meetings** | On request, 38 languages, replaced on view; Advanced Chat Encryption off | Voice translator, 5 languages, add-on, desktop; captions 36 | Host plan tier or add-on | Original text | Zoom EU Infrastructure for EU Enterprise/Education accounts | | **WhatsApp** | Long-press → Translate, on device; Android auto-translate a thread (6 languages), iPhone 19+ | Not documented | Free (on device) | On each member's phone and backup; not on WhatsApp's servers once delivered | The devices | | **Telegram** | Individual messages free; entire chats/groups/channels in real time on Premium | Not documented | Premium subscriber, per reader | Telegram cloud, original language; translated view per reader | Telegram's cloud | | **Mattermost** | Auto, server-side into each allowed language (beta); target = display language | Not covered by the auto-translation docs | Enterprise Advanced + your LibreTranslate or LLM | Translated posts on your server | Self-hosted; single-tenant cloud on request | | **Rocket.Chat** | Auto per room, each user's language; DeepL / Google / Microsoft / LibreTranslate via admin key | Via integrations | Your provider key; Starter free to 50 users | Your server, per configured provider | Self-hosted, dedicated cloud, or air-gapped | | **Element** | Not documented | Element Call, end-to-end encrypted, original language | — | Original, end-to-end encrypted | Self-hosted; Community free | | **Nextcloud Talk** | Via the translate apps on your server | Live transcription on your server + translation via a task provider (GPU/CPU) | Your hardware | On your server | On-premises or a local provider | | **InterMIND** | Yes — 23 languages chat and notes, 30 documents, as the default | Yes — every participant hears every speaker in their language, 23 languages | Host's plan only; participants free, no account | Channel history in each member's language; recap to signed-in members | EU at every runtime hop: France, Paris, Frankfurt | --- ## How to choose (including when the space you have is enough) - **One language, one office, one time zone.** Keep whatever you have. Every tool above works for that team; the axes here don't apply. - **A Microsoft or Google tenant where the multilingual members are few:** Teams' message auto-translation or Google Chat's Translate-for-me covers the channels on the reader's side; the meeting layer is a licensing question — Copilot seats or Gemini add-ons for exactly those people. - **Translation on request is enough and the named city matters:** Slack on Business+ documents both, per reader, with the original text stored. - **The team already lives in WhatsApp or Telegram:** you get on-device or Premium translation of messages, history on phones or in Telegram's cloud, and nothing for calls. That's a workable daily tool and a fragile record — which is why the Telegram-to-channel mirror above exists. - **Nothing may leave your own servers, and you have people to run them:** Rocket.Chat (free to 50 users, translation via a provider key you hold), Mattermost Enterprise Advanced (beta auto-translation on your LibreTranslate or LLM), Nextcloud Talk (transcription on your own GPU), or Element if end-to-end encryption outranks translation entirely. - **The space itself is multilingual** — members replying to each other in three languages, guests without your licenses, a team that needs to reread last month's decision in their own language, and a compliance officer who wants a jurisdiction they can name: that's the case we built [InterMIND](https://intermind.com/chats) for. ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener in any of 23 languages. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, monthly translation quality on real traffic, with the methodology public. - **[Compare feature-by-feature](https://intermind.com/compare)** — InterMIND against each platform, every competitor cell sourced. --- ## FAQ **What are internal communication tools?** The software a team talks in day to day — chat platforms (Microsoft Teams, Slack, Google Chat, Zoom Team Chat), messengers used as workspaces (WhatsApp, Telegram), and self-hosted chat servers (Mattermost, Rocket.Chat, Element, Nextcloud Talk) — plus the calls and history they carry. Employee-newsletter and intranet platforms are a separate category: they broadcast to staff rather than host the team's conversation. **What is the best team communication app for a distributed team?** For a distributed team the deciding axes are what the history looks like a month later and whether every member reads the space in their own language. Documented options: Teams and Google Chat translate messages automatically on the reader's side (Google's with a Gemini add-on); Slack and Zoom translate on request; WhatsApp translates on the device; Telegram translates whole chats on Premium; Mattermost and Rocket.Chat translate on your server with your own engine or key; InterMIND translates the whole space — chat, meetings, documents, history — for every member on the host's plan. **Which team communication tools translate messages?** All of the above except Element and (for chat) Nextcloud without its translate apps — with different shapes: on request (Teams, Slack, Zoom, Telegram free, WhatsApp), automatic per reader (Teams auto-translate, Google Chat, WhatsApp Android per thread, Telegram Premium, Rocket.Chat), automatic server-side into configured languages (Mattermost, beta), or as the space's default for every member (InterMIND). The vendors' documentation describes the first three as views; none of them states that translated history is stored. **Which business messaging apps keep data in the EU or on our own servers?** In the EU by policy: Slack on Business+ (Frankfurt, Paris, Stockholm, Zurich), Google Workspace with a Europe data region on Business Standard and above, Zoom's EU Infrastructure for Enterprise and Education accounts, Microsoft Teams in the tenant's region (country residency for new tenants). On your own servers: Mattermost, Rocket.Chat, Element, Nextcloud Talk. InterMIND runs in the EU at every runtime hop — France, Paris, Frankfurt — as the default on every plan. **Can we use WhatsApp as our team communication tool?** Teams do, and the documentation is clear about the trade: messages are end-to-end encrypted and translated on the device (Android can auto-translate a thread in six languages, iPhone 19+), but WhatsApp does "not retain your messages in the ordinary course of providing our Services" — once delivered "they are deleted from our servers" — so the team's record lives on each member's phone and backup. The Business app "is built with the small business owner in mind". For calls, no translation is documented. **What is the best internal communication software for a multilingual team?** Compare the fences rather than the brands: which plan or add-on the translation sits on (Business+ for Slack, Gemini add-ons for Google, Copilot seats for Teams voice, Premium for Telegram, Enterprise Advanced for Mattermost), whether it's per reader or for everyone, and whether the history is kept in each member's language. On the last point the documentation of every platform above describes translation as a view; InterMIND keeps the channel, the recap and the documents readable in each member's own language. **What if the people we need to reach are customers, not colleagues?** That's a different shape — inbound in a language nobody on the team writes, answered without hiring for it. Written up separately in [multilingual customer support without hiring agents or writing code](https://intermind.com/blog/multilingual-customer-support). --- *Sources: [Microsoft — Translate a message in Microsoft Teams](https://support.microsoft.com/en-us/teams/chat/translate-a-message-in-microsoft-teams){rel=""nofollow""}, [Microsoft — Use live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Microsoft — Interpreter in Teams meetings and calls](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft Learn — Location of data in Microsoft Teams](https://learn.microsoft.com/en-us/microsoftteams/location-of-data-in-teams){rel=""nofollow""}, [Slack — Pricing](https://slack.com/pricing){rel=""nofollow""}, [Slack — Guide to AI features in Slack](https://slack.com/help/articles/25076892548883-Guide-to-AI-features-in-Slack){rel=""nofollow""}, [Slack — Data residency for Slack](https://slack.com/help/articles/360035633934-Data-residency-for-Slack){rel=""nofollow""}, [Google Workspace Updates — Translate for me in Google Chat](https://workspaceupdates.googleblog.com/2024/12/translate-for-me-in-google-chat.html){rel=""nofollow""}, [Google Meet — Learn about Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, [Google Workspace — Choose a geographic location for your data](https://knowledge.workspace.google.com/admin/compliance/choose-a-geographic-location-for-your-data){rel=""nofollow""}, [Google Workspace — Data covered by data regions](https://knowledge.workspace.google.com/admin/compliance/data-covered-by-data-regions){rel=""nofollow""}, [Zoom — Translating messages in Chat](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058113){rel=""nofollow""}, [Zoom — Enabling and configuring translated captions](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0059081){rel=""nofollow""}, [Zoom — Using the Voice translator for meetings](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""}, [Zoom — European Union public sector sovereignty controls explainer](https://library.zoom.com/advanced-enterprise-services/public-sector-sovereignty-controls/european-union-public-sector-sovereignty-controls-explainer){rel=""nofollow""}, [WhatsApp blog — Introducing message translations](https://blog.whatsapp.com/introducing-message-translations){rel=""nofollow""}, [WhatsApp — Privacy policy](https://www.whatsapp.com/legal/privacy-policy){rel=""nofollow""}, [WhatsApp Business app](https://whatsappbusiness.com/products/business-app/){rel=""nofollow""}, [Telegram blog — Real-time translation](https://telegram.org/blog/profile-pics-emoji-translations){rel=""nofollow""}, [Telegram — Premium FAQ](https://telegram.org/faq_premium){rel=""nofollow""}, [Telegram blog — Telegram Business](https://telegram.org/blog/telegram-business){rel=""nofollow""}, [Mattermost — Pricing](https://mattermost.com/pricing/){rel=""nofollow""}, [Mattermost — Set up Auto-translation (Beta)](https://docs.mattermost.com/administration-guide/manage/admin/autotranslation.html){rel=""nofollow""}, [Rocket.Chat — Our plans](https://docs.rocket.chat/docs/our-plans){rel=""nofollow""}, [Rocket.Chat — Auto-Translate messages](https://docs.rocket.chat/docs/auto-translate-messages){rel=""nofollow""}, [Element — Pricing](https://element.io/pricing){rel=""nofollow""}, [Nextcloud Talk](https://nextcloud.com/talk/){rel=""nofollow""}, [Nextcloud — Live Transcription and Translation in Nextcloud Talk](https://docs.nextcloud.com/server/stable/admin_manual/ai/app_live_transcription.html){rel=""nofollow""}, [Nextcloud — Local Machine translation 2 (translate2)](https://docs.nextcloud.com/server/31/admin_manual/ai/app_translate2.html){rel=""nofollow""}. Vendors change plans, prices, language lists and beta status over time; check their pages for the current state. All facts checked August 2026.* # Microsoft Teams live translation (2026): how it works, what it costs, and where it stops - **Yes, three ways.** Live translated captions, the AI Interpreter agent and human interpreters you book. Captions and the Interpreter sit behind Teams Premium or Copilot seats. - **It ends with the meeting.** No Interpreter in instant meetings, webinars or town halls, and nothing stays in anyone's language: recordings keep the original audio only. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, files and the recap, next to Teams rather than instead of it. Guests join free by link, no account; you pay only for active members. If you searched "Microsoft Teams live translation" or "can Teams translate in real time," the honest short answer is: **yes, Teams can translate a live meeting — three different ways — and which one you get depends on whose license the organizer has and what kind of meeting you booked.** Microsoft has shipped more live-translation machinery than any other conferencing vendor, including a genuinely ambitious AI interpreter. It has also fenced each piece differently, and the fences are where buying decisions actually happen. This post explains how each works, how to turn it on, and exactly where the ceiling is. > This is the platform how-to companion to our foundational guide, [*Real-time meeting translation: how it works, and how to evaluate one*](https://intermind.com/blog/real-time-meeting-translation). For the Google Meet and Zoom versions of this post, see [Meet](https://intermind.com/blog/google-meet-live-translation) and [Zoom](https://intermind.com/blog/zoom-live-translation). New to interpretation as a category? Start with [*Simultaneous interpretation: booth, RSI, or AI*](https://intermind.com/blog/simultaneous-interpretation-guide). --- ## The three features, and why they're not the same thing ### 1. Live translated captions (text) The established feature. Teams transcribes the meeting live and translates the caption stream into each participant's chosen language — **every attendee picks their own caption language independently**. Microsoft's support page lists **31 translation languages** for meetings (its own licensing page says 40, and the town-hall page says "over 50" — we'd cite the 31-language list it actually enumerates). Works in meetings, webinars, and town halls — though in town halls the organizer pre-selects a pool of six languages, ten with Premium. The gate: **the organizer needs a Teams Premium or Microsoft 365 Copilot license** for attendees to get translated captions. Plain English captions are free; translation is the paid layer. And captions aren't saved — when the meeting ends, the translation evaporates. ### 2. Interpreter agent (audio, AI) The Ignite 2024 headliner, now generally available: an AI agent that translates **spoken audio into spoken audio**, per participant — you pick the language you want to *listen* in, and Interpreter can even **simulate the speaker's own voice** in the translation. Calls got it in January 2026; a turn-based consecutive mode for two-language meetings rolled out in May 2026. Of the big three platforms, this is architecturally the closest thing to per-listener simultaneous interpretation. Which is exactly why its fences matter — they're in the limits section, and they're decisive. ### 3. Language interpretation (humans, channels) The classic: the organizer pre-configures up to **16 language pairs** and invites **human interpreters** — people you source, brief, and pay — who each get an audio channel. Attendees pick a channel and balance original vs. interpreter volume with a slider. No premium license documented, but the production burden is yours, and the constraints are real: set up before the meeting starts, interpreters must join from the desktop app, no web support, no breakout rooms, no end-to-end-encrypted meetings. --- ## How to turn each one on **Translated captions:** organizer has Premium or Copilot → any attendee turns on live captions, opens the caption settings, and picks a language under *Translate to*. **Interpreter agent:** you (the listener) need a **Microsoft 365 Copilot license**. In a scheduled meeting, turn on Interpreter for yourself, pick the language under *Listen to meeting in*, and optionally let it simulate voices (your admin controls whether that's on by default). **Language interpretation:** organizer enables it *while scheduling*, assigns interpreters per language pair, and attendees pick their channel once the meeting starts. It cannot be added to a meeting that's already running. The friction isn't the toggles. It's what the toggles can and can't do. --- ## What Teams live translation costs The features are bundled into licenses rather than priced on their own. Microsoft's list prices, US, checked August 2026: - **Live translated captions** — the organizer needs **Teams Premium** at **$10.00 per user/month, paid yearly**, or a Microsoft 365 Copilot license. One organizer license unlocks translated captions for every attendee of that meeting. - **Interpreter agent** — each *listener* needs a **Microsoft 365 Copilot** license: **$30.00 per user/month paid yearly** for the enterprise add-on (annual commitment; $31.50 when paid monthly). Microsoft also lists a Copilot Business SKU at $18.00 per user/month through December 31, 2026 (from $21.00). The license includes **20 hours of Interpreter per user per month**. - **Language interpretation (human channels)** — no premium license documented; the cost is the interpreters you contract, billed per interpreter, per language, per day. So a 30-person team that wants everyone to *hear* the meeting in their own language is looking at 30 Copilot seats for the metered Interpreter, or one Premium seat for captions everyone reads. ## The three features side by side | | Live translated captions | Interpreter agent | Language interpretation | | ------------------------- | ----------------------------------------- | ---------------------------------------------------------- | -------------------------------------------- | | What you get | Text captions in each attendee's language | Spoken translation per listener, optional voice simulation | Audio channels for human interpreters | | Who needs the license | The organizer (Teams Premium or Copilot) | Each listener (Microsoft 365 Copilot, 20 h/month) | Nobody documented — you pay the interpreters | | Languages | 31 listed for meetings | 10 | Up to 16 language pairs you staff | | Routing | Direct from the transcript | Through English text | Human | | Instant / ad-hoc meetings | Yes | No | No — pre-configured only | | Webinars and town halls | Yes (organizer-selected languages) | No | No breakout rooms, no web attendees, no E2EE | | Saved after the meeting | No | No — recordings keep original audio | Original audio only | --- ## The limits that actually decide if it fits As of mid-2026, by Microsoft's own documentation: - **The Interpreter agent speaks 10 languages** — English, Spanish, Portuguese, Japanese, Mandarin, Italian, German, French, Korean, and (since April 2026) Traditional Chinese. Under the hood it **pivots through English text**: speech is recognized, converted to English, translated, then synthesized. Every non-English pair pays the relay toll. - **It's metered and licensed per user.** Interpreter comes with a **Microsoft 365 Copilot license** and includes **20 hours per user per month**; beyond that, access is "subject to available capacity." Multilingual meetings as a metered utility. - **It skips the meetings where you'd want it most.** No ad-hoc/instant meetings, **no webinars, no town halls**, no Teams Free, no Teams Rooms on Android. The big multilingual broadcast formats get translated captions only — and there the organizer preselects the list the audience may read in (six languages, ten with Teams Premium), not the attendee. - **Nothing survives the meeting.** Recordings capture **original audio only** — no interpretation track. Translated transcripts exist only live; afterwards, only the spoken-language original remains. Translated captions aren't saved either. - **Microsoft's own quality caveat:** Interpreter is "not optimized for rapid exchanges or overlapping dialogue" — that is, for the way real working meetings sound. No latency figure is published. - **Human interpretation is a production.** Pre-configured only, desktop-only interpreters, no web attendees, no breakout rooms, no E2EE — and the interpreters bill you per day, per language, [a cost structure of its own](https://intermind.com/features/simultaneous-interpretation). None of this makes Teams' stack bad — it's the most complete of the big platforms. But it makes it **a per-seat-licensed, 10-language, 20-hour-a-month interpreter for scheduled internal meetings, with captions for everything else.** --- ## The meeting without the license matrix If those limits are the problem, the fix isn't a better toggle — it's a meeting that's multilingual for everyone in it by default: - [Start or join a multilingual meeting](https://intermind.com/chats) — every participant in their own language, with no per-listener license and no 20-hour meter. - [How the real-time translation stack works](https://intermind.com/features/realtime-translation) — 23 languages, translated directly between pairs, so a French↔Japanese meeting never routes through English. --- ## The structural ceiling, in one sentence **Teams will interpret a scheduled meeting for the colleagues whose seats carry Copilot licenses — in 10 languages, through an English relay, 20 hours a month, leaving no translated record.** A genuinely multilingual organization needs the *meeting* to be multilingual — for everyone in it, including the webinar audience, the guest without your license, and the recording you keep. If your multilingual meetings are internal, scheduled, and inside the 10 languages — and your organization is already paying for Copilot — Interpreter is a real answer, built into a tool you already have. If your meetings include webinars, externals, language pairs that shouldn't route through English, or anything you need a record of, you've hit the ceiling. --- ## When you've outgrown the license matrix This is the job we built InterMIND for: **the meeting itself runs in every participant's language — no per-listener license, no meter, no English relay.** Concretely, where Teams gates and meters: - **23 languages live on voice**, chat and shared notes, translated **directly between pairs** — a French↔Japanese meeting never routes through English. ([The full end-to-end stack](https://intermind.com/features/realtime-translation) is its own page.) - **Everyone in the meeting gets it.** Translation is how the platform works, not a per-seat entitlement — guests and externals included, no 20-hour meter. - **Webinars, town halls and conferences included** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant picking their own listening language: [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation). The full event workflow — Q\&A, recap and slide decks included — is at [events & webinars](https://intermind.com/use-case/events). - **The record survives.** Multilingual transcript, recording, and translated documents bundled after the meeting — not captions that evaporate. - **Quality you can audit.** Per-language-pair scores on real traffic, published monthly at [`/benchmark`](https://intermind.com/benchmark) — not asserted, measured. We're not claiming Teams is bad — Interpreter is the most serious translation feature any incumbent has shipped. We're claiming the fences around it describe a different meeting than the one multilingual teams actually run. The feature-by-feature version is at [InterMIND vs. Microsoft Teams](https://intermind.com/compare/microsoft-teams). --- ## What stays after the call, and where it lands The live part is the half of the meeting a vendor demos; the other half starts when the call ends. What InterMIND keeps, and where it can go — each item has its own guide: - **The recap, in each member's language.** After every transcribed meeting the signed-in participants get the AI summary, the full transcript and the recording on one permanent, members-only link; each reads the summary in their own language, and a channel keeps the recap of every past session. — [Meeting recap: what you get after the call](https://intermind.com/blog/meeting-recap) - **A copy in your CRM or help desk, by email.** The host adds the tool's inbound address as a recap copy recipient, confirms it once through a test email, and every recap of that room is sent there as a hidden BCC. — [How to get a copy of every meeting recap in your CRM by email](https://intermind.com/blog/how-to-get-a-copy-of-every-meeting-recap-in-your-crm-by-email) - **Structured, into any system.** A Zapier trigger, a signed `recap.ready` webhook, and an API with an OpenAPI 3.1 contract for Make, n8n, Pipedream and AI agents. — [Zapier, a webhook, or the API](https://intermind.com/blog/how-to-send-meeting-recaps-to-your-crm-with-zapier-or-the-api) - **The channel's history.** A meeting that persists as a channel keeps its chat, files, document summaries and recaps, readable by every member in their own language — and a client outside the team can be a member of it by email. — [How to add an external client to a team chat channel](https://intermind.com/blog/how-to-add-an-external-client-to-a-team-chat-channel) - **What the team sends in from elsewhere.** Every channel has its own email address, so a ticketing system or a monitoring tool posts into it without a bot; a file shares in from any app's share sheet on a phone or a Mac. — [Email to channel](https://intermind.com/blog/email-to-channel-no-bot), [Share from any app](https://intermind.com/blog/how-to-share-a-file-into-your-team-chat-from-any-app) Teams draws its own line at the door. Microsoft's admin documentation keeps anonymous join — people not signed in with a work or school account — behind the organization-wide **Anonymous users can join a meeting** setting and a per-organizer meeting policy, with the lobby policy deciding who waits; once inside, an anonymous participant has no meeting chat before and after the meeting, no profile cards and no collaborative meeting notes (checked October 2026). In InterMIND a participant without an account opens the link, enters a name and knocks; the host admits them from the notice, and inside they get video, audio, live translation, subtitles and the in-meeting chat. The host provides the room; participants pay nothing. A guest of a meeting — a participant without an account — gets the live part in full and none of the record; the account is free, and it is what makes the record reachable. --- ## Try the other side of the ceiling - **[Try the live demo](https://intermind.com/demo)** — hear a real meeting translated live, per listener, in any of 23 languages, with no license matrix — no signup needed. - **[Start your first meeting](https://intermind.com/chats)** — guests join by link, each in their own language. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month translation quality on real traffic, with the methodology written down. - [InterMIND vs. Microsoft Teams](https://intermind.com/compare/microsoft-teams) — honest, feature-by-feature. - Just need a record, not live translation? The notetaker side of the market: [the 9 best Otter.ai alternatives](https://intermind.com/blog/otter-ai-alternatives). Teams live translation is real, ambitious, and precisely fenced: captions for the many, an English-relay interpreter for the licensed few, human channels for the events that justify staffing. Knowing where the fences are is the whole decision. --- ## FAQ **Does Microsoft Teams translate speech or only captions?** Both, behind different gates. Live translated captions cover 31 languages as text. The Interpreter agent speaks translations as synthetic audio in 10 languages — but it pivots through English text, and each user needs the right license. **What license do you need for Teams live translation?** Translated captions need the meeting organizer on Teams Premium or Microsoft 365 Copilot — then all participants get them. Interpreter is metered per user: 20 hours per user per month with a Copilot license. **Does Teams Interpreter translate between any two languages?** No. It routes through English text, and it doesn't work in ad-hoc calls, webinars, town halls, Teams Free, or on Teams Rooms on Android. Microsoft also notes it isn't optimized for rapid exchanges or overlapping dialogue. **Are translated captions saved in the Teams transcript or recording?** No. Captions aren't saved, translated transcripts exist only live, and recordings keep the original audio only. **Can Microsoft Teams translate in real time?** Yes, in three ways. Live translated captions translate the transcript into each attendee's chosen language as text (31 languages). The Interpreter agent speaks a translation per listener in 10 languages. Language interpretation routes human interpreters you hire into per-language audio channels. **Is Microsoft Teams live translation free?** Plain English captions are free. Translated captions need the organizer on Teams Premium ($10 per user/month, paid yearly) or Microsoft 365 Copilot. Interpreter needs a Copilot license per listener ($30 per user/month, paid yearly, for the enterprise add-on) and is metered at 20 hours per user per month. **How do I turn on live translation in Teams?** For captions: turn on live captions in the meeting, open the caption settings and pick a language under *Translate to* — the organizer must hold the license. For Interpreter: in a scheduled meeting, turn on Interpreter and pick the language under *Listen to meeting in*. For human interpretation: the organizer enables it while scheduling and assigns interpreters per language pair. **What languages does Teams live translation support?** Microsoft's support page lists 31 translation languages for translated captions in meetings. The Interpreter agent covers 10: English, Spanish, Portuguese, Japanese, Mandarin, Italian, German, French, Korean and Traditional Chinese. **Does Teams live translation work in webinars and town halls?** Translated captions do — in town halls the organizer pre-selects six languages (ten with Premium). The Interpreter agent does not work in webinars or town halls, and human interpretation channels can't be added to a running meeting. **Can I join a Microsoft Teams meeting without an account?** Only if the organizer's admin allows it. Microsoft documents anonymous join as an admin setting — the organization-wide **Anonymous users can join a meeting** toggle plus a per-organizer policy — and the lobby policy decides whether you wait to be let in; an anonymous participant then has no meeting chat before and after the meeting, no profile cards and no collaborative meeting notes (checked October 2026). In InterMIND the link is enough: a participant without an account enters a name, knocks, and the host admits them; they get the live meeting in full — video, audio, translation, subtitles, in-meeting chat — and the host's plan covers it. The record after the call needs an account, which is free. **What if the conversation isn't in Teams at all?** The same question comes up for a French, Spanish or Russian speaker talking to an Italian one: a phrase app handles a menu, a conversation needs a room where everyone speaks their own language. Our guides on the [French–Italian](https://intermind.com/blog/traduttore-francese-italiano-vocale), [Spanish–Italian](https://intermind.com/blog/traduttore-spagnolo-italiano-vocale) and [Russian–Italian](https://intermind.com/blog/traduttore-italiano-russo-vocale) voice translator draw that line, and the [Italian voice translator overview](https://intermind.com/blog/traduttore-vocale) covers the rest. — The Mind.com Team --- *Sources: [Microsoft — Use live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Microsoft Learn — Meeting transcription and captions](https://learn.microsoft.com/en-us/microsoftteams/meeting-transcription-captions){rel=""nofollow""}, [Microsoft — Interpreter in Teams meetings and calls](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft Learn — Interpreter agent in Teams](https://learn.microsoft.com/en-us/microsoftteams/interpreter-agent-teams){rel=""nofollow""}, [Microsoft — Use language interpretation in Teams meetings](https://support.microsoft.com/en-us/office/use-language-interpretation-in-microsoft-teams-meetings-b9fdde0f-1896-48ba-8540-efc99f5f4b2e){rel=""nofollow""}, [Microsoft Learn — Teams Premium licensing](https://learn.microsoft.com/en-us/microsoftteams/teams-add-on-licensing/licensing-enhance-teams){rel=""nofollow""}, [Microsoft — Teams Premium pricing](https://www.microsoft.com/en-us/microsoft-teams/premium){rel=""nofollow""}, [Microsoft — Microsoft 365 Copilot pricing](https://www.microsoft.com/en-us/microsoft-365/copilot/enterprise){rel=""nofollow""}, [Microsoft — Microsoft 365 Copilot Business pricing](https://www.microsoft.com/en-us/microsoft-365/copilot/business){rel=""nofollow""}, [Microsoft Learn — Manage anonymous participant access to Teams meetings](https://learn.microsoft.com/en-us/microsoftteams/anonymous-users-in-meetings){rel=""nofollow""} (checked October 2026). Microsoft expands language lists and licensing over time; check the pages for the current state. All facts checked August 2026.* # Teams Meeting Shared Files: what the documentation states, and how a shared file becomes an answer in the meeting - **Files for everyone, read by a licensed and scoped AI.** Facilitator needs a Copilot license, scheduled meetings only, one answer language per meeting. - **External participants are outside the loop.** They do not see Facilitator's real-time updates; the roadmap names no access rule or language behaviour. - **InterMIND keeps the whole meeting in each member's language,** a shared file summarized on every plan and answered aloud by Mia (preview), next to Teams rather than instead of it. Guests join free by link, no account; you pay only for active members. On 8 September 2026 Microsoft added feature 570427 to the Microsoft 365 roadmap. The entry reads, in full: > The new Meeting Shared Files feature allows users to add relevant files and links to their meeting for easy access and to automatically share that content with all meeting participants. AI in the meeting, like the Facilitator agent, uses these files for targeted grounding to answer questions and enhance skill functionality. It is a mechanic worth having. Files stop being messages that scroll away, and the AI in the room answers from the deck the room is actually looking at. This post is two documented maps. First: what Microsoft's own pages say about the feature and about the AI that reads those files — the license it needs, the meetings it works in, who can switch it on, the language it answers in. Second: how the same job works in InterMIND today, mechanic by mechanic — a file dropped into the meeting, the summary that appears by itself, and Mia, the meeting's AI participant, answering questions grounded on that file aloud, each participant hearing her in their own language. Vendor facts are quoted from Microsoft's roadmap and support pages, checked September 2026; links are in the footer. ## What the roadmap entry states The roadmap row is the primary document, so it is worth reading as data rather than as an announcement. Fetched from Microsoft's roadmap API on 9 September 2026, feature 570427 carries: | Field | Value | | ------------------ | ------------------------------------------------------ | | Title | "Microsoft Teams: Meeting Shared Files" | | Status | "In development" | | Release phase | "General Availability" | | Availability | "October CY2026" | | Cloud instance | "Worldwide (Standard Multi-Tenant)" | | Products | "Microsoft Teams", "Microsoft Copilot (Microsoft 365)" | | Platforms | Android, Desktop, iOS, Linux, Mac | | Created / modified | 2026-09-08 | Two things the entry does not state, as of the check: it names no access rule for participants who are not in the tenant, and it names no language behaviour for the shared content or for the AI answers grounded on it. The product tag "Microsoft Copilot (Microsoft 365)" is the entry's own; what that tag implies for licensing is documented elsewhere, on the Facilitator page. ## The AI that reads the files is licensed and scoped The roadmap entry names the Facilitator agent as the consumer of shared files. Microsoft's support page for Facilitator states the boundaries, and each of these is a quote: **The license.** "A Microsoft Copilot license is required to add Facilitator to a meeting or turn it on during a meeting. However, any meeting participant (excluding external participants) can see all real-time updates in Chat and Notes." **The meeting types.** "Facilitator can only be added to scheduled meetings, and can't be added to channel meetings, instant meetings, or Teams calls." **What it does with files.** Among its listed features: "Create a high-quality word document based on the meeting discussion, chat history and shared files." **The condition for asking it afterwards.** "To prompt Facilitator about the meeting after it ends, make sure to turn on transcription before or during the meeting. If Copilot is set to start without transcription, Facilitator will start without transcription as well." **Who can switch it on mid-meeting.** "Only meeting participants who are organizers or presenters and are using Teams for web or desktop can turn Facilitator on or off during a meeting." **The language.** "When you turn on Facilitator, you'll be asked to select a language if a language for the meeting hasn't already been selected." The selection is a property of the meeting, not of the person asking. Microsoft also documents two cases where the agent cannot read what it was pointed at: when "only the organizer has joined," because "Facilitator can't read the organizer's copy of the meeting invite due to privacy requirements," and when the invite or notes carry a sensitivity label — "if the meeting invite or notes have a sensitivity label (such as Confidential or another label that requires encryption), Facilitator can't read or extract the agenda." Two more documented facts from the same product family, because a shared file in a multilingual room meets them: the Interpreter agent page lists ten supported languages — "English, Spanish, Portuguese, Japanese, Simplified Chinese (Mandarin), Italian, German, French, Korean and Taiwanese" — with "20 hours of interpretation … included per person per month with a Microsoft Copilot license"; and the live-captions page states that "Teams doesn't save captions. If you'd like a transcript of the meeting, turn on transcription." Put together, that is the documented picture as of September 2026: the file is shared with everyone; the AI that reads it needs a Copilot license, works in scheduled meetings only, is switched on by organizers or presenters, and answers in the one language selected for the meeting; external participants do not see its real-time updates in Chat and Notes. ## How this works in InterMIND Everything below is how the product works today, and each item is a mechanic rather than a claim about quality. **A file dropped into the meeting chat is read on your machine.** When a document is attached in a meeting chat or a channel, its text is extracted in your browser — a Web Worker converts the file locally, up to 50 MB. Covered: DOC, DOCX, DOCM, ODT, RTF; PDF with a text layer; PPT, PPTX, PPSX, PPTM, ODP; XLS, XLSX, XLSM, ODS, CSV; TXT, MD, Markdown; EPUB. The file's text is not mailed to a third party to be parsed. **The summary is automatic — there is no button and no license.** A moment after the file lands, the card's status strip flips from **Preparing summary…** to **AI summary**, with **Preview** next to it for the document itself. Nobody presses anything, nobody has to be the person who "runs the AI on it", and summaries carry no plan quota. **A question about the file gets an answer in the meeting, in each participant's language.** Status, 19 September 2026: Mia in meetings is in preview — it is being tested inside InterMIND; any account can switch her on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). What follows describes how she works in the preview. Mia is the organization's AI participant. Say *«Mia, what delivery date is in the contract?»* aloud, or switch the meeting chat to its private mode — the lock next to the message field — and write the question there, and she answers from the material of this session: the transcript so far, the chat, the summaries of the documents shared in it, and the recaps of the room's previous sessions. If the material does not contain the answer, she says so in one sentence rather than inventing a number. She answers licensed participants of paid plans — Pro, Business and Enterprise: a participant on a paid plan has her in every meeting they join, whoever hosts it. Guests and participants on the free plan hear her spoken answers to others, but she does not answer them. There is no AI add-on on top of the plan, no meeting type she cannot join, and nobody has to switch her on during the call — she runs whenever AI features are on for the host's organization. **The answer follows the question.** Asked aloud, Mia answers aloud to the whole room: the answer is written natively in the language of the question and in every other language present in the room, and it is voiced on each participant's device in that participant's language; nothing is written to the chat. Asked in the private mode of the chat, she answers there only, in text, and nobody else in the room sees the exchange. Mia is not a participant of the call itself: she is not in the recording or the transcript, and her voice never crosses another participant's microphone. Start talking and she stops; **Stop Mia** cuts an answer short. **The answer runs on the gateway the host's organization chose.** She uses the AI gateway the organization chose for all of its AI features — the default EU gateway or the organization's own endpoint — and the voice comes from that gateway's vendor. On an organization's own endpoint there is no voice, so a spoken question is answered as text in the meeting chat. **Every point in the summary is anchored to the document.** The summary bullets are written against paragraph markers injected into the extracted text, so each bullet ends with a **¶ link** that jumps to the exact source paragraph in the **Extracted text** tab. A claim in the summary is one click from the author's wording, and the extracted text is deliberately never translated, so the anchor always lands on the author's own words. **Each member reads the summary in their own language.** The summary is written in the document's own language first, then served to each reader in that reader's meeting language and cached per language. **A document opened during the call arrives on every stage.** A Google Docs or OneDrive document linked in the meeting chat can be opened for the whole conference — it appears on every participant's stage, labeled with who shared it, each viewer scrolls and zooms independently, and each viewer's client requests it in their own interface language. Rich-text notes go on the stage the same way, with **Translated**, **Original** and side-by-side views per reader. **The file's substance lands in the record with the same weight as speech.** Documents shared during a session contribute their summaries to the meeting recap alongside what was said, and the recap prompt treats a figure or a decision stated in a document exactly like a spoken one. A session where nobody spoke but documents were shared still produces a recap. **Reading it requires being a member.** The extracted text and the summary live only in our database, never in public file storage, and the route that serves them requires membership of that meeting or channel. **Translating the whole file is a separate, metered feature.** Reading a shared PDF or Office file *in your language* — the document, not its summary — is document translation, covering 30 document languages, counted in distinct files over a rolling 30-day window: 10 on Pro, 30 on Business, 100 on Enterprise, and not available on Basic. The per-pipeline numbers, because there is no single answer: **23 languages for voice and chat, 30 for documents**, 17 interface locales. Five limits worth stating plainly. An unauthenticated guest can be in the meeting, see the document on the stage and hear Mia's spoken answers about it, but Mia does not answer a guest's own questions, and the summary card belongs to a signed-in member — there is no account for it to belong to otherwise. A Google Drive or OneDrive link shares a pointer rather than the file, so there is no text on our side to extract, summarize or ask Mia about; the content stays with its provider. A scanned PDF has no text layer and is labeled as such rather than silently summarized — OCR is not performed. Files arriving from the mobile app or from the Telegram bridge aren't extracted yet. And Mia answers from a document's summary, not from its full text, so a detail the summary did not keep is a detail she will tell you she does not have. ## Side by side Documented facts from Microsoft's own pages, checked September 2026. Where a page doesn't state something, the cell says so. | | InterMIND | Microsoft Teams (as documented) | | ---------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | File shared with everyone in the meeting | yes — attached in the meeting chat, and linked documents can be put on every participant's stage | Meeting Shared Files: "add relevant files and links to their meeting … automatically share that content with all meeting participants" (roadmap, "In development", "October CY2026") | | AI in the meeting answers from the shared file | Mia — addressed by name aloud or in the private mode of the meeting chat, grounded on the session's documents, chat, transcript and previous recaps | Facilitator "uses these files for targeted grounding to answer questions" (roadmap); can "create a high-quality word document based on the meeting discussion, chat history and shared files" | | License for the in-meeting AI | a paid plan (Pro, Business or Enterprise) held by the participant who asks, with no AI add-on on top of it; document summaries are on every plan with no quota | "A Microsoft Copilot license is required to add Facilitator to a meeting or turn it on during a meeting" | | Meeting types | any meeting or channel call — a shared file is extracted, summarized and available to Mia on the same path, with no meeting-type condition | Facilitator "can only be added to scheduled meetings, and can't be added to channel meetings, instant meetings, or Teams calls" | | Who switches it on during the call | nobody — there is no in-call switch; the organization's AI setting applies to every meeting | "Only meeting participants who are organizers or presenters and are using Teams for web or desktop can turn Facilitator on or off during a meeting" | | Who can ask | licensed participants of paid plans, in every meeting they join, whoever hosts it; guests and free-plan participants hear the spoken answers | not stated for Facilitator prompts; real-time updates are visible to "any meeting participant (excluding external participants)" | | Language of the AI's answer | per participant — a spoken answer is written natively in every language present in the room and voiced on each device in that participant's language | one per meeting: "you'll be asked to select a language if a language for the meeting hasn't already been selected" | | Where the AI runs | the organization's chosen gateway or its own endpoint; Mia is not in the recording or the transcript | not stated on the Facilitator page | | Asking after the meeting | the recap carries the file's summary with the same weight as speech; Mia in the next session of the same room answers from the previous recaps | "To prompt Facilitator about the meeting after it ends, make sure to turn on transcription before or during the meeting" | | Spoken-language coverage | 23 languages for voice and chat | Interpreter: ten listed languages; "the interpretation output will always be in one of the supported languages listed above" | | Reading the document itself in your language | document translation, 30 languages, metered per plan (Basic 0, Pro 10, Business 30, Enterprise 100 files per 30 days) | not stated in the roadmap entry | | Checking a summary claim against the source | every bullet carries a ¶ link to the exact source paragraph; the extracted text is never translated | not stated | | Text extraction | in your browser, up to 50 MB, then stored members-only in our database | not stated | Both columns tie the in-meeting AI to a paid entitlement of the person using it. The rows where the two sets of documentation differ are the meeting types, the in-call switch, who hears the answer, and the language of the answer. ## If you're staying on Teams Four things worth doing, all from the documentation above: 1. **Check who in the meeting holds a Copilot license.** The agent that reads shared files needs one to be added or switched on, and only organizers or presenters on Teams web or desktop can turn it on mid-meeting. 2. **Schedule the meeting.** Facilitator can't be added to channel meetings, instant meetings, or calls — if the file-grounded AI matters, the calendar invite is the entry point. 3. **Turn transcription on before or during the call** if anyone will want to ask about the meeting afterwards; Microsoft documents that as the condition. 4. **Pick the meeting language deliberately.** Facilitator answers in the one language selected for the meeting; participants outside the tenant don't see its real-time updates in Chat and Notes. If most of the people the file was shared with can't ask about it — wrong meeting type, wrong tenant, wrong language — the file was distributed rather than shared. ## FAQ **What is Microsoft Teams Meeting Shared Files?** A Teams feature on the Microsoft 365 roadmap as feature 570427, created 8 September 2026. Microsoft's entry states it "allows users to add relevant files and links to their meeting for easy access and to automatically share that content with all meeting participants," and that "AI in the meeting, like the Facilitator agent, uses these files for targeted grounding to answer questions and enhance skill functionality." The row is tagged to both Microsoft Teams and Microsoft Copilot (Microsoft 365) (checked September 2026). **When is Meeting Shared Files available?** The roadmap entry lists status "In development", release phase "General Availability", and availability "October CY2026", for the "Worldwide (Standard Multi-Tenant)" cloud instance, with platform tags for Android, Desktop, iOS, Linux and Mac (checked September 2026). Roadmap dates are Microsoft's own and can move. **Do I need a Microsoft Copilot license to use the AI that reads meeting files?** For Facilitator, yes: "A Microsoft Copilot license is required to add Facilitator to a meeting or turn it on during a meeting." Microsoft adds that "any meeting participant (excluding external participants) can see all real-time updates in Chat and Notes," so the license gates turning it on rather than watching its output inside the tenant (checked September 2026). **Can external or anonymous participants use the file-grounded AI in a Teams meeting?** Microsoft's Facilitator page states that real-time updates in Chat and Notes are visible to "any meeting participant (excluding external participants)". The roadmap entry for Meeting Shared Files does not state an access rule for participants outside the tenant (checked September 2026). **Can I ask the meeting AI a question about a shared file?** In InterMIND, yes: address Mia by name aloud, or write to her in the private mode of the meeting chat (the lock next to the message field), and she answers from the summaries of the documents shared in this session, together with the transcript, the chat and the recaps of the room's previous sessions. She answers licensed participants of paid plans in every meeting they join; guests and free-plan participants hear her spoken answers to others; no in-call switch is involved. For Teams, the roadmap entry states that "AI in the meeting, like the Facilitator agent, uses these files for targeted grounding to answer questions," and the Facilitator page documents the Copilot license and the scheduled-meeting condition (checked September 2026). **In which language does the meeting AI answer?** In InterMIND, in every language present in the room: Mia's spoken answer is written natively per language and voiced on each participant's device in that participant's language. A question written in the private mode of the chat is answered there, in text, to the person who wrote it. For Facilitator, Microsoft states that "you'll be asked to select a language if a language for the meeting hasn't already been selected" — one language per meeting (checked September 2026). **Can everyone in a meeting read a shared file in their own language?** In InterMIND, the file's summary is served to each member in that member's own language and cached per language, a linked document opened on the stage is requested by each viewer's client in that viewer's own interface language, and reading the document itself in your language is document translation, covering 30 languages and metered per plan. For Teams, the roadmap entry states the file is shared with all participants and does not state per-participant language behaviour (checked September 2026). **Can I check an AI summary against the document it came from?** In InterMIND, yes: each summary bullet ends with a ¶ link that jumps to the exact paragraph of the extracted text it was written from, and the extracted text is never translated so the anchor always lands on the author's own wording. The **Extracted text** tab holds the document's full text as it was read from the file. **Are document summaries limited by plan?** In InterMIND the summary of a shared document is included on every plan with no quota. Mia in meetings is in preview and is not part of any plan yet; in the preview she answers participants of the Pro, Business and Enterprise plans, with no AI add-on on top. Translating the whole document is the metered feature: distinct files over a rolling 30-day window, 10 on Pro, 30 on Business, 100 on Enterprise, and not available on Basic. **What happens to a shared file after the meeting?** Its summary feeds the meeting recap alongside what was said, with the same weight as spoken content — a session where nothing was said but documents were shared still produces a recap. The file's card stays in the chat with its **AI summary** and **Extracted text**, readable by members of that meeting or channel and by nobody else, and Mia in the room's next session answers from that recap. ## Try it - **[Open the live demo](https://intermind.com/demo)** — a meeting in your language, no signup. - **[See what document summaries look like](https://intermind.com/features/document-summaries)** — the ¶ anchors, the status strip, the language rule. - **[Read the document-summaries docs](https://intermind.com/docs/chat/document-summaries)** — formats, card statuses, privacy and quotas. - **[Read how sharing works in-call](https://intermind.com/docs/meetings/shared-documents)** — documents, notes and recaps on the stage. - **[Check the translation quality before you pay for it](https://intermind.com/benchmark)** — per-pair scores on real traffic. If what bothers you is not the file but the record it becomes, that argument is laid out separately in [how to keep a meeting's transcript, summary and action items after the call](https://intermind.com/blog/keep-meeting-transcript-summary-after-the-call). *Sources: Microsoft 365 Roadmap — [feature 570427, "Microsoft Teams: Meeting Shared Files"](https://www.microsoft.com/en-us/microsoft-365/roadmap?featureid=570427){rel=""nofollow""} (fields quoted from Microsoft's roadmap API); Microsoft Support — [Facilitator in Microsoft Teams meetings](https://support.microsoft.com/en-us/teams/copilot/facilitator-in-microsoft-teams-meetings){rel=""nofollow""}, [Interpreter in Microsoft Teams meetings and calls](https://support.microsoft.com/en-us/teams/copilot/interpreter-in-microsoft-teams-meetings-and-calls){rel=""nofollow""} and [Use live captions in Microsoft Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, checked September 2026.* # How to bring your Telegram chats into InterMIND — and read them in your own language - **Connect once, then add the bot.** Connect in Settings → Telegram Integration; add the bot to a group, set it as your Telegram Business chatbot, or forward it anything. - **Three rules route it, one way.** A group mirrors into the channel with its name, a one-on-one chat into your shared channel, the rest into your Inbox; nothing goes back. - **InterMIND keeps the whole conversation in each member's language,** Telegram messages included: in a channel they read like any message, history and all, next to Telegram, not instead of it. For a lot of teams, the real work doesn't happen in meetings. It happens in Telegram: the group where decisions get made at 11pm, the one-on-one where the client sends the contract, the voice note that settles an argument. Meanwhile the meetings — and their recaps, notes and history — live in InterMIND channels, where [every member reads them in their own language](https://intermind.com/features/multilingual-chat). That splits the team's record in two. One half persists in a space built for it; the other half stays in Telegram, in whatever language it was typed, findable only by whoever was in the chat. The InterMIND Telegram bot closes that split in one direction: Telegram in, InterMIND keeps it. It mirrors groups, relays your one-on-one chats, and files anything you forward to it — into the same channels where your meetings already live. And once a message is in a channel, it behaves like every other InterMIND message: each member reads it in their own language, history included. One design decision shapes everything below: **the bot never asks where a message should go.** There are no dialogs, no per-message prompts. Three rules decide the destination, anything the rules can't resolve lands in your private Inbox, and you can override any route with one pin. Here is the whole system. ## Three ways in | You have | You do | Where it lands | | ----------------------------------------------- | ------------------------------------------------- | ----------------------------------------------------------------------------------------------------- | | A Telegram group your team works in | Add the bot to the group as a member | Your channel with the same name as the group; no such channel → your Inbox | | One-on-one chats you want kept (Secretary mode) | Connect the bot as your Telegram Business chatbot | The channel that is exactly you and that person — when they're on InterMIND too; otherwise your Inbox | | A single message, link or file worth keeping | Forward it to the bot | Your Inbox | All three start with the same step. ## Step 1: connect your account In the InterMIND web app, open **Settings → Telegram Integration** and press **Connect**. It opens Telegram with a personal link — press **Start**, and the bot confirms which account it's now connected to. The link is single-use and expires after 15 minutes; if you let it lapse, press the button again. Two things worth knowing about the binding: - **One Telegram account connects to one InterMIND account.** Connecting the same Telegram from a different InterMIND account moves the binding there — the old account stops receiving. - **Connecting comes first.** A bot added to a group by someone who hasn't connected can't mirror anything — it says so in the group and waits. Disconnecting is symmetric: send `/stop` to the bot, or press **Disconnect** in Settings → Telegram Integration. Everything already ingested stays where it landed — it's your channels' history now. ## Mirror a group Add the bot to the Telegram group as an ordinary member. It immediately posts one message saying who connected it and where the group's messages will flow — so every member of the group knows the mirror exists. The destination rule is the group's **name**: - If you have a channel in InterMIND with the same name as the group, messages mirror there. The match is exact — letter case and surrounding spaces are ignored, but there is no fuzzy matching. - No channel with that name — or two of them, which is ambiguous — and messages go to your Inbox instead. The bot never guesses. The name is the router, and it's live: rename the group or the channel and the route follows the new names on the next message. If you want a route that survives renames, pin it (below). The matched channel has to be one *you* created — the mirror follows the person who added the bot, and everything the group says lands in that person's channel, where its members read it. Removing the bot from the group stops the mirror. This route covers groups and supergroups; Telegram broadcast channels are not part of it. ## Secretary mode: your one-on-one chats Groups have a bot in them, visibly. Your personal chats don't — so for those, Telegram has a different mechanism: [Telegram Business](https://telegram.org/blog/telegram-business){rel=""nofollow""} lets you connect a chatbot to your *own* account, scoped to chats you choose. Telegram makes Business features available to Premium subscribers (checked August 2026). In Telegram: **Settings → Telegram Business → Chatbots**, pick the InterMIND bot, and choose which chats it can access — Telegram's own controls let you exclude your contacts, limit it to new chats, or exclude specific people. From then on, when someone you've included writes to you: - If they're on InterMIND too (with their own Telegram connected), and there is exactly one channel whose members are exactly the two of you — the message lands in that shared channel. - Anything else — the sender isn't on InterMIND, or there's no unambiguous shared channel — lands in your Inbox. Only the other side's messages are ingested. What you write in the chat stays where you wrote it — the point is to keep what's sent *to* you, not to copy your own outbox. ## The Inbox, and the one manual control Every routing rule above falls back to the same place: your **Inbox** — a private channel, one per account, visible to you alone. It's the honest answer to ambiguity: better a message in your Inbox than a guess in the wrong channel. It's also the direct target: forward anything to the bot — a message, a link, a file — and it's in your Inbox. The Inbox is where the one manual control lives. Open the context menu on any Telegram message in it and choose **Always deliver to a channel…** — pick one of your channels, and from then on everything from that Telegram chat goes there. A pin overrides the name rule and the shared-channel rule; it's the only routing state you ever set by hand. Pins are listed — and removed — in **Settings → Telegram Integration**, under Chat routing. ## What lands, exactly - **Text arrives as ordinary channel messages.** Each member reads it in their own language, on demand, like any other message in the channel — the same chat-translation allowance of your plan applies. Sender name and photo come along, so the channel shows who said it in Telegram. - **Photos, files, video and voice notes are stored in the channel**, and count toward your plan's storage. If your storage is full, the bot tells you so and skips the file — text keeps flowing. InterMIND does not transcribe or translate media on ingest: a voice note arrives as an audio file, not as text. - **Captions travel with their files** as text, so they translate like any message. - **Edits follow, deletions don't.** Edit a mirrored message in Telegram and the channel copy updates, keeping its edit history. Delete one in Telegram and the channel copy stays — ingest is one-way, and what's in your space is yours. - **Nothing is posted back.** The bot never sends your InterMIND replies into Telegram. The only messages it ever writes are service notices: the connection announcement in a group, the storage warning, the `/start` and `/stop` confirmations. ## Who sees what - **In the group:** the bot is an ordinary member — everyone can see it in the member list, and it announces the mirror when it's added. Nothing about the group route is invisible. - **In InterMIND:** mirrored group messages land in the connecting person's channel, where that channel's members read them. Secretary-mode messages land in the shared two-person channel or in the Inbox. The Inbox itself is strictly personal — no one else can be in it. - **Off switch:** `/stop` to the bot or Disconnect in Settings ends everything at once; removing the bot from a group ends that group's mirror; unpinning a chat returns it to the rules. ## Try it - **[Try the live demo](https://intermind.com/demo)** — no signup; see what per-participant translation feels like in a live room. - **[How translated chat works](https://intermind.com/features/multilingual-chat)** — the feature the ingested messages inherit. - **[The meeting a week later](https://intermind.com/blog/the-meeting-a-week-later)** — why we build for the history, not just the call. ## FAQ **How do I connect Telegram to InterMIND?** Open Settings → Telegram Integration in the InterMIND app, press Connect, and press Start in the Telegram chat that opens. The personal link is single-use and expires after 15 minutes. To disconnect, send `/stop` to the bot or press Disconnect in the same Settings card. **Does InterMIND mirror Telegram groups?** Yes. Add the InterMIND bot to the group as a member (after connecting your account). Messages mirror into your InterMIND channel with the same name as the group; if no such channel exists — or two share the name — they go to your private Inbox instead. Groups and supergroups are covered; Telegram broadcast channels are not. **Do I need Telegram Premium for this?** Only for Secretary mode, because it runs on Telegram Business, which Telegram makes available to Premium subscribers (checked August 2026). Mirroring groups and forwarding messages to the bot need no Premium. **What happens if I rename the Telegram group or the InterMIND channel?** The group route matches names live, so the route follows the new names: if they no longer match, messages fall back to your Inbox until the names align again — or until you pin the chat to a channel, which overrides name matching entirely. **Are messages from Telegram translated?** Text messages behave like any InterMIND channel message: each member reads them in their own language, translated on demand under your plan's chat-translation allowance. Files, photos, video and voice notes are stored as files — InterMIND does not transcribe or translate media on ingest. **Does the bot post anything back into my Telegram chats?** No. Ingest is one-way — your InterMIND replies stay in InterMIND. The bot only ever writes service notices: the announcement when it's added to a group, a storage-full warning, and confirmations for `/start` and `/stop`. **Who can read what the bot brings in?** Members of the destination channel — mirrored group content lands in the connecting person's channel, Secretary-mode messages land in the shared two-person channel, and everything unresolved lands in the Inbox, which only its owner can see. In the group itself, the bot is visible to every member and announces the mirror when added. **What happens to messages someone deletes in Telegram?** They stay in InterMIND. Edits propagate (the channel copy updates and keeps edit history), deletions don't — the ingested record belongs to your space. --- *Sources: [Telegram — Telegram Business](https://telegram.org/blog/telegram-business){rel=""nofollow""} (Business features for Premium subscribers; chatbot chat-access controls), [Telegram — Connected business bots](https://core.telegram.org/api/bots/connected-business-bots){rel=""nofollow""}. Checked August 2026.* # How much of your meeting still exists in your language a week later? - **On the major platforms, nothing translated.** Teams and Meet state translated captions and audio aren't saved; Zoom's docs don't state they are. The record stays in the spoken language. - **Notetakers keep the record, not the language.** Otter and Fireflies persist a transcript and summary in the spoken language. - **InterMIND keeps the whole meeting in each member's language,** persisting as a channel: chat history, recap and documents readable by each signed-in member. Guests join free by link, no account; you pay only for active members. Run this test on your last cross-language meeting: **one week later, what can each participant still open and read in their own language?** Not "was the meeting translated." Almost every platform can now answer yes to that, with an asterisk. The test is what remains. The decision your Portuguese colleague wants to quote back in a dispute. The action item your German teammate needs to re-read before the follow-up. The three weeks of context a new hire from Bogotá has to absorb. The number procurement asks you to confirm from the call two Tuesdays ago. A meeting lasts forty-five minutes. Its outputs get used for months. And on today's major platforms, translation is built for the forty-five minutes — the moment the call ends, the translated layer disappears, and the record that remains speaks one language. This post is the audit: what each vendor's own documentation says survives the call, and in whose language. Then the architectural reason the answer comes out the way it does — and what it looks like when a meeting is built to outlive the call instead. --- ## A meeting's real lifespan The industry measures meeting translation on two axes: how fast (latency) and how wide (language count). Both describe the live call. We've argued elsewhere that a third axis decides more purchases than either — [how much of the meeting comes back in your language](https://intermind.com/blog/real-time-meeting-translation) — and the week-later test is that axis stretched to its natural length. Because the call is the shortest-lived thing the meeting produces. What actually circulates afterwards: - **Decisions** — cited in later meetings, escalations, and audits, often word-by-word. - **Action items** — re-read by the people executing them, days later. - **History** — the searchable record a newcomer reads to catch up, and the reference the team searches when memory disagrees. - **Documents** — the contract, the spec, the deck that the meeting was about. If translation exists only during the call, then every one of those artifacts exists in one language — usually English — and everyone else works from memory or from a second-hand summary. The organization's *memory* is monolingual even when its meetings weren't. A participant who heard the meeting in Spanish spends the following week working with a record they can only read in English. --- ## What survives the call, vendor by vendor Everything below is from vendor public documentation, checked August 2026. Links in the footer. ### Microsoft Teams Teams documents the live layer thoroughly — translated captions in 31 languages, an AI Interpreter agent in 10 — and is equally explicit about the afterlife: - **Translated captions aren't saved.** Microsoft's caption documentation states captions are not stored after the meeting; the translation exists only while the meeting runs. - **Recordings capture original audio only** — the Interpreter agent's translated audio is not in the recording. - **Translated transcripts exist only live.** Afterwards, the transcript that remains is in the spoken language. The full walkthrough of the live features is in our [Teams live translation](https://intermind.com/blog/teams-live-translation) post; the summary here is one sentence in Microsoft's own docs: nothing translated survives the meeting. ### Google Meet Meet's Gemini-powered speech translation translates spoken audio between English and five languages, one pair per meeting. On persistence, Google's documentation is direct: - **Speech translation is not available in recordings** (or live streams) — it's a live-only beta, capped at 90 minutes per meeting. - **No audio is saved.** Google states plainly that speech-translation audio isn't stored — a clean privacy answer, and also a complete answer to the week-later test. - Translated captions, the older text feature, are likewise an on-screen live view. Details and limits in [Google Meet live translation](https://intermind.com/blog/google-meet-live-translation). ### Zoom Zoom's live stack is the broadest of the three — translated captions in 36 languages, a five-language Voice translator, human interpretation channels — and its documentation describes all three as live views: - **Translated captions** are rendered on screen, per participant, while the meeting runs. Zoom's translated-captions documentation does not state that the translated stream is saved after the meeting (checked August 2026). - **The Voice translator** speaks synthetic translated audio live, in meetings only, on the desktop app. Its documentation likewise does not state that translated audio persists anywhere (checked August 2026). - What Zoom's recording stack keeps is the meeting *as spoken* — the original audio and its transcript. The live features are mapped in [Zoom live translation](https://intermind.com/blog/zoom-live-translation). ### The AI notetakers Otter, Fireflies and their category are the mirror image of the platforms: built precisely for the afterlife — transcripts, summaries, search — which makes their language model the interesting part: - **The transcript persists in the language the meeting was held in.** [Otter](https://intermind.com/compare/otter) transcribes in six languages (English, Spanish, French, German, Japanese, Chinese); [Fireflies](https://intermind.com/compare/fireflies) claims 100+ with auto-detection. Either way, one meeting produces one transcript in one language — the spoken one. - A meeting held in English produces an English record, however many languages its *readers* think in. The notetaker solves "we forgot what was said," not "half of us read this at half speed." The category comparison is in [Otter alternatives](https://intermind.com/blog/otter-ai-alternatives) and [Fireflies alternatives](https://intermind.com/blog/fireflies-ai-alternatives). --- ## The week-later audit, in one table | Platform | Translation during the call | What its docs say survives the call | A week later, in *your* language | | ----------------- | -------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------ | | Microsoft Teams | Translated captions (31 languages, organizer needs Premium/Copilot); Interpreter agent (10 languages, metered) | Captions not saved; recordings keep original audio only; translated transcripts live-only | Nothing translated | | Google Meet | Speech translation (English ↔ 5 languages, one pair per meeting, 90-min beta); translated captions | Speech translation unavailable in recordings; no audio saved | Nothing translated | | Zoom | Translated captions (36 languages); Voice translator (5 languages, add-on, desktop, meetings only) | Recording and transcript of the meeting as spoken; docs don't state translated output is saved | Nothing translated stated in documentation | | Otter / Fireflies | None (notetakers don't translate the live meeting) | Transcript + summary — in the spoken language | The record persists; the language doesn't change | | InterMIND | Voice, chat, notes and documents translated per participant, live | The meeting persists as a channel: chat history readable in each member's language, a recap delivered to each signed-in member in their own language, documents translated on request | The history, in the language you think in | The pattern in the middle column isn't an accident, and it isn't vendors forgetting a feature. It's architecture. --- ## Why translated moments can't become translated history A caption is a *view* — text rendered over a live stream for as long as the stream exists. When the call ends, the stream ends, and a view of nothing is nothing. The same holds for translated audio synthesized on the fly: it's played, not kept. Translation implemented as an overlay dies with the thing it overlays. That's not a bug in Zoom, Teams or Meet; it's the honest consequence of where translation sits in their architecture — a layer on the call. For a meeting's history to exist in every reader's language, translation has to be a property of the *place that holds the history*, not of the call that produced it. The chat message, the recap, the document need to live somewhere that renders them per reader — this week, next month, for the member who joins in October. That's the difference we mean when the InterMIND homepage says "[a space for everyday communication](https://intermind.com) " rather than "video calls with translation." It's also why we treat a meeting becoming a channel as the product working as intended, not as a leftover artifact. ## What a space that outlives the call looks like Concretely, in InterMIND: - **The meeting persists as a channel.** The call is an event inside the space; when it ends, the space — members, chat, files, history — stays. - **Chat history reads in each member's language.** Messages are [translated per viewer](https://intermind.com/features/multilingual-chat), and that applies to the history, not just to messages arriving live. - **Every signed-in member gets the recap in their own language.** After the call, the [AI recap](https://intermind.com/features/recap) — summary, decisions, action items — is delivered per participant, each in theirs. - **Documents translate on request** — [30 languages](https://intermind.com/features/document-translation), inside the same space as the meeting they belong to. - **Voice comes back as a recap, honestly labeled.** We removed live transcription deliberately; the persistent trace of what was *said* is the recap, not a word-for-word multilingual replay. If your compliance case needs a verbatim record, that's what recording — under the host's control — is for. - **You choose the jurisdiction the space lives in.** History that persists is history that's stored; where it's stored is a first-class setting, with an [EU data path](https://intermind.com/features/security) and zero data retention on AI processing. And because quality claims about translation age badly, the translation itself is [benchmarked publicly, per language pair, every month](https://intermind.com/benchmark) — the history is only worth keeping if the translation in it holds up. ## Run the audit on your own stack Five questions, answerable from any vendor's documentation in an afternoon: 1. **Where do translated captions go when the meeting ends?** If the docs don't say they're saved, they aren't. 2. **What language is the recording's transcript in?** "The spoken one" means your multilingual meeting has a monolingual record. 3. **Can a participant read last month's chat in their own language?** Not "can they machine-translate an export" — can they open it and read it. 4. **What does the participant who missed the meeting receive, and in whose language?** 5. **Who can verify the translation quality of whatever *does* persist?** A record nobody can trust is a record nobody uses. If the answers are "nowhere, English, no, an English summary, nobody" — you don't have a multilingual meeting tool. You have a monolingual archive with multilingual moments. --- ## Try the week-later test with a real meeting - **[Try the live demo](https://intermind.com/demo)** — no signup; hear per-participant voice translation, then look at what the room leaves behind. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month translation quality on real traffic, methodology included. - **[How one InterMIND meeting is built](https://intermind.com/blog/what-one-intermind-meeting-is-built-from)** — the architecture behind the space, for the technically curious. - **[Where the transcript, summary and action items actually live](https://intermind.com/blog/keep-meeting-transcript-summary-after-the-call)** — the other half of the question: not what language the record is in, but who owns each file and what breaks when you move it. --- ## FAQ **Are Zoom translated captions saved after the meeting?** Zoom's translated-captions documentation describes a live, per-participant caption view and does not state that the translated stream is saved after the meeting (checked August 2026). What Zoom's recording features keep is the meeting as spoken — original audio and its transcript. **Are Microsoft Teams translated captions or Interpreter audio saved?** No — and here Microsoft is explicit: captions aren't saved, translated transcripts exist only during the meeting, and recordings capture original audio only, without the Interpreter agent's translated track (checked August 2026). **Does Google Meet speech translation work in recordings?** No. Google documents speech translation as a live beta — not available in recordings or live streams, capped at 90 minutes per meeting — and states that no audio is saved (checked August 2026). **Can you get a meeting transcript in another language?** From the major platforms, the transcript that persists is in the meeting's spoken language. AI notetakers persist a transcript too — also in the spoken language. Translating a transcript afterwards is an export-and-translate workflow, outside the meeting tool. InterMIND takes a different route: the persistent record — chat history, recap, documents — is rendered in each member's language inside the space itself. **What does "a space that outlives the call" mean?** It means the meeting doesn't end when the call does: it persists as a channel holding the chat, files, recaps and history, and every member reads that history in their own language. The call is an event inside the space, not the container of everything. **Why does history in your language matter if you attended the meeting live?** Because the work happens after: decisions get cited, action items get re-read, disputes get settled by the record, and new teammates catch up from it. If all of that exists only in English, everyone who thinks in another language does the *follow-through* at a disadvantage — which is where the meeting's actual value lives. --- *Sources: [Microsoft — Use live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Microsoft — Interpreter in Teams meetings and calls](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft Learn — Meeting transcription and captions](https://learn.microsoft.com/en-us/microsoftteams/meeting-transcription-captions){rel=""nofollow""}, [Google Meet — Learn about Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, [Google Meet — Use translated captions](https://support.google.com/meet/answer/10964115){rel=""nofollow""}, [Zoom — Enabling and configuring translated captions](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0059081){rel=""nofollow""}, [Zoom — Using the Voice translator for meetings](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""}, [Otter — supported languages](https://help.otter.ai/hc/en-us/articles/360047247414-Supported-languages){rel=""nofollow""}, [Fireflies — supported languages](https://guide.fireflies.ai/articles/2973706448-learn-about-fireflies-supported-languages){rel=""nofollow""}. Vendors change plans and language lists over time; check their pages for the current state. All facts checked August 2026.* # Voice translator: phrase, face-to-face, or live conversation - **Three products share one name.** A phone app relays a phrase, earbuds translate one person, live meeting translation runs the whole room in each participant's language at once. - **The exchange decides.** A phrase: a phone app. One person, both equipped: earbuds. Several people, instant back-and-forth: live meeting translation, because a relay makes everyone wait. - **InterMIND keeps the whole conversation in each participant's language,** voice, chat, notes and documents, live and per listener. Guests join free by link, no account; you pay only for active members. "Voice translator" names three products at once. A phone app that listens and reads a translation back. Earbuds that whisper a translation of the person in front of you. And live meeting translation, where a whole conversation runs in several languages instantly, each participant hearing it in their own. They all translate speech. Only the last keeps an *instant, multi-person conversation* flowing without turning every exchange into a wait. This guide separates the three, shows how each works, and names the question that decides which you need: **a phrase, a face-to-face exchange, or a conversation?** --- ## The three kinds ### Phone-app voice translators Open an app, tap the mic, speak, and it plays back — or shows — the translation. Google Translate, Apple Translate, Microsoft Translator, dozens of travel apps. Genuinely good for one sentence at a time: a menu, a taxi, a hotel desk. The mechanic is a relay: you speak → it transcribes → it translates → it speaks back, then the other person answers into the same device and it relays the other way. It works because the exchanges are short and you pass the phone back and forth. Stretch it to a real back-and-forth and the relay is the bottleneck — you take turns operating a translator instead of talking. ### Earbud / device translators AirPods with Live Translation, Pixel Buds, dedicated translator earbuds. You wear them and hear the other person translated in your ear. Nicer than a screen — but **one-to-one, and it needs matching gear on both sides.** Built for a traveler and a local, not for a room. ### Live meeting translation A different architecture, not a better app. The *room* is multilingual: everyone speaks their own language and hears everyone else in **their** language, instantly, for the whole meeting. No phone to pass, no matching earbuds. It's the only one that survives an instant conversation among several people. --- ## Which one do you need? - **A phrase** — a menu, a direction, one exchange with a stranger. A phone app is perfect. Don't over-buy. - **A face-to-face exchange with one person, both equipped** — earbuds are the nicest experience. - **A conversation — a call, a meeting, several people, instant back-and-forth** — live meeting translation, because the others turn every exchange into a relay and every extra person into a broken assumption. The trap is using a phrase tool for a conversation: it technically "works," and it makes the conversation twice as slow, because everyone waits on the relay instead of talking. --- ## What "instant" and "live" really require Three things have to be true at once — and this is where most tools quietly fail: - **Per-listener, not per-device.** Every participant hears the room in their own picked language, simultaneously — five people, five languages, one call. The *whole room* is translated for *everyone*, each to their own language. - **Continuous, not after the pause.** If translation only arrives after the speaker pauses, it's consecutive interpretation with a synthetic voice — you feel every gap. Truly instant translation keeps pace with the talking. - **No English anchor, no regional gate, no five-language beta.** Any mix of languages, translated between participants directly — not everything routed through English, not five languages in a beta. That's not a bigger phone app. It's the architecture behind [real-time meeting translation](https://intermind.com/blog/real-time-meeting-translation) — the foundational guide to the category. --- ## Where InterMIND fits InterMIND is the third kind: a voice translator for instant, real conversations, built as live meeting translation. It starts with one person: you open the room and send the link; the others join free, without an account, each in their own language. - **23 languages live on voice**, chat and shared notes — any mix, no English anchor, no regional gate, no five-language beta. ([The full end-to-end translation stack](https://intermind.com/features/realtime-translation) is its own page.) - **Per-listener audio, live.** Each participant hears the meeting in their own picked language at the same time. (Under the hood: [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Webinars and conferences included** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant on their own listening language: [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation). - **Documents too** — drop a PDF or DOCX into the meeting and each viewer gets it in their language, 30 languages on files. - **Quality you can audit** — per-language-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark), methodology written down. A phone app is right for a phrase. Earbuds are right for one person in front of you. When it's an instant *conversation* among several people, that's the job InterMIND was built for. --- ## Try it - **[Try the live demo](https://intermind.com/demo)** — *hear* a real meeting translated live, per listener, in any of 23 languages — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month translation quality on real traffic, methodology included. - Start with the category guide: [*Real-time meeting translation*](https://intermind.com/blog/real-time-meeting-translation). - Comparing specific language pairs? See the voice-pair guides for [English ↔ Italian](https://intermind.com/blog/traduttore-inglese-italiano-vocale), [French ↔ Italian](https://intermind.com/blog/traduttore-francese-italiano-vocale), [Spanish ↔ Italian](https://intermind.com/blog/traduttore-spagnolo-italiano-vocale), [Italian ↔ Russian](https://intermind.com/blog/traduttore-italiano-russo-vocale), [Romanian ↔ Italian](https://intermind.com/blog/traduttore-rumeno-italiano-vocale) and [Hindi ↔ English](https://intermind.com/blog/hindi-to-english-voice-translator). - The same three-way split, written for another market: [Italian](https://intermind.com/blog/traduttore-vocale), [Spanish](https://intermind.com/blog/traductor-de-voz), [Portuguese](https://intermind.com/blog/tradutor-de-voz), [German](https://intermind.com/blog/sprachuebersetzer), [Turkish](https://intermind.com/blog/sesli-cevirmen). — The Mind.com Team --- *Sources: [Apple — Live Translation with AirPods](https://support.apple.com/en-us/123185){rel=""nofollow""}, [Google — Translate with Pixel Buds](https://support.google.com/googlepixelbuds/answer/7573100){rel=""nofollow""}, checked August 2026. Vendors change features and language lists over time — check their pages for the current state.* # Simultaneous translation: booth, RSI, or AI — and which tools for your meetings (2026) - **Three forms, three budgets.** A human interpreter in a booth, remote interpretation with booked interpreters, or an AI cascade with nothing to book; only the last fits a working meeting. - **Ask what comes back after the audio.** Most tools translate the spoken moment and stop; chat, notes and documents are not stated in most vendors' documentation. - **InterMIND keeps the whole meeting in each participant's language,** voice, chat, notes, documents and the summary, both directions at once. Guests join free by link, no account; you pay only for active members. "Simultaneous translation" is what everyone types; "simultaneous interpretation" is what the profession calls it. Both name the same thing: speech rendered in another language *while* it is being spoken — no pauses, no relay. But under that one term hide three very different ways of getting it — the human interpreter in a booth, remote simultaneous interpretation (RSI), and real-time AI translation — and three budgets that have nothing in common. This guide separates the three, then compares named tools on a verifiable basis: what each vendor's public documentation states, with the source and the date we checked it. We build one of them ([InterMIND](https://intermind.com){rel=""nofollow""}); we'll say where it fits and where it doesn't. --- ## The three forms of simultaneous translation ### 1. The interpreter in a booth (the historical standard) Two interpreters per language pair, a soundproof booth, receivers for the room. This is how institutions and large conferences do it. The quality comes from a professional who understands context, irony, and jargon — and the cost comes from the same place: qualified humans, booked by the day, per language pair, plus equipment. For a weekly working meeting, this setup simply isn't designed to apply. ### 2. RSI: the human interpreter, remote Remote-simultaneous-interpretation platforms (Interprefy, KUDO, Boostlingo) deliver human interpreters' audio — sometimes with an AI option alongside — to participants' phones or headsets, on site or in a video call. The setup remains an *event*: one speaker, an audience, languages fixed in advance, interpreters booked. ### 3. AI simultaneous translation No interpreter here: a speech-recognition → machine-translation → speech-synthesis cascade renders the speech in each listener's language within seconds, with nothing to book. This is the only form whose marginal cost fits an ordinary meeting — the category's tipping point. The question then becomes: *what* does the tool translate, beyond the voice? --- ## The question that actually separates tools An honest comparison doesn't ask "is the translation good?" — every vendor answers yes. It asks two things: **One speaker, or everyone at once?** Event tools optimize *one stage → one audience*, often one-directional. A working meeting is N people speaking, typing, reading, and replying, each in their own language, both directions, at once. A tool that excels at conferences can be unusable for a four-person standup. **After the audio, what comes back in your language?** A meeting isn't just speech: it's the chat, the shared notes, the document dropped mid-session, the record you keep. Most tools translate the spoken moment and stop — the translation evaporates the instant the talking does. Ask any candidate plainly: *after the audio, what else comes back in my language?* --- ## The tools, on the record Every fact below comes from the vendor's public documentation, checked August 2026 (links at the end). "Not stated" means we found no claim in the public docs — check with the vendor if the point matters to you. ### For events with interpreters (RSI) - **Interprefy** — its documentation states 190+ languages and 6,000+ combinations with human interpreters, and 80 languages for its AI translation (audio and captions). ([InterMIND vs Interprefy, feature by feature.](https://intermind.com/compare/interprefy)) - **KUDO** — RSI platform with an AI option: the KUDO AI Speech Translator page states translated audio and captions in 60+ languages, alongside human-interpreter delivery. - **Boostlingo** — interpreter network: its site states 10K qualified interpreters and 275+ languages on demand, plus AI captions. ### For multilingual working meetings - **Wordly** — AI-only translation for meetings and events: its documentation states 60+ languages and 3,000+ pairs, with attendees choosing text, audio, or both; its FAQ states translated transcripts and session summaries. Chat, shared-notes, and document translation are not stated in its public documentation (checked August 2026). ([InterMIND vs Wordly, feature by feature.](https://intermind.com/compare/wordly)) - **DeepL Voice** — the product page states live captions in 40+ languages inside Microsoft Teams, Zoom, and Google Meet; voice-to-voice output is listed as "coming soon" (checked August 2026). - **InterMIND** — what we build: the *whole* meeting comes back in each participant's language, both directions. Voice — 23 languages, rendered in the **speaker's own voice**, live ([how the cascade works](https://intermind.com/blog/inside-the-translation-pipelines)); chat and shared notes — translated live, per viewer, in the same 23 languages; documents dropped in-meeting (PDF, DOCX, PPTX, XLSX) — returned in 30 languages with formatting intact ([the honest per-surface count](https://intermind.com/blog/how-many-languages-do-you-support)); the post-meeting summary — generated in your language, on EU-hosted models with zero retention of meeting data ([the GDPR audit](https://intermind.com/blog/gdpr-audit-what-we-closed)). Quality is published, not claimed: the production cascade is scored monthly against FLORES-200, full per-pair distribution, at [/benchmark](https://intermind.com/benchmark). ### Inside the platforms you already use - **Zoom** — translated captions in 36 languages (Business Plus/Enterprise or a paid add-on); a Voice translator that renders translated audio (AI Companion, US-cluster accounts, desktop app 7.0+); and audio channels for up to 20 human interpreters you source yourself. ([Full breakdown.](https://intermind.com/blog/zoom-live-translation)) - **Microsoft Teams** — translated captions in 31 languages (Teams Premium or Copilot); an Interpreter agent that translates speech into speech, optionally simulating the speaker's voice (Copilot license); channels for 16 language pairs of human interpreters. ([Full breakdown.](https://intermind.com/blog/teams-live-translation)) - **Google Meet** — translated captions (Workspace Business Standard and above) and Gemini speech translation "in a voice like yours" (qualifying plans). ([Full breakdown.](https://intermind.com/blog/google-meet-live-translation)) --- ## The table: how much of the meeting comes back in your language? Every cell is what the vendor's own public documentation states, checked August 2026. | Tool | Translated audio (live) | Translated captions | Chat | Shared notes | Documents in-meeting | After the meeting | | ------------------- | -------------------------------------------------- | ------------------------------------------------------ | ------------------------------ | --------------------------- | -------------------------------------- | ---------------------------------- | | **Interprefy** | Yes — interpreters (190+ languages) or AI (80) | Yes (AI, 80 languages) | Not stated | Not stated | Not stated | Not stated | | **KUDO** | Yes — interpreters or AI (60+) | Yes (60+) | Not stated | Not stated | Not stated | Not stated | | **Wordly** | Yes (AI; 60+ languages, 3,000+ pairs) | Yes | Not stated | Not stated | Not stated | Translated transcripts + summaries | | **DeepL Voice** | "Coming soon" (per product page) | Yes (40+ languages, in Teams/Zoom/Meet) | Not stated | Not stated | Separate DeepL product | Not stated | | **Zoom** | Yes — Voice translator (AI Companion, US cluster) | Yes (36 languages; Business Plus/Enterprise or add-on) | Manual per-message translation | Not stated | Not stated | Not stated | | **Microsoft Teams** | Yes — Interpreter agent (Copilot license) | Yes (31 languages; Premium/Copilot) | Per-message, optional auto | Not stated | Not stated | Not stated | | **Google Meet** | Yes — Gemini speech translation (qualifying plans) | Yes (Business Standard+) | Not stated | Not stated | Not stated | Not stated | | **InterMIND** | Yes — 23 languages, speaker's own voice | Yes (23, per viewer) | Automatic per viewer (23) | Yes — live, per viewer (23) | Yes — PDF/DOCX/PPTX/XLSX, 30 languages | Summary + digest, in your language | Two honest notes on our own row: the counts differ per surface (voice/chat/notes 23, documents 30, website 17 languages — [the breakdown and why](https://intermind.com/blog/how-many-languages-do-you-support)); and voice quality is checked on [/benchmark](https://intermind.com/benchmark), not in this table. --- ## The decision shortcut - **Conference with an audience + human interpreters required** → Interprefy, KUDO, Boostlingo. - **Working meeting, several people, both directions, AI** → Wordly, DeepL Voice, [InterMIND](https://intermind.com){rel=""nofollow""} — and here, test three things specifically: the rendered voice (generic or the speaker's own), coverage beyond the audio (chat, notes, documents, the record), and quality that is *published* rather than claimed. - **Captions are enough** → your existing Zoom/Teams/Meet, with the license gates in the table. --- ## FAQ **What is the best simultaneous translation software for meetings?** Depends on the setup. For an event with an audience and interpreters: Interprefy (80 AI languages, 190+ with interpreters), KUDO (60+), or Boostlingo. For a working meeting where everyone speaks, types, and reads in their own language, both directions: Wordly states 60+ languages as audio and text; InterMIND translates voice (23 languages, in the speaker's own voice), chat and notes (23), and documents (30) per participant. For captions only: Zoom (36 languages), Teams (31), or Meet, depending on your plan. **What is the difference between simultaneous translation and simultaneous interpretation?** In practice, none: "simultaneous interpretation" is the professional term for real-time spoken rendering, "simultaneous translation" the everyday one. Strictly, *translation* concerns text and *interpretation* speech — we unpacked the distinction and the types of interpretation [here](https://intermind.com/blog/interpretation-vs-translation). **Can Zoom, Teams, or Google Meet do simultaneous translation?** Yes, with plan gates. Zoom: translated captions in 36 languages (Business Plus/Enterprise or a paid add-on) and translated audio via the Voice translator (AI Companion, US cluster). Teams: captions in 31 languages (Premium/Copilot) and the speech-to-speech Interpreter agent (Copilot license). Meet: translated captions (Business Standard+) and Gemini speech translation on qualifying plans. Per-platform detail: [Zoom](https://intermind.com/blog/zoom-live-translation), [Teams](https://intermind.com/blog/teams-live-translation), [Meet](https://intermind.com/blog/google-meet-live-translation). **Can AI simultaneous translation keep the speaker's voice?** Most AI tools render every speaker as the same synthetic narrator. A few state output close to the original voice: Teams' Interpreter agent can "simulate" the speaker's voice, Google Meet states "a voice like yours," and InterMIND renders the translation in the speaker's own voice via zero-shot synthesis, in 23 languages — [how that works](https://intermind.com/blog/own-voice-translation). **How does AI simultaneous translation work?** A three-stage cascade: speech recognition transcribes the speech, machine translation converts it, speech synthesis renders it — continuously, a few seconds behind. Each stage fails in its own ways; we documented the production cascade stage by stage [here](https://intermind.com/blog/inside-the-translation-pipelines), and how to evaluate any tool in this category [here](https://intermind.com/blog/real-time-meeting-translation). --- ## See it for yourself For the multilingual working meeting, the fastest test — for any tool, ours included — is to put your own meeting through it: talk, then check whether the chat, the notes, and the document came back in your language too. - **[Try the live demo](https://intermind.com/demo)** — InterMIND's production voice cascade, on your own audio, in any of 23 languages. - **[Read the benchmark](https://intermind.com/benchmark)** — monthly FLORES-200 scores, full per-pair distribution, no cherry-picking. - **[How to evaluate a real-time meeting translator](https://intermind.com/blog/real-time-meeting-translation)** — the vendor-neutral foundation behind this guide. --- *Sources: [Interprefy — AI translation languages](https://knowledge.interprefy.com/what-languages-can-interprefy-ai-translate-from-and-to){rel=""nofollow""}, [Interprefy — platform](https://www.interprefy.com/){rel=""nofollow""}, [KUDO — AI Speech Translator](https://kudo.ai/solutions/kudo-ai-speech-translator/){rel=""nofollow""}, [Boostlingo](https://boostlingo.com/){rel=""nofollow""}, [Wordly — translator languages](https://www.wordly.ai/translator-languages){rel=""nofollow""}, [Wordly — FAQ](https://www.wordly.ai/faq){rel=""nofollow""}, [DeepL — Voice](https://www.deepl.com/en/products/voice){rel=""nofollow""}, [Zoom — viewing captions in another language](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0060844){rel=""nofollow""}, [Zoom — Voice translator](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""}, [Zoom — Language Interpretation](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0064768){rel=""nofollow""}, [Microsoft — live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Microsoft — Interpreter in Teams](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft — language interpretation in Teams](https://support.microsoft.com/en-us/office/use-language-interpretation-in-microsoft-teams-meetings-b9fdde0f-1896-48ba-8540-efc99f5f4b2e){rel=""nofollow""}, [Google Meet — translated captions](https://support.google.com/meet/answer/10964115){rel=""nofollow""}, [Google Meet — Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, checked August 2026. Vendors expand plans and language lists over time; check their pages for the current state. InterMIND facts: [per-surface language breakdown](https://intermind.com/blog/how-many-languages-do-you-support), [live benchmark](https://intermind.com/benchmark).* # Spanish voice translator: one phrase, one counterpart, or a whole meeting? - **Three products, one search.** A phone app relays a phrase, earbuds translate one counterpart, live meeting translation runs the whole call in Spanish, English and more at once. - **Region and pair are the test.** Mexican, Rioplatense, Caribbean and Castilian trip tools tuned to one register, and Latin American work often pairs Spanish with Portuguese, not English. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, documents and recap, Spanish to any voice language directly. Guests join free by link, no account; you pay only for active members. Spanish is where voice translation gets real. Over twenty countries speak it natively; US–Latin America business runs on the English–Spanish pair daily — sales calls, supplier reviews, nearshored engineering standups, clinics, courts. So when you search for a Spanish voice translator, the stakes are usually higher than a menu. And the search returns three different products wearing one name. A phone app that listens, then reads the translation back. Earbuds that whisper a translation of the person in front of you. And live meeting translation, where a whole call runs in Spanish and English (and Portuguese, and anything else) at once, and each participant hears it in their own language. All three "translate Spanish." Only one of them holds up when the exchange is a *conversation*. ## The three products behind one search ### 1. Phone-app voice translators Open the app, tap the mic, speak; it transcribes, translates, and plays back. Google Translate, Apple Translate, Microsoft Translator all handle English↔Spanish well — it's among the most heavily used pairs in every one of them. For a phrase, this is the right tool, and it's free. The mechanic is a relay: you speak → it processes → it answers → your counterpart replies into the same phone. Two people passing one device works for a taxi or a hotel desk. Stretch it to a supplier negotiation — three people, interruptions, someone thinking out loud — and the relay becomes the meeting. You're not conversing; you're taking turns operating a translator. ### 2. Earbud and device translators The 2025–2026 hardware wave: AirPods with Apple's Live Translation, Pixel Buds, dedicated translator earpieces. The person across the table speaks Spanish; you hear English in your ear. It feels closer to conversation because you're not staring at a screen. But note the shape: **one-to-one, one direction at a time, on your device.** For reciprocity, your counterpart needs compatible hardware and setup. It's designed for a traveler and a shopkeeper — not for the Tuesday call where Monterrey, Bogotá and Chicago are all on the line. Past two people, or past the people who happen to own the hardware, the model breaks. ### 3. Live meeting translation The third kind is a different architecture, not a bigger app. In live meeting translation the *room* is multilingual: each participant speaks their own language and hears everyone else **in theirs, simultaneously**, for the whole meeting. Nobody passes a phone; nobody pairs earbuds. Translation is a property of the call itself. It's the only one of the three built for the way Spanish is actually used at work: several people, both directions at once, nobody wanting to perform their second language in front of colleagues. The category guide — what "real time" must mean, what to ask before adopting one — is here: [real-time meeting translation](https://intermind.com/blog/real-time-meeting-translation). ## The Spanish-specific part Two things make the Spanish pair unforgiving for translation tools: - **Region.** Mexican, Rioplatense, Caribbean, Castilian — vocabulary and pacing differ enough that phrase tools tuned on one register wobble on another. A tool that can't handle *ahorita*, *vos querés* and *ordenador* in the same afternoon isn't done with Spanish. That's a quality question, and quality claims deserve receipts: we publish [per-language-pair scores on real traffic, monthly](https://intermind.com/benchmark) — including the Spanish pairs — instead of asserting accuracy in a press release. - **The pair isn't always with English.** Latin American business runs Spanish↔Portuguese constantly (Mexico–Brazil, Colombia–Brazil), and a workday can need Spanish↔German or Spanish↔Japanese with no English speaker on the call. Tools that anchor every translation on English handle exactly one shape of Spanish workday. InterMIND translates directly between any of its [23 voice languages](https://intermind.com/features/realtime-translation) — Spanish↔Portuguese included, no English in the middle. ## Which one do you actually need? One question decides it: **is this a phrase, or is this a conversation?** - **A phrase** — directions, a menu, one question to a stranger: a phone app, free, done. - **One counterpart, face to face, hardware in hand** — earbuds are the most pleasant version of the relay. - **A conversation — a call, a meeting, several people, both directions**: you need live meeting translation, because the other two turn every exchange into waiting, and every extra participant into a broken assumption. The trap is using a phrase tool for a conversation. It technically works — at half the speed and half the humanity, with everyone waiting on the relay instead of talking. ## Where InterMIND fits InterMIND is the third kind, built as meeting translation from the start — one person opens the room and sends the link, the others join free, without an account, each in their own language: - **23 languages live in voice, chat and shared notes** — Spanish to and from any of them, each participant choosing their own listening language, simultaneously, live. - **Nothing to install, nothing to pay for participants** — guests [join by link, free, no account](https://intermind.com/blog/free-for-participants); the host's plan covers the room. - **Documents too** — drop a PDF or DOCX into the meeting and each reader gets it in their language (30 languages for files). - **The meeting persists** — chat history, the recap and the documents stay readable in each signed-in member's language, [a week later included](https://intermind.com/blog/the-meeting-a-week-later). A phone app is right for a phrase. Earbuds are right for one counterpart. When it's a conversation — Monterrey, Bogotá and Chicago on one call, in three accents of two or three languages — that's the job InterMIND was built for. ## Hear it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; hear a room of English and Spanish translated live, per listener. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair monthly quality on real traffic, Spanish pairs included, methodology public. - New to the category? Start with [real-time meeting translation: how it works](https://intermind.com/blog/real-time-meeting-translation). - The same three-way split, written for another market: [Italian](https://intermind.com/blog/traduttore-vocale), [French](https://intermind.com/blog/traducteur-vocal), [Portuguese](https://intermind.com/blog/tradutor-de-voz), [German](https://intermind.com/blog/sprachuebersetzer), [Turkish](https://intermind.com/blog/sesli-cevirmen). --- ## FAQ **What is the best Spanish voice translator?** Match the tool to the exchange. For phrases, the free phone apps (Google Translate, Apple Translate, Microsoft Translator) handle English↔Spanish well. For one face-to-face counterpart, translator earbuds are the most comfortable relay. For a conversation with several people — a call or meeting — you need live meeting translation, where each participant hears the room in their own language simultaneously. **Is there a Spanish voice translator that works both directions at once?** Phone apps and earbuds relay one direction at a time. Live meeting translation runs both directions continuously: the Spanish speaker hears English colleagues in Spanish while they hear her in English, with no turn-taking. That's the architecture InterMIND uses, across 23 languages. **Does Spanish voice translation work between Spanish and Portuguese, without English?** Depends on the architecture. Tools that anchor translation on English cover Spanish↔English shapes only. InterMIND translates directly between any two of its 23 voice languages — Spanish↔Portuguese included — with no English relay. **How good is machine translation for Spanish meetings?** Don't take any vendor's word for it, ours included — ask for measurements. We publish per-language-pair translation scores on real production traffic every month at [/benchmark](https://intermind.com/benchmark), with the methodology written down, so you can check the Spanish pairs yourself before relying on them. --- *Sources: [Google Translate — translate by speech](https://support.google.com/translate/answer/6142474){rel=""nofollow""}, [Apple — Live Translation with AirPods](https://support.apple.com/en-us/123185){rel=""nofollow""}, [Google Pixel Buds — real-time translation](https://support.google.com/googlepixelbuds/answer/7573100){rel=""nofollow""}. Vendors change features and language lists over time — check their pages for the current state. InterMIND numbers are verified against the production product. All facts checked August 2026.* # Online voice translator, in real time: what those words actually promise - **The adjectives filter three products.** Online means nothing to install, free holds for phrases, real-time is the least-delivered promise: an app that waits for you to finish isn't. - **Phrase or conversation decides.** A phone app for a phrase, earbuds for one person face to face, live meeting translation for several people on a call. - **InterMIND keeps the whole conversation in each participant's language,** voice, chat, notes and documents, per listener and continuous. Guests join free by link, no account; you pay only for active members. Search for a voice translator and the qualifiers do the selling: *online*, *free*, *real-time*, *instant*. Underneath the adjectives sit three different products wearing one name. A phone app that listens, then reads the translation back. Earbuds that whisper a translation of the person in front of you. And live meeting translation, where a whole call runs in several languages at once and everyone hears it in their own. All three "translate voice." Only the last one keeps a *conversation* moving without turning every exchange into a wait. This guide unpacks the qualifiers, separates the three products, and names the one question that decides which you need: **is this a phrase, or is this a conversation?** --- ## The three products behind one search ### 1. Phone-app voice translators The familiar one: open an app, tap the mic, speak, and it plays back — or displays — the translation. Google Translate, Apple Translate, Microsoft Translator and dozens of travel apps do this. They're genuinely good at what they're for: a menu, a taxi, a hotel desk, one sentence at a time. The mechanic is a relay. You speak → it transcribes → it translates → it speaks back. Then the other person answers into the same phone and it relays the other way. It works because the exchanges are short and you're both willing to pass one device back and forth. Stretch it to a real back-and-forth — three people, interruptions, someone thinking out loud — and the relay is the bottleneck. You're not having a conversation; you're taking turns operating a translator. ### 2. Earbud / device translators The 2025–2026 hardware wave: AirPods with Apple's Live Translation, Pixel Buds, dedicated translator earbuds. You wear them, the other person speaks, and you hear a translation in your ear. It feels closer to a conversation because you're not staring at a screen. But look at the shape: it's **one-to-one, one direction at a time.** It translates the person in front of you, into your ear, on your device. For it to be mutual, the other side needs the same hardware and the same setup. It's built for a traveler and a shopkeeper, not for five people on a call speaking five languages. The moment the "room" grows past two people, or the others don't own compatible gear, the model breaks. ### 3. Live meeting translation The third kind is a different architecture, not a better app. In a live meeting translator, the *room* is multilingual: every participant speaks their own language, and every participant hears everyone else **in their own**, at the same time, for the whole meeting. Nobody passes a phone. Nobody wears paired earbuds. Translation is a property of the call, not of somebody's device. It's the only one of the three that survives a real conversation — several people, all speaking, no shared hardware, no English in the middle. --- ## What "online", "free" and "real-time" actually filter for - **Online** usually means "nothing to install" — a page that translates voice right in the browser. That exists, and it's also where meeting translation lives: a browser call is "online" by definition. - **Free** is true for phrases: phone apps handle a sentence at no cost. For an ongoing *conversation*, the real cost isn't the app's price — it's the time everyone loses waiting on the relay. - **Real-time** is the most-sold and least-delivered promise. An app that waits for you to finish speaking before it starts translating isn't real-time — it's consecutive interpretation with a synthetic voice. Real real-time keeps pace with the speaker. If what you mean by those filters is "a conversation that flows," the filters you actually want are different ones: per listener, continuous, and no shared device — the checklist below. --- ## How to tell which one you need One question settles it: - **Is it a phrase?** — a menu, a direction, a quick word with a stranger. A phone app is perfect. Don't spend more. - **Is it face-to-face with one person, and you own the device?** — earbuds are the nicest experience. - **Is it a conversation — a call, a meeting, several people, back-and-forth?** — you need live meeting translation, because the other two turn every exchange into a relay and every extra person into a broken assumption. The trap is using a phrase tool for a conversation. It technically "works" — and makes the conversation twice as slow and half as human, because everyone is waiting on the relay instead of talking. --- ## What "live" has to mean For a voice translator to hold a conversation together, three things must be true at once — and this is where most tools quietly fail: - **Per listener, not per device.** Every participant hears the room in the language they picked, simultaneously — five people, five languages, one call. Not "I translate what they say for you"; the *whole room* is translated for *everyone*, each in their own language. - **Continuous, not after the pause.** If translation only arrives after the speaker stops, that's consecutive interpretation with a synthetic voice — you feel every pause. Real live translation keeps pace with the speaker. - **No English anchoring, no regional lockouts, no five-language beta.** Any language combination, translated directly between participants — not everything routed through English, not five languages in beta. That isn't a bigger phone app. It's the architecture behind [real-time meeting translation](https://intermind.com/blog/real-time-meeting-translation) — the category's foundational guide, if you want the full picture of how it works and what to ask before you pick one. --- ## Where InterMIND fits InterMIND is the third kind: a voice translator for real conversations, built as live meeting translation rather than a phrase relay. It starts with one person: you open the room and send the link; the others join free, without an account, each in their own language. - **23 live languages on voice**, chat and shared notes — any combination, no English anchoring, no regional lockouts, no five-language beta. ([The full end-to-end translation stack](https://intermind.com/features/realtime-translation) is its own page.) - **Per-listener audio, live.** Every participant hears the meeting in their chosen language at the same moment. (How it works under the hood: [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Webinars and conferences included** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant picking the language they listen in. That's [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation), not an add-on. - **Documents too** — drop a PDF or DOCX into the meeting and every reader receives it in their own language, 30 languages on files. - **Quality you can check.** We publish per-language-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark), with the methodology written down — not accuracy claims in a press release. A phone app is fine for a phrase. Earbuds are fine for one person in front of you. When it's a *conversation* — several people, several languages, no shared hardware — that's the job InterMIND was built for. --- ## Try the conversation side - **[Try the live demo](https://intermind.com/demo)** — *hear* a real meeting translated live, per listener, in any of 23 languages — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — translation quality per pair, per month, on real traffic, methodology included. - Voice notes arriving in another language? See [how to transcribe (and understand) WhatsApp audios](https://intermind.com/blog/transcrever-audio-whatsapp). - After a dictionary with examples, not voice? See [Linguee English–Portuguese: what it's actually for](https://intermind.com/blog/linguee-tradutor-ingles-portugues). - New to the category? Start with [*Real-time meeting translation: how it works and how to evaluate it*](https://intermind.com/blog/real-time-meeting-translation). - Comparing specific language pairs? See the voice-pair guides for [English ↔ Italian](https://intermind.com/blog/traduttore-inglese-italiano-vocale), [French ↔ Italian](https://intermind.com/blog/traduttore-francese-italiano-vocale), [Spanish ↔ Italian](https://intermind.com/blog/traduttore-spagnolo-italiano-vocale), [Italian ↔ Russian](https://intermind.com/blog/traduttore-italiano-russo-vocale), [Romanian ↔ Italian](https://intermind.com/blog/traduttore-rumeno-italiano-vocale) and [Hindi ↔ English](https://intermind.com/blog/hindi-to-english-voice-translator). - The same split, written for another market: [Italian](https://intermind.com/blog/traduttore-vocale), [French](https://intermind.com/blog/traducteur-vocal), [Spanish](https://intermind.com/blog/traductor-de-voz), [German](https://intermind.com/blog/sprachuebersetzer), [Turkish](https://intermind.com/blog/sesli-cevirmen). "Voice translator" is three products. Match the tool to the shape of the exchange — phrase, face-to-face, or conversation — and the choice makes itself. — The Mind.com Team --- *Sources: [Google Translate — translate by speech](https://support.google.com/translate/answer/6142474){rel=""nofollow""}, [Apple — AirPods Live Translation](https://support.apple.com/en-us/123185){rel=""nofollow""}, [Google Pixel Buds — real-time translation](https://support.google.com/googlepixelbuds/answer/7573100){rel=""nofollow""}, checked August 2026. Vendors change features and language lists over time — check their pages for the current state. InterMIND numbers verified against the shipped product.* # French–Italian voice translator: for a phrase, and for a conversation - **A phrase and a conversation are two jobs.** Any phone voice translator handles a menu or a direction; a call between French and Italian teams breaks the relay model. - **A conversation needs the call translated, not a phone.** Both directions at once, per listener, French to Italian directly, not through English. - **InterMIND keeps the whole conversation in each participant's language,** French and Italian speakers hearing each other live, chat, notes and documents too. Guests join free by link, no account; you pay only for active members. If you need to translate spoken French into Italian, or Italian into French, there are two very different situations hiding behind one search — and the right tool is different for each. **A phrase** — asking directions in Milan, reading a menu in Lyon, one exchange with a shopkeeper. Any phone voice translator does this well: speak, it plays back, done. Don't over-buy. **A conversation** — a call between a French team and an Italian team, a negotiation, an interview, anything with back-and-forth and more than two people. Here the phone-app model breaks, because it's a relay: you speak, it translates, it plays back, then the other person answers into the same device and it relays the other way. Two people passing a phone can just about manage. A real conversation can't. --- ## Why "voice translator" behaves differently in a conversation The phone-app and earbud models share one assumption: **two people, one device or one pair of earbuds, taking turns.** For French ↔ Italian that's fine when it's a traveler and a local. It falls apart the moment the exchange is a meeting: - More than two people — a couple of French speakers, a couple of Italian speakers — and there's no single device to pass. - Everyone talking, interrupting, thinking out loud — the relay adds a beat to every turn, and the conversation stops flowing. - No shared hardware — you can't hand a Zoom call a pair of earbuds. A conversation needs the translation to be a property of the *call*, not of one person's phone: every French speaker hears the Italian speakers in French, every Italian speaker hears the French speakers in Italian, at the same time, live. That's live meeting translation — a different architecture, covered in full in [*Voice translator: what actually translates a live conversation*](https://intermind.com/blog/traduttore-vocale). --- ## What good French–Italian live translation looks like - **Both directions at once.** French → Italian *and* Italian → French, simultaneously, without anyone switching a mode or passing a device. - **Per-listener.** Each person hears the room in their own language, live — not "the translator reads it back after you stop talking." - **Direct, not through English.** French ↔ Italian translated between the two languages, not French → English → Italian, which drops nuance twice. - **Quality you can check.** For a Romance pair like French–Italian the translation is strong; we publish per-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark) rather than asserting accuracy. --- ## Where InterMIND fits InterMIND is a voice translator built for the conversation case: French and Italian speakers on the same call, each hearing the other in their own language, live. One person opens the room and sends the link; the others join free, without an account. - **French and Italian are both live voice languages** — part of [23 languages on voice](https://intermind.com/features/realtime-translation), chat and shared notes, any mix, no English anchor, no regional gate. - **Per-listener audio, live.** (How it works under the hood: [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Meetings, webinars and conferences** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant on their own listening language: [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation). - **Documents too** — share a PDF or DOCX and each side reads it in their language. For a menu in Nice or a taxi in Turin, a phone app is all you need. For a French–Italian *conversation*, that's the job InterMIND was built for. --- ## Try it - **[Try the live demo](https://intermind.com/demo)** — *hear* French ↔ Italian translated live, per listener, in a real meeting — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair quality on real traffic, methodology included. - The full picture: [*Voice translator: what actually translates a live conversation*](https://intermind.com/blog/traduttore-vocale). — The Mind.com Team --- *Sources: the phone-app and earbud categories described above are documented by their vendors — [Google Translate — translate by speech](https://support.google.com/translate/answer/6142474){rel=""nofollow""}, [Apple — AirPods Live Translation](https://support.apple.com/en-us/123185){rel=""nofollow""}, [Google Pixel Buds — real-time translation](https://support.google.com/googlepixelbuds/answer/7573100){rel=""nofollow""}, checked August 2026. InterMIND numbers verified against the shipped product.* # English–Italian voice translator: for a phrase, and for a conversation - **A phrase and a conversation are two jobs.** Any phone voice translator handles a direction or an announcement; a client call, interview or team meeting breaks the relay model. - **A conversation needs the call translated, not a phone.** Both directions at once, per listener, continuous rather than turn-based. - **InterMIND keeps the whole conversation in each participant's language,** English and Italian speakers hearing each other live, chat, notes and documents too. Guests join free by link, no account; you pay only for active members. If you need to translate spoken English into Italian, or Italian into English, two very different situations hide behind one search — and the right tool differs for each. **A phrase** — asking directions in London, catching an airport announcement, one exchange with a receptionist. Any phone voice translator does this well: speak, it plays back, done. Don't over-buy. **A conversation** — a call with an English-speaking client, a job interview, a meeting with an international team, an online class. This is the single most common language pair in work, and it's exactly where the phone-app model breaks, because it's a relay: you speak, it translates, it plays back, then the other person answers into the same device and it relays the other way. Two people passing a phone can just about manage. A real meeting can't. --- ## Why "voice translator" behaves differently in a conversation The phone-app and earbud models share one assumption: **two people, one device or one pair of earbuds, taking turns.** For English ↔ Italian that's fine when it's a traveler and a local. It falls apart the moment the exchange is a meeting: - More than two people — English-speaking colleagues on the call, you and an Italian colleague on the other side — and there's no single device to pass. - Everyone talking, interrupting, thinking out loud — the relay adds a beat to every turn, and the conversation stops flowing. - No shared hardware — you can't hand a Zoom or Teams call a pair of earbuds. A conversation needs the translation to be a property of the *call*, not of one person's phone: the English speakers hear you in English, you hear them in Italian, at the same time, live. That's live meeting translation — a different architecture, covered in full in [*Voice translator: what actually translates a live conversation*](https://intermind.com/blog/traduttore-vocale). --- ## What good English–Italian live translation looks like - **Both directions at once.** English → Italian *and* Italian → English, simultaneously, without anyone switching a mode or passing a device. - **Per-listener.** Each person hears the room in their own language, live — not "the translator reads it back after you stop talking." You speak Italian and stay focused on the content; your passive English stops being the meeting's bottleneck. - **Continuous, not turn-based.** A work call doesn't wait: the translation has to follow the rhythm of people interrupting and resuming, not impose its own. - **Quality you can check.** English ↔ Italian is one of the strongest pairs; we publish per-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark) rather than asserting accuracy. --- ## Where InterMIND fits InterMIND is a voice translator built for the conversation case: English speakers and Italian speakers on the same call, each hearing the other in their own language, live. One person opens the room and sends the link; the others join free, without an account. - **English and Italian are both live voice languages** — part of [23 languages on voice](https://intermind.com/features/realtime-translation), chat and shared notes, in any mix: a three-way call can run English ↔ Italian ↔ Spanish with nobody switching anything. - **Per-listener audio, live.** (Under the hood: [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Meetings, webinars and conferences** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant on their own listening language: [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation). - **Documents too** — share a PDF or DOCX and each side reads it in their own language. For a taxi in Manchester or a menu in New York, a phone app is all you need. For an English–Italian *conversation* — the client call, the interview, the team meeting — that's the job InterMIND was built for. --- ## Try it - **[Try the live demo](https://intermind.com/demo)** — *hear* English ↔ Italian translated live, per listener, in a real meeting — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair quality on real traffic, methodology included. - The full picture: [*Voice translator: what actually translates a live conversation*](https://intermind.com/blog/traduttore-vocale). - Other pairs: [French ↔ Italian](https://intermind.com/blog/traduttore-francese-italiano-vocale), [Spanish ↔ Italian](https://intermind.com/blog/traduttore-spagnolo-italiano-vocale), [Italian ↔ Russian](https://intermind.com/blog/traduttore-italiano-russo-vocale), [Romanian ↔ Italian](https://intermind.com/blog/traduttore-rumeno-italiano-vocale). — The Mind.com Team --- *Sources: the phone-app and earbud categories described above are documented by their vendors — [Google Translate — translate by speech](https://support.google.com/translate/answer/6142474){rel=""nofollow""}, [Apple — AirPods Live Translation](https://support.apple.com/en-us/123185){rel=""nofollow""}, [Google Pixel Buds — real-time translation](https://support.google.com/googlepixelbuds/answer/7573100){rel=""nofollow""}, checked August 2026. InterMIND numbers verified against the shipped product.* # Italian–Russian voice translator: for a phrase, and for a conversation - **A phrase and a conversation are two jobs.** Any phone voice translator handles a menu or a direction; a call between Italian and Russian-speaking teams breaks the relay model. - **A conversation needs the call translated, not a phone.** Both directions at once, per listener, Italian to Russian directly, not through English. - **InterMIND keeps the whole conversation in each participant's language,** Italian and Russian speakers hearing each other live, chat, notes and documents too. Guests join free by link, no account; you pay only for active members. If you need to translate spoken Italian into Russian, or Russian into Italian, two very different situations hide behind one search — and the right tool differs for each. **A phrase** — asking directions, reading a menu, one exchange with a shopkeeper. Any phone voice translator does this well: speak, it plays back, done. Don't over-buy. **A conversation** — a call between an Italian team and a Russian-speaking team, a negotiation, an interview, anything with back-and-forth and more than two people. Here the phone-app model breaks, because it's a relay: you speak, it translates, it plays back, then the other person answers into the same device and it relays the other way. Two people passing a phone can just about manage. A real conversation can't. --- ## Why "voice translator" behaves differently in a conversation The phone-app and earbud models share one assumption: **two people, one device or one pair of earbuds, taking turns.** For Italian ↔ Russian that's fine when it's a traveler and a local. It falls apart the moment the exchange is a meeting: - More than two people — a couple of Italian speakers, a couple of Russian speakers — and there's no single device to pass. - Everyone talking, interrupting, thinking out loud — the relay adds a beat to every turn, and the conversation stops flowing. - No shared hardware — you can't hand a video call a pair of earbuds. A conversation needs the translation to be a property of the *call*, not of one person's phone: every Italian speaker hears the Russian speakers in Italian, every Russian speaker hears the Italian speakers in Russian, at the same time, live. That's live meeting translation — a different architecture, covered in full in [*Voice translator: what actually translates a live conversation*](https://intermind.com/blog/traduttore-vocale). --- ## What good Italian–Russian live translation looks like - **Both directions at once.** Italian → Russian *and* Russian → Italian, simultaneously, without anyone switching a mode or passing a device. - **Per-listener.** Each person hears the room in their own language, live — not "the translator reads it back after you stop talking." - **Direct, not through English.** Italian ↔ Russian translated between the two languages, not Italian → English → Russian, which drops nuance twice — and matters more for a cross-family pair than for two Romance languages. - **Quality you can check.** We publish per-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark) rather than asserting accuracy. --- ## Where InterMIND fits InterMIND is a voice translator built for the conversation case: Italian and Russian speakers on the same call, each hearing the other in their own language, live. One person opens the room and sends the link; the others join free, without an account. - **Italian and Russian are both live voice languages** — part of [23 languages on voice](https://intermind.com/features/realtime-translation), chat and shared notes, any mix, no English anchor, no regional gate. - **Per-listener audio, live.** (How it works under the hood: [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Meetings, webinars and conferences** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant on their own listening language: [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation). - **Documents too** — share a PDF or DOCX and each side reads it in their language. For a menu or a taxi, a phone app is all you need. For an Italian–Russian *conversation*, that's the job InterMIND was built for. --- ## Try it - **[Try the live demo](https://intermind.com/demo)** — *hear* Italian ↔ Russian translated live, per listener, in a real meeting — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair quality on real traffic, methodology included. - The full picture: [*Voice translator: what actually translates a live conversation*](https://intermind.com/blog/traduttore-vocale). — The Mind.com Team # Romanian–Italian voice translator: for a phrase, and for a conversation - **A phrase and a conversation are two jobs.** Any phone voice translator handles a direction or a form line; a family call, interview or supplier meeting breaks the relay model. - **A conversation needs the call translated, not a phone.** Both directions at once, per listener, Romanian to Italian directly, not through English. - **InterMIND keeps the whole conversation in each participant's language,** Romanian and Italian speakers hearing each other live, chat, notes and documents too. Guests join free by link, no account; you pay only for active members. If you need to translate spoken Romanian into Italian, or Italian into Romanian, two very different situations hide behind one search — and the right tool differs for each. **A phrase** — a street direction, one line of a form, a quick exchange at a counter. Any phone voice translator does this well: speak, it plays back, done. Don't over-buy. **A conversation** — a family video call between Italy and Romania, a job interview, a meeting with a supplier in Bucharest, an important appointment where the details matter. Romanian–Italian is one of the most lived language pairs in Italy — and it's exactly where the phone-app model breaks, because it's a relay: you speak, it translates, it plays back, then the other person answers into the same device and it relays the other way. Two people passing a phone can just about manage. A real conversation can't. --- ## Why "voice translator" behaves differently in a conversation The phone-app and earbud models share one assumption: **two people, one device or one pair of earbuds, taking turns.** For Romanian ↔ Italian that's fine when the exchange is short and in person. It falls apart the moment it's a real call: - More than two people — relatives in Romania on one side, family in Italy on the other — and there's no single device to pass. - Everyone talking, interrupting, thinking out loud — the relay adds a beat to every turn, and the conversation stops flowing. - No shared hardware — you can't hand a video call a pair of earbuds. A conversation needs the translation to be a property of the *call*, not of one person's phone: Romanian speakers hear the Italian side in Romanian, Italian speakers hear the Romanian side in Italian, at the same time, live. That's live meeting translation — a different architecture, covered in full in [*Voice translator: what actually translates a live conversation*](https://intermind.com/blog/traduttore-vocale). --- ## What good Romanian–Italian live translation looks like - **Both directions at once.** Romanian → Italian *and* Italian → Romanian, simultaneously, without anyone switching a mode or passing a device. - **Per-listener.** Each person hears the call in their own language, live — not "the translator reads it back after you stop talking." - **Direct, not through English.** Romanian ↔ Italian translated between the two languages, not Romanian → English → Italian, which drops nuance twice — and for two close Romance languages, nuance is half the meaning. - **Quality you can check.** We publish per-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark) rather than asserting accuracy — see how Romanian ↔ Italian stands before you rely on us. --- ## Where InterMIND fits InterMIND is a voice translator built for the conversation case: Romanian speakers and Italian speakers on the same call, each hearing the other in their own language, live. One person opens the room and sends the link; the others join free, without an account. - **Romanian and Italian are both live voice languages** — part of [23 languages on voice](https://intermind.com/features/realtime-translation), chat and shared notes, in any mix, no English anchor. - **Per-listener audio, live.** (Under the hood: [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Guests join from one link, in the browser** — the person on the other side installs nothing and signs up for nothing: they open the link and speak their own language. - **Documents too** — share a PDF or DOCX and each side reads it in their own language. For one phrase at a counter, a phone app is all you need. For a Romanian–Italian *conversation* — the family video call, the interview, the negotiation — that's the job InterMIND was built for. --- ## Try it - **[Try the live demo](https://intermind.com/demo)** — *hear* Romanian ↔ Italian translated live, per listener, in a real meeting — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair quality on real traffic, methodology included. - The full picture: [*Voice translator: what actually translates a live conversation*](https://intermind.com/blog/traduttore-vocale). - Other pairs: [English ↔ Italian](https://intermind.com/blog/traduttore-inglese-italiano-vocale), [French ↔ Italian](https://intermind.com/blog/traduttore-francese-italiano-vocale), [Spanish ↔ Italian](https://intermind.com/blog/traduttore-spagnolo-italiano-vocale), [Italian ↔ Russian](https://intermind.com/blog/traduttore-italiano-russo-vocale). — The Mind.com Team # Spanish–Italian voice translator: for a phrase, and for a conversation - **A phrase and a conversation are two jobs.** Any phone voice translator handles a menu or a direction; a call between Spanish and Italian teams breaks the relay model. - **A conversation needs the call translated, not a phone.** Both directions at once, per listener, Spanish to Italian directly, not through English. - **InterMIND keeps the whole conversation in each participant's language,** Spanish and Italian speakers hearing each other live, chat, notes and documents too. Guests join free by link, no account; you pay only for active members. If you need to translate spoken Spanish into Italian, or Italian into Spanish, two very different situations hide behind one search — and the right tool differs for each. **A phrase** — asking directions in Madrid, reading a menu in Rome, one exchange with a shopkeeper. Any phone voice translator does this well: speak, it plays back, done. Don't over-buy. **A conversation** — a call between a Spanish team and an Italian team, a negotiation, an interview, anything with back-and-forth and more than two people. Here the phone-app model breaks, because it's a relay: you speak, it translates, it plays back, then the other person answers into the same device and it relays the other way. Two people passing a phone can just about manage. A real conversation can't. --- ## Why "voice translator" behaves differently in a conversation The phone-app and earbud models share one assumption: **two people, one device or one pair of earbuds, taking turns.** For Spanish ↔ Italian that's fine when it's a traveler and a local. It falls apart the moment the exchange is a meeting: - More than two people — a couple of Spanish speakers, a couple of Italian speakers — and there's no single device to pass. - Everyone talking, interrupting, thinking out loud — the relay adds a beat to every turn, and the conversation stops flowing. - No shared hardware — you can't hand a video call a pair of earbuds. A conversation needs the translation to be a property of the *call*, not of one person's phone: every Spanish speaker hears the Italian speakers in Spanish, every Italian speaker hears the Spanish speakers in Italian, at the same time, live. That's live meeting translation — a different architecture, covered in full in [*Voice translator: what actually translates a live conversation*](https://intermind.com/blog/traduttore-vocale). --- ## What good Spanish–Italian live translation looks like - **Both directions at once.** Spanish → Italian *and* Italian → Spanish, simultaneously, without anyone switching a mode or passing a device. - **Per-listener.** Each person hears the room in their own language, live — not "the translator reads it back after you stop talking." - **Direct, not through English.** Spanish ↔ Italian translated between the two languages, not Spanish → English → Italian, which drops nuance twice. - **Quality you can check.** For a Romance pair like Spanish–Italian the translation is strong; we publish per-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark) rather than asserting accuracy. --- ## Where InterMIND fits InterMIND is a voice translator built for the conversation case: Spanish and Italian speakers on the same call, each hearing the other in their own language, live. One person opens the room and sends the link; the others join free, without an account. - **Spanish and Italian are both live voice languages** — part of [23 languages on voice](https://intermind.com/features/realtime-translation), chat and shared notes, any mix, no English anchor, no regional gate. - **Per-listener audio, live.** (How it works under the hood: [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Meetings, webinars and conferences** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant on their own listening language: [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation). - **Documents too** — share a PDF or DOCX and each side reads it in their language. For a menu in Seville or a taxi in Milan, a phone app is all you need. For a Spanish–Italian *conversation*, that's the job InterMIND was built for. --- ## Try it - **[Try the live demo](https://intermind.com/demo)** — *hear* Spanish ↔ Italian translated live, per listener, in a real meeting — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair quality on real traffic, methodology included. - The full picture: [*Voice translator: what actually translates a live conversation*](https://intermind.com/blog/traduttore-vocale). — The Mind.com Team # Voice translator: what actually translates a live conversation - **Three products share one name.** A phone app relays a phrase, earbuds translate one person, live meeting translation runs the whole call in each participant's language at once. - **Phrase or conversation decides.** A phone app for a phrase, earbuds for one person face to face, live meeting translation for several people on a call. - **InterMIND keeps the whole conversation in each participant's language,** voice, chat, notes and documents, per listener and continuous. Guests join free by link, no account; you pay only for active members. Search "voice translator" and you get three products wearing one name. A phone app that listens, then reads the translation back to you. A pair of earbuds that whisper a translation of the person in front of you. And live meeting translation, where a whole call runs in several languages at once and everyone hears it in their own. They all "translate voice." Only the last one keeps a *conversation* moving without turning every exchange into a two-step relay. This guide separates the three, shows how each actually works, and names the one question that decides which you need: **is this a phrase, or is this a conversation?** --- ## The three things "voice translator" means ### 1. Phone-app voice translators The familiar one: open an app, tap the mic, speak, and it plays back — or displays — the translation. Google Translate, Apple Translate, Microsoft Translator and dozens of travel apps do this. They're genuinely good at what they're for: a menu, a taxi, a hotel desk, one sentence at a time. The mechanic is a relay. You speak → it transcribes → it translates → it speaks back. Then the other person answers into the same phone and it relays the other way. It works because the exchanges are short and you're both willing to pass one device back and forth. Stretch it to a real back-and-forth — three people, interruptions, someone thinking out loud — and the relay is the bottleneck. You're not having a conversation; you're taking turns operating a translator. ### 2. Earbud / device translators The 2025–2026 hardware wave: AirPods with Apple's Live Translation, Pixel Buds, dedicated translator earbuds. You wear them, the other person speaks, and you hear a translation in your ear. It feels closer to a conversation because you're not staring at a screen. But look at the shape: it's **one-to-one, and one-directional at a time.** It translates the person in front of you, into your ear, on your device. For it to be mutual, they need the same gear and the same setup. It's built for a traveler and a shopkeeper, not for five people on a call who each speak a different language. The moment the "room" has more than two people, or the other people aren't holding a compatible device, the model breaks. ### 3. Live meeting translation The third thing is a different architecture, not a better app. In a live meeting translator, the *room* is multilingual: each participant speaks their own language, and each participant hears everyone else in **their** language, at the same time, for as long as the meeting runs. No one passes a phone. No one wears matching earbuds. The translation is a property of the call, not of any one person's device. This is the only one of the three that survives a real conversation — several people, all talking, no shared hardware, no English in the middle. --- ## How to tell which one you actually need One question does it: - **Is it a phrase?** — a menu, a direction, one sentence to a stranger. A phone app is perfect. Don't over-buy. - **Is it a face-to-face exchange with one person, and you both have the gear?** — earbuds are the nicest experience. - **Is it a conversation — a call, a meeting, several people, back-and-forth?** — you need live meeting translation, because the other two turn every exchange into a relay and every extra person into a broken assumption. The trap is using a phrase tool for a conversation. It technically "works" — and it makes the conversation twice as slow and half as human, because everyone is waiting on the relay instead of talking. --- ## What "live" really has to mean For a voice translator to hold a conversation together, three things have to be true at once — and this is where most tools quietly fail: - **Per-listener, not per-device.** Every participant hears the room in their own picked language, simultaneously — five people, five languages, one call. Not "you translate what's said to you"; the *whole room* is translated for *everyone*, each to their own language. - **Continuous, not after the pause.** If translation only arrives after the speaker pauses, it's consecutive interpretation with a synthetic voice — you feel every gap. Real live translation keeps pace with the talking. - **No English anchor, no regional gate, no five-language beta.** Any mix of languages, translated between the participants directly — not everything routed through English, not five languages in a beta. That's not a bigger phone app. It's the architecture behind [real-time meeting translation](https://intermind.com/blog/real-time-meeting-translation) — the foundational guide to the category, if you want the full picture of how it works and what to ask before buying one. --- ## Where InterMIND sits InterMIND is the third kind: a voice translator for real conversations, built as live meeting translation rather than a phrase relay. It starts with one person: you open the room and send the link; the others join free, without an account, each in their own language. - **23 languages live on voice**, chat and shared notes — any mix, no English anchor, no regional gate, no five-language beta. ([The full end-to-end translation stack](https://intermind.com/features/realtime-translation) is its own page.) - **Per-listener audio, live.** Each participant hears the meeting in their own picked language at the same time. (How that works under the hood: [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Webinars and conferences included** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant picking their own listening language. That's [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation), not an add-on. - **Documents too** — drop a PDF or DOCX into the meeting and each viewer gets it in their language, 30 languages on files. - **Quality you can audit.** We publish per-language-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark), with the methodology written down — not accuracy claims in a press release. A phone app is right for a phrase. Earbuds are right for one person in front of you. When it's a *conversation* — several people, several languages, no shared hardware — that's the job InterMIND was built for. --- ## Try the conversation side of it - **[Try the live demo](https://intermind.com/demo)** — *hear* a real meeting translated live, per listener, in any of 23 languages — no signup needed. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month translation quality on real traffic, methodology included. - New to the category? Start with [*Real-time meeting translation: how it works, and how to evaluate one*](https://intermind.com/blog/real-time-meeting-translation). - Comparing specific language pairs? See the voice-pair guides for [English ↔ Italian](https://intermind.com/blog/traduttore-inglese-italiano-vocale), [French ↔ Italian](https://intermind.com/blog/traduttore-francese-italiano-vocale), [Spanish ↔ Italian](https://intermind.com/blog/traduttore-spagnolo-italiano-vocale), [Italian ↔ Russian](https://intermind.com/blog/traduttore-italiano-russo-vocale), [Romanian ↔ Italian](https://intermind.com/blog/traduttore-rumeno-italiano-vocale) and [Hindi ↔ English](https://intermind.com/blog/hindi-to-english-voice-translator). - Same three-way split, written for another market: [French](https://intermind.com/blog/traducteur-vocal), [Spanish](https://intermind.com/blog/traductor-de-voz), [Portuguese](https://intermind.com/blog/tradutor-de-voz), [German](https://intermind.com/blog/sprachuebersetzer), [Turkish](https://intermind.com/blog/sesli-cevirmen). - Weighing the earbud route specifically? [What AirPods Live Translation does well, and where a meeting needs more](https://intermind.com/blog/airpods-live-uebersetzung). "Voice translator" is three products. Match the tool to the shape of the exchange — phrase, face-to-face, or conversation — and the choice makes itself. — The Mind.com Team --- *Sources: [Google Translate — translate by speech](https://support.google.com/translate/answer/6142474){rel=""nofollow""}, [Apple — AirPods Live Translation](https://support.apple.com/en-us/123185){rel=""nofollow""}, [Google Pixel Buds — real-time translation](https://support.google.com/googlepixelbuds/answer/7573100){rel=""nofollow""}, checked August 2026. Vendors change features and language lists over time — check their pages for the current state. InterMIND numbers verified against the shipped product.* # How to transcribe WhatsApp voice messages — and what to do when the audio is in another language - **WhatsApp already does it, on-device.** Settings → Chats → Voice message transcripts, long-press a voice note → Transcribe; the audio never leaves the encrypted chat. - **It fails predictably and can't translate.** Noise, slang and mixed languages mangle the text, and a transcript in a language you don't read stays unreadable. - **InterMIND keeps the whole conversation in each side's language:** when voice notes are really a conversation, move it to a call where each side speaks and hears their own language. Guests join free by link, no account. The three-minute voice note always lands at the worst time: you're in a meeting, somewhere loud, or just can't listen right now. The good news: for most cases **you don't need any extra app** — WhatsApp transcribes voice messages by itself, right on the device. The less-good news: transcription fails in predictable situations, and there's a whole case it can't solve — when the audio is in a language you don't speak. This guide covers all three scenarios, from the simplest to the most overlooked. --- ## 1. The built-in path: WhatsApp's own transcription Since late 2024 WhatsApp transcribes voice messages natively — as of August 2026 the transcript languages are English, Portuguese, Spanish and Russian. Two details matter: - **Transcription happens on your device.** The audio isn't shipped to a transcription server — processing is local, and the chat's end-to-end encryption stays intact. That's the reason to prefer the native feature over any third-party app. - **It's opt-in and per message.** You enable it once, then transcribe only the voice notes you want. The path (exact menu names vary slightly by version): 1. **Settings → Chats → Voice message transcripts** — switch it on and pick a language. The device downloads a small language pack, once. 2. In the chat, **long-press the voice note → Transcribe**. The text appears under the message itself. If the option isn't there, update the app — the feature rolled out in stages and needs a reasonably recent WhatsApp (and, on iPhone, a recent iOS). --- ## 2. Where native transcription fails — and what you can actually do On-device transcription is good, but it isn't magic. The failure modes are predictable: - **Noisy audio, background music, or a far-away microphone.** The local model is compact; it degrades faster than a server-side transcriber. There's no button that fixes it — ask for the audio again, or listen at 1.5×. - **Mixed languages in one message** ("and then he said *isso não foi o que combinamos*…") — the transcript follows the configured language and mangles the other-language stretch. - **Heavy slang, proper names, technical terms.** The text comes out with holes exactly where the important words were. - **WhatsApp Web / Desktop:** transcription is a phone feature; in the browser it may simply not be there. Transcribe on the phone. What **not** to do: forward the voice note to some unknown "WhatsApp transcriber app." Forwarding takes the message out of the encrypted chat and hands it to a third-party server with a privacy policy you haven't read. For a personal or work audio that's rarely a sensible trade — especially with the local path sitting there for free. --- ## 3. The case transcription can't solve: the audio is in another language Here's the fastest-growing scenario — and the one no "Transcribe" button fixes: the supplier in China, the customer in the US, the relative who emigrated. The voice note arrives, transcription even works… **and the text is still in a language you can't read.** You can paste the transcript into a text translator, of course. It works once. But look at what the flow became: listen → transcribe → copy → paste → translate → write a reply → translate it back → record. Every loop is friction, and working conversations run ten loops a day. The real problem stopped being "turn audio into text" — it's **holding a conversation across languages**. That problem has its own category — the [voice translator](https://intermind.com/blog/tradutor-de-voz) — and one criterion decides the choice: is this a one-off phrase, or a conversation that will continue? - **One-off phrase:** the transcribe-copy-translate loop is fine, and any translation app will do. - **Ongoing conversation:** the chain of voice notes is the symptom — you're *conversing* by messages because talking live was impossible. That's exactly the case for live meeting translation: in InterMIND, each side speaks their own language on a call and hears the other in theirs, **across 23 languages, with per-listener audio live** — nothing to transcribe, copy or paste. And the meeting ends with a recap note for whoever missed it. Want to feel the difference without scheduling anything: open [`/demo`](https://intermind.com/demo), play a stretch of audio (it can be that exact voice note) near the microphone, and *hear* the live translation instead of reading it. Then [start your first meeting](https://intermind.com/chats) — guests join by link, each in their own language. --- ## The practical summary | Situation | Best path | | ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- | | Can't listen right now | WhatsApp's native transcription (on-device, encryption intact) | | Noisy audio / slang / mixed languages | Listen at 1.5× — local transcription will fail | | Personal audio + third-party app | Avoid: the audio leaves the encrypted chat | | Audio in another language, one-off | Transcribe → translate the text | | Ongoing cross-language conversation | [Live meeting voice translator](https://intermind.com/blog/tradutor-de-voz) — everyone speaks and hears their own language | WhatsApp transcription is one of those features already sitting in your pocket that half of us never switched on. Switch it on. And when the transcript is still unreadable because the language is the problem — the problem changed its name, and so does the tool: [it's a conversation, not a phrase](https://intermind.com/blog/tradutor-de-voz). --- ## FAQ **How do I turn on WhatsApp voice message transcripts?** Settings → Chats → Voice message transcripts — switch it on and pick a language (the device downloads a small language pack once). Then in any chat, long-press a voice note → Transcribe. **Is the voice note sent to a server for transcription?** No — WhatsApp's transcription runs on your device, and the chat's end-to-end encryption stays intact. That's the reason to prefer it over any third-party "WhatsApp transcriber" app, which requires taking the audio out of the encrypted chat. **Which languages can WhatsApp transcribe?** English, Portuguese, Spanish and Russian (as of August 2026, per WhatsApp's help page). A voice note in another language — or mixing two languages — comes out mangled. **What if the voice message is in a language I don't speak?** Transcription doesn't solve that — the text is still unreadable. For a one-off, transcribe and paste into a text translator. For an ongoing conversation, that's the [voice translator](https://intermind.com/blog/tradutor-de-voz) category: a live call where each side speaks and hears their own language. — The Mind.com Team --- *Sources: [WhatsApp — How to turn voice message transcripts on or off](https://faq.whatsapp.com/241617298315321){rel=""nofollow""}, [WhatsApp blog — voice message transcripts announcement](https://blog.whatsapp.com/making-voice-messages-easier-with-transcripts){rel=""nofollow""}, checked August 2026. WhatsApp changes features and language lists over time — check their pages for the current state.* # Translated captions, live translation and an AI copilot during the meeting: how each participant gets them inside an InterMIND room (2026) - **Inside the room, for everyone.** The host opens it; each participant hears the others translated and reads the captions in their chosen language, nothing to install. - **Three limits, stated plainly.** No speaker label on the banner, a mid-meeting language switch is one click rather than automatic, and a guest gets nothing after the call. - **InterMIND keeps the whole meeting in each member's language,** voice, captions, chat and the recap. Guests join free by link, no account; you pay only for active members. A call where two or three languages are spoken has one question that cannot wait for the notes: what is being said right now, in words I read without effort? Two answers are on the market. One is a copilot that runs beside the call — on the listener's own screen — and shows that person a live transcript, translated, with AI help while the conversation runs. The other is a room where the host provides the same thing for everyone in it, and where it stays after the call. This guide shows the second answer in detail, as it works in InterMIND today, after a short map of the first. ## The copilot beside the call: what Bearbits states Bearbits was shown on Hacker News on 4 October 2026 by its author, who built it "mainly for myself and my wife" to "see in real time what's being said, irrespective of the language being spoken", with real-time translation into a chosen language and "suggestions for what to say that are grounded in actual web search". The public pages state the following (checked October 2026; sources at the end): - **Where it runs.** "Bearbits runs in your browser and captures audio you share" — it "never joins your call as a participant" and works with "Zoom, Google Meet, Teams, or any browser-based call". The documentation describes capturing "microphone and system audio", with a tab or screen share used only for the audio; no recording is kept. - **Languages.** "Live multilingual transcription with speaker labels" in "60+ languages", and "Real-time translation into a selected language". On language changes: "Set language hints so the recognizer matches the languages you expect. You can adjust during a meeting if speakers switch languages." Transcription runs on Soniox, web search on Exa.ai (per the author's post). - **The copilot.** An in-call assistant with "What do I say?, Anti-BS, Catchup, and Ask AI — grounded in your transcript and workspace context", and "Current web research with public sources during the meeting". - **Who sees it.** Transcripts are "private to your authenticated account". Whether other participants of the call see anything is not stated in the public documentation. - **Price.** Prepaid credits, "No subscription": $15 for 5, $45 for 20, $100 for 100; "Each credit covers up to two hours, and stays ready for 90 days." The author offers "30 minutes usage for free". That is the copilot: one participant's own window beside somebody else's meeting, paid per meeting by that participant. ## The room: the host provides it for everyone In InterMIND the meeting itself is the place where every participant speaks, hears and reads in their own language. Nobody brings a tool to the call — the host opens the room, and what follows is there for every person who joins the link, with or without an account. ### Captions and voice, each in the listener's language Translation in a room is switched on once the room has at least two languages — **More → Enable translation**, or **Alt+T**. From then on each participant hears the others translated into their own language, in a voice modelled on the original speaker's rather than a generic narrator ([how that pipeline works](https://intermind.com/blog/own-voice-translation)). A five-person call with five languages is five simultaneous translations, each picked by its listener. The captions are the text of that same translated stream. **More → Show subtitles** puts a banner at the bottom of the screen with what the current speaker is saying, in the language you chose; the banner fades when nobody speaks, flips to right-to-left when the target language calls for it, and remembers its on/off state per browser, so the choice made in one meeting holds in the next. Two limits, stated plainly: - The subtitle banner shows the translated text of the current speaker. It does not print a speaker label next to each line — speaker attribution lives in the transcript after the call (below). - The banner is text on top of the translated audio, not a separate transcript window; the live written record of the meeting as a whole is produced when the meeting ends. ### Languages, and what happens when someone switches Voice, chat and shared notes share one list of **23 languages**; files shared into the chat use a wider list of 30 ([why the numbers differ](https://intermind.com/blog/how-many-languages-do-you-support)). Every language is available on every plan. Each participant has one language of their own: by default it follows the interface language, and the **Translation language** submenu in the More menu changes it at any moment during the meeting — the switch takes effect immediately. That is also the honest answer to the mid-meeting switch: InterMIND does not detect on its own that a speaker has moved from Spanish to English in the middle of a call. The speaker's language is the one they declared, and changing it is one click in the same menu — speech recognition is given that declared language rather than guessing one. ### What a guest needs to install: nothing A participant opens the link in a browser, picks their language on the join page, and is in the room with translation, captions and their own words going into the shared transcript — no account, no payment surface. Apps for the desktop, iOS and Android exist for people who use InterMIND every day; the guest of one meeting needs none of them. The host's plan pays for the room; participants pay nothing, whoever hosts. ### The transcript and the recap: the part that stays Transcription has no Start button. From the first word of a live meeting, speech is captured on the server, attributed to the person who said it, in the language it was spoken. When the meeting ends, a recap appears in the meeting chat — the summary in each member's own language — and its **Transcript** tab holds the full speaker-attributed, timestamped transcript, translated on demand into the language of whoever opens it. Every signed-in member receives it; a channel keeps every session's recap next to its chat. The limit here is the one the terminology hides: a guest who joined without an account gets the full room during the call and nothing afterwards — there is no account to deliver a recap to, and the anonymous identity is not kept once the call ends. An account is free, and it is what makes the after-the-call half reachable. ### The AI in the room Mia is the organization's AI, and she is in the same window as the meeting. Signed in on a paid plan, **Cmd/Ctrl + /** (or **Mia** in the sidebar) opens her panel on any page and inside a meeting room. She knows which screen you are on, answers from your organization's meetings, chats and files, and can prepare a meeting link or a message for you to confirm. When a question needs facts from outside the organization — a company, a price, a law, another product's documentation — she searches the web and gives the address of every fact she takes from it. What leaves InterMIND for that search is the phrase Mia words herself, never a document, recap or chat; an owner or admin switches the search off for the whole organization under **Settings → AI features**. Aloud in a meeting she does not search. Every AI feature of the organization — recaps, document summaries, the writing assistant, Mia — runs on **one language-model gateway the organization chooses**: Azure OpenAI in the EU Data Zone by default, Google Vertex AI in the EU, Amazon Bedrock in the organization's own AWS account, or the organization's own OpenAI-compatible endpoint; AI can be switched off per organization, and meetings are still transcribed and translated with it off ([the gateway, in detail](https://intermind.com/blog/meeting-ai-on-your-own-cloud-gateway)). ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup: speak, and hear the room translated back to you with the captions on. - **[See the benchmark](https://intermind.com/benchmark)** — per-language-pair translation quality, measured monthly on real traffic, methodology public. - **[Read the subtitles docs](https://intermind.com/docs/translation/subtitles)** and **[the transcription docs](https://intermind.com/docs/translation/transcription)** — the full mechanics. --- ## FAQ **How do I turn on translated captions in a meeting?** In an InterMIND room, open **More** in the control bar: **Enable translation** (or Alt+T) once the room has at least two languages, then **Show subtitles**. The banner shows what the current speaker is saying, translated into the language you chose; the same item becomes **Hide subtitles**. The on/off state is remembered per browser for the next meeting. **Can the captions be translated into a different language for each participant?** Yes. Each participant picks their own translation language — the one setting covers the translated voice, the captions and chat messages — so in one room the same sentence appears in Spanish on one screen and in German on another. The choice is per person, not per meeting, and changes at any moment from the **Translation language** submenu. **Is live translation or captioning an add-on I have to buy?** No. Translation, subtitles and automatic transcription are part of every InterMIND plan, the free one included; what the plan sets is the room size and the monthly translation time, listed on the [Usage & Limits](https://intermind.com/docs/billing/usage) page and on [Pricing](https://intermind.com/pricing). Participants never pay — only the host's plan counts. **What is the difference between live captions and a transcript?** Captions are the translated text of the current speaker, shown on screen while the meeting runs, without a speaker label. The transcript is the written record produced when the meeting ends: every turn attributed to its speaker, timestamped, kept in the language it was spoken and translated on demand when a member opens it in their own language. It is reached from the recap in the meeting chat. **Does the AI help during the call, or only after it?** Both, in different forms. During the meeting a signed-in member on a paid plan opens Mia with Cmd/Ctrl + / in the same window: she answers from the organization's meetings, chats and files and searches the web when a question needs it, with a source for every fact. After the meeting the recap and the transcript arrive in each member's language. A spoken Mia who listens in the room and answers by name is in preview — it is being tested inside InterMIND; any account can switch her on under Settings → Advanced after accepting the alpha terms (the [Preview features](https://intermind.com/previews) page describes each one). **Does a guest need to install anything to get the captions?** No. A guest opens the meeting link in a browser, picks a language on the join page, and has the translated voice, the captions and their own words in the shared transcript. Apps exist for desktop and phones, but a guest of one meeting does not need them — and pays nothing. **What happens if a speaker switches languages in the middle of the meeting?** The speaker changes their declared language in **More → Translation language**; the switch takes effect immediately. InterMIND does not guess a language change on its own: speech is recognized in the language the speaker declared. --- *Sources: [Bearbits — home page](https://bearbits.io/){rel=""nofollow""}, [Bearbits — documentation](https://bearbits.io/docs){rel=""nofollow""}, [Bearbits — Live meetings](https://bearbits.io/docs/live-meetings){rel=""nofollow""}, [Bearbits — pricing](https://bearbits.io/pricing){rel=""nofollow""}, [Show HN: Bearbits – AI copilot that helps during meetings instead of only after](https://news.ycombinator.com/item?id=49954800){rel=""nofollow""}, all checked October 2026. InterMIND facts: [real-time translation docs](https://intermind.com/docs/translation), [live subtitles docs](https://intermind.com/docs/translation/subtitles), [choosing languages](https://intermind.com/docs/translation/languages), [transcription docs](https://intermind.com/docs/translation/transcription), [meeting recap](https://intermind.com/docs/meetings/recap), [AI features and Mia](https://intermind.com/docs/settings/ai-features), [usage and limits](https://intermind.com/docs/billing/usage), [language breakdown](https://intermind.com/blog/how-many-languages-do-you-support), [own-voice translation](https://intermind.com/blog/own-voice-translation), [live benchmark](https://intermind.com/benchmark).* # How live translation, captions, and a searchable transcript work together in one InterMIND meeting - **One switch, not three.** Transcription is always on; translation is enabled once from the More menu and captions follow by default, each participant in their own language. - **Searchable means the transcript, not the summary.** Each turn lands in the meeting chat and chat search finds it; the short AI summary surfaces by its title only. - **InterMIND keeps the whole meeting in each member's language,** voice, captions, chat and the recap with its transcript. Guests join free by link, no account; you pay only for active members. A team spread across four time zones does not have a language problem on the calendar invite — it has one the moment somebody starts talking. Live translation, live captions and a transcript you can go back to are the three things that actually remove that friction, and increasingly they show up together on a single product page, described as one bundle rather than three separate add-ons. One recent example: a September 2026 post from workplace platform NexGen Virtual Workplace opens with "Live voice translation, meeting captions, and searchable transcripts, built into the workday rather than bolted onto the meeting," and states that "these features are available within the NexGen Virtual Workplace platform for subscribers to use." That is the whole specification on offer — the post does not name a supported language count, does not say which subscription tier unlocks the three features, and does not describe what "searchable" means beyond "people can also look up past transcriptions... for a reference" (checked September 2026, source linked at the end). None of that is a criticism of the vendor; it is simply what a reader has to go find out elsewhere, or take on faith, before knowing whether the bundle fits their team. Since the same three words — translation, captions, transcript — get used for meaningfully different mechanics across products, here is the specific, checkable version of each as it works in InterMIND today. ## Translation: you turn it on, and it is your own voice Translation is not ambient — you enable it deliberately, per meeting, from the **More** menu in the control bar (or the **Alt+T** shortcut), available once the room has at least two languages. From there each participant sets their own translation language independently; in a five-person call with five languages, everyone hears everyone else translated into their own, simultaneously. The output is not a generic narrator voice. Speech recognition, sentence segmentation, translation and voice synthesis run as a pipeline, and the last stage resynthesizes the translated sentence in a version of the original speaker's own voice — recognizably them, not a flat text-to-speech read-out. The technical breakdown of how that pipeline works is in a [separate post](https://intermind.com/blog/own-voice-translation); the summary here is that once translation is on, "who said it" survives translation, not just "what was said." Coverage is 23 languages for voice, chat and shared notes, and 30 for whole-document file translation — the split and the reasons for it are in [the language breakdown](https://intermind.com/blog/how-many-languages-do-you-support). ## Captions: on by default, not a separate toggle to remember Live captions in InterMIND are the translated text of the same stream, shown as a subtitle banner during the meeting. Two details matter more than the feature existing at all: - **The default is on.** A participant who changes nothing already sees the translated speech on screen once translation is enabled — there is no second switch to discover mid-meeting. - **The banner remembers your last choice, per browser**, so turning captions off in one meeting keeps them off in the next until you turn them back on, and it renders right-to-left automatically when the target language calls for it. Captions are a read channel on top of the same translated audio, not a separate product with its own settings page to configure in advance — which is the opposite of the "who gets to see which caption language" question that dominates on platforms where caption languages are an organizer-side setting picked before the event. How the same captions compare with a copilot that runs beside the call on one participant's screen is in [a separate guide](https://intermind.com/blog/translated-captions-and-live-translation-in-the-room). ## Transcription: automatic, and specific about what "searchable" covers Transcription has no Start/Stop button. From the moment a meeting is live, every word is captured, attributed to the speaker who said it, and stored on the server in the language it was actually spoken in — nobody has to remember to turn it on, and nobody can forget to. After the meeting, a **recap** message appears in the meeting chat; opening it and switching to the **Transcript** tab shows the full, speaker-attributed, timestamped transcript, translatable on demand into the reader's own language even though it was captured in the speakers' original ones. "Searchable" is the word that needs the most precision, so here is exactly what it means today, without rounding up: - **Within the meeting's chat, it is real text search.** Each turn of speech lands as a transcription message in the channel as the meeting runs, and those messages are covered by the same chat search every other message is — **Ctrl/⌘+F** opens it, you type a keyword, and matching messages jump into view with context. - **The transcript page itself is plain rendered text**, so your browser's own page search finds a word or a name on it exactly as it would on any web page. - **What is not yet full-text search is the AI-written summary that sits above the transcript in the recap** — today that summary surfaces by its title, not by searching its body. If what you are hunting for is a specific sentence someone said, the transcript tab is where it lives and where search reaches it; the short summary is a separate object with a narrower search surface, and closing that gap is on our roadmap. That distinction — a spoken-word archive that is genuinely searchable, next to a short AI summary that currently is not — is the kind of specific behavior a one-line "searchable transcripts" bullet on a product page tends to skip past. ## One seat, one plan limit — not three licenses None of the three is gated behind its own add-on or its own license tier. What scales with the plan is the size of the room: 50 participants on Basic, 100 on Pro, 300 on Business, 1500 on Enterprise. A host on any plan gets translation, captions and transcription together; upgrading changes how many people can be in the room, not which of the three features they get. ## What a guest gets, and what they do not keep A participant who joins through a meeting link without ever creating an account gets the full in-meeting experience — their own translation language (defaulting to their interface language, which itself follows the browser), captions in it, and their words captured into the shared transcript like anyone else's. What they do not get is anything afterward: there is no account to deliver a recap to, and the anonymous identity is not retained once the call ends. An account is free, and it is specifically what makes the after-the-call half — the recap, the searchable transcript, the channel history — reachable later. That is a real limit, worth stating plainly rather than glossing over, since it is the opposite of the parts of this feature set that sound unconditional. ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup: speak, and hear the room translated back to you. - **[See the benchmark](https://intermind.com/benchmark)** — per-language-pair translation quality, measured monthly on real traffic, methodology public. - **[Read the transcription docs](https://intermind.com/docs/translation/transcription)** — the full mechanics of how a transcript is captured and read back translated. --- ## FAQ **Do I need to turn on translation, captions and transcription separately?** Transcription is always on, automatically, from the moment a meeting starts. Translation is a deliberate choice — enabled from the More menu or Alt+T, once the room has at least two participant languages. Captions are the translated text of that same stream and default to on the moment translation is enabled, so in practice there is one switch to think about, not three. **Can I actually search a meeting transcript, or just scroll it?** Both. The transcript is captured turn by turn as chat messages during the meeting, and those are covered by the same chat search (Ctrl/⌘+F) as every other message — type a keyword and matching turns jump into view. The full transcript page is also plain text, so a browser's own page search works on it directly. The one thing not yet covered by full-text search is the body of the short AI-written meeting summary, which today surfaces by its title. **Does everyone hear the same translated voice, or does it keep the speaker's own voice?** Each participant's translated speech is resynthesized in a voice modeled on their own, not a shared generic narrator — the effect is a translated conversation that still sounds like the people having it, in both directions and for every participant independently. **What happens to the transcript and recap if someone joins as a guest, with no account?** A guest gets full in-meeting translation, captions and transcription like any other participant. What does not carry over is anything afterward: there is no account for the recap or transcript to go to, and the guest's anonymous identity is not kept once the meeting ends. Signing up (free) is what makes the after-the-call record reachable. **Is there a separate plan or add-on for translation, captions or transcription?** No — all three ship together on every plan. What changes between plans is the number of participants a host can host at once: 50 on Basic, 100 on Pro, 300 on Business, 1500 on Enterprise. --- *Sources: [NexGen Virtual Workplace — Speaking the Same Language: How Translation and Transcription Work Inside NexGen Virtual Workplace](https://www.nexgenvirtualworkplace.net/blog/speaking-the-same-language-how-translation-and-transcription-work-inside-nexgen-virtual-workplace){rel=""nofollow""}, checked September 2026. InterMIND facts: [real-time translation docs](https://intermind.com/docs/translation), [transcription docs](https://intermind.com/docs/translation/transcription), [language breakdown](https://intermind.com/blog/how-many-languages-do-you-support), [own-voice translation](https://intermind.com/blog/own-voice-translation), [live benchmark](https://intermind.com/benchmark).* # Voice notes in a team channel: how it works, and what Copilot, Slack and Teams do with a recorded message - **The transcript is the message.** Record into any channel and the note arrives as text, up to ten minutes, with the recording behind a play button. - **What the incumbents document.** Copilot's Record lands in your own chat; Slack transcribes on request; Teams states captions for video clips, not audio; none mentions the reader's language. - **InterMIND keeps the whole channel in each member's language,** voice notes included, next to Copilot, Slack and Teams rather than instead of them. On every plan; you pay only for active members. Some things are faster to say than to type. A thought right after a call, a decision taken in a hallway, a status for the team while you walk to the car. Every major work tool now lets you record that moment: Microsoft added **Record** to the Copilot mobile app, Slack has **audio clips**, Teams has **video and audio clips** in chat. What they do with the recording afterwards is where they differ — and that is the part that decides whether a voice note becomes something the team can act on, or a file someone has to listen to. InterMIND ships voice notes as a channel feature: you record into the channel, and the note arrives as **a text message — the automatic transcript — with the recording behind a play button**. Members read it in their own language, like every other message in the channel. This post is the full mechanics, the limits, and a side-by-side with the three incumbents built only on what their public documentation states. ## How it works ### 1. Record In the web app and in the InterMIND mobile apps, the composer of every channel and chat shows a **microphone** button in place of **send** while the message field is empty. Tap it, allow the microphone the first time, and speak. While you record, the button is **send** and the field stays open — anything typed meanwhile goes out with the note, the note first and the text after it. There is no separate stop step: **send** ends the take and ships it, the way audio clips work in Slack and Teams. A note can run up to **ten minutes**; at the limit the recording stops on its own and waits for the next **send**. ### 2. The transcript is the message The note lands in the channel as a message that says **Transcribing…** for a few seconds, then becomes the text of what you said — an ordinary chat message with a **play** button on it. Everything a message can do, the note can do: search finds it, it can be quoted, forwarded and copied. Nothing is switched on per note and nobody presses "generate": recording is the whole gesture. ### 3. Everyone reads it in their own language Because the transcript is a chat message, it is translated the way every message in the channel is: each member reads it in their own language, and **Show original** in the message menu shows it as it was spoken. A teammate who reads Spanish reads the note in Spanish; the audio is there for anyone who wants the tone of voice. Voice notes work in any channel, including the channel you keep for yourself — a quick way to dictate a thought and have it come back as text. ### Where the audio goes Speech recognition for voice notes runs on Azure AI Speech in Sweden Central (EU) — the speech service of the default AI gateway, the same gateway that writes InterMIND's meeting summaries; organizations on Vertex AI or Amazon Bedrock get the recording without a transcript for now. The audio is sent once, at upload. The audio file is stored with the channel's other files and is deleted when the message is deleted. The transcript lives in the channel's database like any message, readable only by the channel's members. Every hop of the data path is listed on the [trust page](https://intermind.com/trust). Voice notes are included on **every plan**, and the setup reference is in the [docs](https://intermind.com/docs/chat/voice-notes). ## What the incumbents do with a recording Three of the spaces a team already lives in have a recording button. The rows below are documented facts from each vendor's own help pages, checked September 2026; where a page does not state something, the cell says so. | | InterMIND voice note | Microsoft Copilot — Record | Slack — audio clip | Microsoft Teams — audio clip | | ------------------------- | -------------------------------------------- | ----------------------------------------- | ------------------------------------------- | ------------------------------------------------------------------- | | Where the recording lands | in the channel, for every member | in your own Copilot chat, on mobile | in a conversation | in a one-on-one, group chat or channel | | Maximum length | 10 minutes | 120 minutes per recording | 5 minutes | 1 minute | | Transcript | automatic | automatic | on request — "Generate transcript" per clip | video clips get auto-generated captions; not stated for audio clips | | Summary | none — the transcript is the message | AI-generated summary in Copilot Chat | not stated | not stated | | Readers' language | the transcript in each member's own language | not stated | not stated | not stated | | Requires | any InterMIND plan | a Microsoft 365 Copilot license | any Slack plan | not stated | | Where the audio is kept | with the channel's files | a Copilot-managed folder in your OneDrive | not stated | not stated | Two things stand out from the documentation alone. First, the recordings that come with a transcript and a summary — Copilot's Record — are personal: the audio goes to your OneDrive and the summary to your own Copilot chat, and sharing it with the team is a second step. The recordings that land in a shared conversation — Slack and Teams clips — are shorter and, for audio, come with a transcript on request or not at all. Second, none of the three help pages states anything about the reader's language: a transcript, where it exists, is in the language it was spoken in. InterMIND's voice note sits in the shared place from the start: the channel gets the audio and the transcript as a message, and each member reads that message in their own language. That is the whole difference, and it follows from what the product is — a space where the entire history is readable by everyone in it, whatever they speak. ## What a voice note is good for - **After a customer call** — three sentences of what was agreed, recorded on the way back, and the channel has them as text before you sit down. - **A status for a team in several languages** — the manager speaks once; the German, Portuguese and Vietnamese members each read it in their language and the audio is one tap away. - **A decision that would take a paragraph to type** — say it, and it is in the channel as text, searchable and quotable. - **Notes to yourself** — the channel you keep for yourself turns dictation into text. ## FAQ **Can I send a voice note in Microsoft Teams?** Yes. Teams lets you record up to a minute of video or audio and send it to a one-on-one chat, a group chat or a channel; recipients listen in the conversation. The Teams help page describes auto-generated captions for video clips and does not state a transcript for audio clips (checked September 2026). **Does Slack transcribe voice messages?** Slack audio clips can be up to five minutes long and are available on all plans. A transcript is generated when a person selects "Generate transcript" on the clip; it is not automatic (checked September 2026). **What is Record in Microsoft Copilot?** Record is a feature of the Microsoft 365 Copilot mobile app (iPhone, iPad, Android) that captures an in-person conversation or a voice note to yourself, up to 120 minutes per recording. The audio is saved to a Copilot-managed folder in your OneDrive, and a transcript and an AI-generated summary are delivered in your Copilot chat. It requires a Microsoft 365 Copilot license (checked September 2026). **Can my teammates read a voice note in their own language?** In InterMIND, yes: the transcript is a chat message, so each member reads it in the language they read the channel in, and **Show original** shows it as spoken. The three incumbents' help pages do not state anything about the reader's language. **How long can an InterMIND voice note be?** Up to ten minutes. When the limit is reached the recording stops and sends on its own. Longer material belongs in a meeting, which gets a recap of its own. **Where is the audio stored, and who can hear it?** With the channel's other files, visible to the channel's members, and deleted together with the message. Speech recognition runs on Azure AI Speech in the EU, the speech service of the default AI gateway — we measured it against Google's and Amazon's speech services on the same voice notes in [Azure AI Speech vs Google Chirp 3 vs Amazon Transcribe](https://intermind.com/blog/speech-to-text-on-your-own-gateway); the data path hop by hop is on the [trust page](https://intermind.com/trust). **Do I need to press anything to get the transcript?** No. Sending the recording is the only action; the transcript replaces **Transcribing…** on the message a few moments later. ## Try it - **[How to share a file, photo or link into your team chat from any app](https://intermind.com/blog/how-to-share-a-file-into-your-team-chat-from-any-app)** — the share sheet on the phone, the Share menu on the Mac. - **[How to start a call from a team chat](https://intermind.com/blog/how-to-start-a-call-from-a-team-chat)** — one click, the chat stays with you, the recap comes back into the channel. - **[Open the live demo](https://intermind.com/demo)** — a channel in your language, no signup. - **[Read the voice-notes docs](https://intermind.com/docs/chat/voice-notes)** — the reference, limits included. - **[See the data path](https://intermind.com/trust)** — every hop, every vendor. *Sources: Microsoft Support — [Get started with Record in Microsoft Copilot](https://support.microsoft.com/en-us/microsoft-365-copilot/get-started-with-record){rel=""nofollow""} and [Record a video or audio clip in Microsoft Teams](https://support.microsoft.com/en-us/office/record-a-video-or-audio-clip-in-microsoft-teams-0c57dae5-2974-4214-9c46-7a2136386f1c){rel=""nofollow""}; Slack Help — [Record audio and video clips in Slack](https://slack.com/help/articles/4406235165587-Record-audio-and-video-clips-in-Slack){rel=""nofollow""}; Microsoft 365 roadmap — [Capture voice notes in the Microsoft 365 Copilot mobile app](https://www.microsoft.com/en-us/microsoft-365/roadmap?featureid=498640){rel=""nofollow""}, checked September 2026.* # What one InterMIND meeting is built from - **Our code or open source where meeting data lives.** Voice and chat run through our Mind API on OVH France; the client SDK is public, BSD 3-Clause. - **Said out loud: the plumbing is US SaaS.** Vercel, Fly.io, Stripe, Resend run in the EU; the AI gateway is the organization's choice, switchable off. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, files and the recap, on a stack you can audit. Guests join free by link, no account; you pay only for active members. Almost every product is built from the same default stack — the big proprietary SaaS defaults everyone reaches for. They're the frictionless path. At every layer where your meeting data actually lives, we took a different one: our own code, or open-source we could self-host. This is the companion to [*Where one InterMIND meeting actually runs*](https://intermind.com/blog/where-one-intermind-meeting-actually-runs), which mapped the *geography* — where each service executes and what data passes through it. This post answers what a security team asks next: *what is this thing built from — and can we read it, audit it, and replace it?* Not where it runs — what it's made of, layer by layer. --- ## The defaults, and what they cost Every product is a stack of choices. For most products, most of those choices are made by default: Google Analytics, Firebase, the Google Translate API, Auth0, React. They're the frictionless path, and for most teams that's a reasonable call. The trade-off is that each one puts a part of your stack behind a vendor you can't read, can't audit, and can't leave without a rewrite. We made a different choice at every layer where your meeting data actually lives: **our own code, or open-source software we could self-host.** Where a layer doesn't touch the content of your meeting, we stay pragmatic and say so. Here's the whole picture. --- ## The spine: the engine is our code, not a third party's Start with the layer that matters most, because most of your meeting flows through it. Real-time transport and voice/chat translation both run on **`mind-sdk` + the Mind API — our own engine, on OVH France.** The default way to build a translated meeting is to bolt a real-time SaaS (LiveKit) onto a translation API (DeepL, Google); we run neither in the live path. No third-party translation model is in the loop. (We do use DeepL — but only for documents dropped into chat, not the live voice/chat path; see the runtime map. We covered the pipeline mechanics in [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) Here's the part that isn't in the runtime map: the SDK your meeting runs on is **open source under the BSD 3-Clause license** — the `mind-sdk` client is public at [gitlab.com/mindlabs/api/sdk](https://gitlab.com/mindlabs/api/sdk){rel=""nofollow""}, copyright MindMeeting OÜ, our Estonian IP entity. It speaks to the Mind API at [api.mind.com](https://api.mind.com){rel=""nofollow""}, which we run ourselves on OVH France. This isn't a "look, but don't touch" source-available arrangement. BSD 3-Clause is a permissive, OSI-approved license. Your security team can clone the SDK, read exactly how your audio and text are captured, framed, and streamed, and audit that integration against your own requirements. The server-side engine it talks to is ours — not a third party's black box — and a fully self-hostable engine for a tenant who needs it is on our roadmap, not something we offer today. We'll update this post the moment it ships. --- ## Layer by layer: the default vs. what we run | Layer | The usual default | What we run | Why it matters to you | | --------------------------------------------------------------------------- | -------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | | **Real-time + translation engine** (voice + chat) | LiveKit + a translation API (DeepL / Google) | `mind-sdk` (BSD-3-Clause client) + our Mind API, OVH France | The heaviest data flow is our own engine, not a third-party model — and its client SDK is open and auditable | | **Frontend framework** | React (Meta) / Next.js | Vue + Nuxt | Community-governed OSS — no single corporation owns the framework your UI rides on | | **Product analytics** | Google Analytics | PostHog | Open-source, EU cloud, proxied first-party through our own domain — usage data doesn't flow into a third-party advertising platform | | **Fonts** | Google Fonts CDN | Self-hosted (`@nuxt/fonts`) | No third-party font callout from the page your users load — a recurring GDPR finding, avoided | | **Authentication** | Auth0 / Clerk / Firebase Auth | Self-run OIDC, federated to your Google / Microsoft | No auth middleman holds your sessions — you bring your own identity provider | | **Document translation** | Google Translate | DeepL (Cologne) | Specialized EU vendor, German processing | | **AI features** (recap, document summaries, writing assistant, Ask AI, Mia) | One vendor's model behind its own API | The AI gateway the organization selects — Azure OpenAI EU Data Zone (default), Vertex AI EU, Amazon Bedrock Frankfurt — or its own OpenAI-compatible endpoint | The model is yours to choose and to host; switching AI off is a setting | | **Content / docs** | Contentful / Sanity (headless CMS) | Nuxt Content (git-tracked markdown) | The words on our site live in our repo, not a vendor's database | | **Application database** | Firestore / DynamoDB (proprietary) | Postgres (on Neon) | Open standard — portable to any Postgres host, no proprietary query API to rewrite | | **Object storage** | Proprietary blob APIs | Tigris (S3-compatible) | Open protocol — recordings and exports are portable to any S3 store | | **CRM / sales** | Salesforce / HubSpot | Pipedrive (Estonian) | Customer and deal records sit in an EU-domiciled CRM, not a US sales platform | Two threads run through that table. **Open-source** where the tool processes your data — so it can be audited, and in principle self-hosted. **Open standards** (Postgres, the S3 API, OIDC) where we depend on infrastructure — so nothing is locked to one vendor's pricing or compliance posture. Postgres can move to any Postgres host; storage can move to any S3 store; auth federates to the identity provider you already run. The last row sits on a third axis: the CRM holding customer records is **EU-domiciled** (Pipedrive, Estonian) rather than a US sales platform — not open-source, but not under US jurisdiction either. A couple of these deserve a sentence more. PostHog is open-source and self-hostable; we run it on PostHog's EU cloud and proxy it first-party through our own origin, so the events aren't silently dropped by ad-blockers *and* don't transit a third-party analytics domain. Authentication never goes to a third-party auth SaaS that would sit between you and your sessions — we run the OIDC flow ourselves and federate to your existing Google or Microsoft identity. And the fonts on every page are served from our own domain; the only place Google Fonts appears in our codebase is an offline brand-asset script, never the app your users load. --- ## Where we're pragmatic — said out loud We don't pretend the whole stack is hand-rolled or non-US. It isn't, and a post that claimed otherwise would be contradicted by our own runtime map. The plumbing — hosting and SSR (**Vercel**), the meeting server's compute (**Fly.io**), payments (**Stripe**), transactional email (**Resend**) — runs on US-domiciled SaaS. Stripe and Resend handle billing and invites and never see meeting content. Vercel and Fly are rented compute: our own code runs on them, and the meeting server on Fly does handle the live session and the transcript our digest reads — but that's our code on their machines, not a vendor product ingesting your meeting. All of it executes in the EU at runtime (the subject of [the runtime map](https://intermind.com/blog/where-one-intermind-meeting-actually-runs)). That's a deliberate, bounded trade-off: own and open-source the data plane; use the best available SaaS for the control plane. Naming it is the point — "sovereignty" means little if the exceptions aren't on the table next to the wins. --- ## The AI steps, and the plan that shipped The language-model steps — the **AI digest** (topics, decisions, action items), **document summaries**, the **AI note-editor**'s generative actions, **Ask AI** and **Mia** — run on the AI gateway your organization selects: **Azure OpenAI in the EU Data Zone** by default, **Vertex AI** on the EU multi-region endpoint or **Amazon Bedrock** in Frankfurt by choice, each in our own tenant with zero data retention and no training on customer content — or **your own OpenAI-compatible endpoint**, which keeps the model on infrastructure you control. The post-meeting summary and the editor's *translate* action go through the translation tract, not the language model. Real-time voice, chat, notes, and documents never went near a general-purpose LLM in the first place. That is the honest shape of this layer: the models are proprietary, and their vendors are US companies operating EU regions — the same trade-off as the plumbing above, stated next to it rather than hidden. What shipped instead of a self-hosted model of our own is the choice: **an organization can turn AI off entirely** (transcription and translation keep working), and it can point every AI feature at its own endpoint — vLLM in its own data centre, a deployment in its own tenant — which puts this layer on the same open-and-self-hostable axis as the rest of the data plane. Our public [translation benchmark](https://intermind.com/benchmark) is scored by an LLM judge (Gemini, with Claude as fallback) on fixed [FLORES-200](https://github.com/facebookresearch/flores){rel=""nofollow""} reference sentences — never anyone's meeting. --- ## Why this matters beyond us This isn't engineering for its own sake. The reason to build a stack this way shows up on your side of the contract: 1. **Auditable.** The SDK your meeting runs on is open-source code your security team can read, and the engine behind it is our own — not a third party's black box. 2. **Portable.** Open standards at every data layer — Postgres, S3, OIDC — mean no proprietary lock-in. What can be moved isn't tied to a single vendor. 3. **Self-hostable.** The open-standard data layers — Postgres, S3, OIDC — already run on infrastructure you control; a fully self-hosted translation engine is on the roadmap for the tenant who needs it. This is the picture on 2026-06-07. We'll update it when the stack changes — a vendor swap, a layer rebuilt, the digest model replaced. The current configuration is verifiable in our open `vercel.json`, our `nuxt.config.ts`, and the BSD-3-Clause `mind-sdk` repository linked above. If a layer here looks wrong, or your security review needs an answer this map doesn't give, write us. We'd rather correct a missing detail than have you find it in a code audit. --- *Sources: the [mind-sdk repository](https://gitlab.com/mindlabs/api/sdk){rel=""nofollow""} (BSD-3-Clause), [FLORES-200](https://github.com/facebookresearch/flores){rel=""nofollow""}; stack facts verified against the deployed configuration (`vercel.json`, `nuxt.config.ts`) and the shipped code, checked August 2026.* # How to translate WhatsApp messages (2026): the built-in feature, what it covers, and where it stops - **Yes, long-press and tap Translate.** Built in since September 2025, on the phone, in chats, groups and Channels; Android translates a whole chat automatically. - **It stops at reading.** Calls are not covered, a multilingual group stays a mix of originals, and the history keeps each message in the language it was written. - **InterMIND keeps the whole space in each member's language,** chat, calls and the history, when the conversation is the work. Guests join free by link, no account; you pay only for active members. The message arrives in a language you don't read — a supplier, a customer, the group your cousin added you to. For most of WhatsApp's history the answer was copy, switch apps, paste, switch back. Since September 2025 it isn't: WhatsApp translates messages itself, on the device, without the text leaving the chat. This is the whole feature as WhatsApp documents it — where it lives, what it ships with, and the cases it doesn't cover — with the vendor's own words, checked August 2026. ## 1. The built-in path: long-press → Translate WhatsApp's announcement puts it in one sentence: "If you see a message in a different language, you can now simply long-press and tap 'Translate'." Then "choose the language you want the message to be translated from or to, and download it to be saved for future translations" — the language pack is fetched once and reused. Three things about how it works: - **It runs on the phone.** "Translations occur on your device where WhatsApp cannot see them." The text isn't sent to a translation server, and the chat's end-to-end encryption stays intact — the reason to prefer this over any third-party "WhatsApp translator" app, which needs the text taken out of the encrypted chat. - **It works everywhere in the app.** "This works for 1:1 chats, groups, and Channel updates too." - **You can see the original again.** Long-press the translated message and tap *View translation* to switch views or change the target language. The rollout started "gradually from today" on September 23, 2025, "in a few select languages to start with more to follow" — so a phone that doesn't show *Translate* yet may simply not have received it; section 3 covers what to do in the meantime. ## 2. Translate a whole chat automatically (Android) On Android the per-message step can be skipped: "Android users will also be able to choose to turn on automatic translation for an entire chat thread, so that all future incoming messages in that conversation are translated as well." In practice: translate one message, and toggle *Translate all new messages in this chat* when the language picker appears. Every incoming message in that conversation is then shown translated. The announcement lists the launch languages per platform: - **Android:** six at launch — "English, Spanish, Hindi, Portuguese, Russian, and Arabic". - **iPhone:** "19+ languages", using Apple's on-device translation. So an Android user reading a German or Japanese message at launch is outside the six; an iPhone user usually isn't. WhatsApp says more languages follow; the app's language picker is the current list. ## 3. Phones without the feature yet: Google's Tap to Translate If *Translate* isn't in the long-press menu, Android has a documented fallback that predates WhatsApp's own feature. Google Translate's **Tap to Translate** lets you "translate text from apps and you don't need to open the Google Translate app": switch it on in the Translate app (*Settings → Tap to Translate → Enable*), then in WhatsApp copy the message and tap the Google Translate icon that appears. Two documented limits: it "works with text, not with images", and the first time it asks to "Display over other apps". The difference from WhatsApp's own feature is where the text goes: Google's translation is Google's service, not on-device processing inside the encrypted chat. For a menu or a delivery note that's fine; for a contract clause, it's a different privacy question. ## 4. Voice notes: transcribe first, then translate WhatsApp's translation is for text. A voice note in another language takes two steps, both built in: 1. **Transcribe it on the device.** *Settings → Chats → Voice message transcripts* — switch on, pick a language (a small pack downloads once); then long-press the voice note → *Transcribe*. As of August 2026 the transcript languages are English, Portuguese, Spanish and Russian, and the audio never leaves the phone. Full walkthrough and the predictable failure modes (noise, mixed languages, Web/Desktop): [how to transcribe WhatsApp voice messages](https://intermind.com/blog/transcrever-audio-whatsapp). 2. **Translate the transcript** — long-press the transcribed text if your phone has the feature, or Tap to Translate. Neither the translation announcement nor the transcript feature covers **calls**: a WhatsApp voice or video call happens in the language it's spoken in. ## 5. Where the built-in feature stops Everything above is about *reading*. Three cases the documentation doesn't cover — not because WhatsApp is bad at them, but because they're a different problem: - **A group where everyone writes in a different language.** Each reader translates their own view; the group itself stays a mix of originals. Nobody sees the conversation in one language except on their own screen, and the sender never knows what the recipient read. - **A record you can reread in your own language.** WhatsApp's privacy policy: "we do not retain your messages in the ordinary course of providing our Services to you. Once your messages are delivered, they are deleted from our servers." The history is on each member's phone and backup, in the original languages; the translated view is not a second copy of the chat. - **The call itself.** No translation for voice or video calls is documented. For a message from a supplier, none of this matters — long-press, done. It starts to matter when the conversation *is* the work: a team, a customer relationship, a project where three languages meet every day and the decision made on Tuesday has to be findable — and readable — next month. ## 6. When the conversation is work That case is what we build [InterMIND](https://intermind.com/chats) for, and it's a different shape than a translate button: - **The space is translated for every member as its default.** Chat and shared notes in 23 languages, documents in 30 — a member who reads Polish reads the channel in Polish, with no per-message step and no add-on. ([Why the language counts differ per pipeline.](https://intermind.com/blog/how-many-languages-do-you-support)) - **Calls are translated too, live, per listener.** Every participant hears every speaker in the language they chose, in the speaker's own voice. **Participants pay nothing and need no account** — a link is enough. ([Why participation is free.](https://intermind.com/blog/free-for-participants)) - **The history persists, in each member's language.** A meeting becomes a channel; chat, recap (for signed-in members) and documents stay readable in everyone's own language. ([What still exists a week later.](https://intermind.com/blog/the-meeting-a-week-later)) - **It runs in the EU at every hop**, on our own translation engine — not a consumer translation service. ([Where one InterMIND meeting actually runs.](https://intermind.com/blog/where-one-intermind-meeting-actually-runs)) If your Telegram groups are where the work happens, they can be mirrored into the same channels — [how the Telegram bot works](https://intermind.com/blog/telegram-ingest-how-it-works). For WhatsApp, the built-in translation is the tool; the sections above are the whole of it. ## Which tool for which message | Situation | What to use | | ----------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------- | | One message in another language | Long-press → **Translate** (on device, 1:1, groups, Channels) | | A whole chat that arrives in another language | Android: **Translate all new messages in this chat**; iPhone: per message, 19+ languages | | The feature isn't on your phone yet | Google Translate **Tap to Translate** (copy → tap; text only; Google's service, not on-device) | | A voice note in another language | *Voice message transcripts* on device (EN/PT/ES/RU) → translate the text | | A call in another language | Not covered by WhatsApp's documentation | | A team or customer relationship running in several languages, with a history you need to reread | A space translated for every member — [InterMIND](https://intermind.com/chats), free for participants | ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener in any of 23 languages. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, monthly translation quality on real traffic, with the methodology public. --- ## FAQ **Does WhatsApp translate messages?** Yes, since September 2025: long-press a message and tap *Translate*, pick the language pair, and the translation is shown in place — on the device, "where WhatsApp cannot see them". It works in 1:1 chats, groups and Channels. The rollout is gradual and by language, so not every phone shows it yet. **How do I turn on auto-translate in WhatsApp?** On Android: translate a message once and switch on *Translate all new messages in this chat* — every incoming message in that conversation is then shown translated. The announcement describes automatic translation for whole chat threads on Android only; on iPhone, translation is per message. **Which languages does WhatsApp translate?** At launch, six on Android — English, Spanish, Hindi, Portuguese, Russian, Arabic — and "19+ languages" on iPhone via Apple's translation, "with more to follow". The current list is the language picker in the app. **Can WhatsApp translate voice messages?** Not directly. Voice notes are transcribed on the device (English, Portuguese, Spanish, Russian as of August 2026); the transcript can then be translated like any text. Calls are not covered by either feature. **Is WhatsApp's translation private?** WhatsApp states that "translations occur on your device where WhatsApp cannot see them", so the text stays inside the end-to-end-encrypted chat. Google's Tap to Translate, the fallback for phones without the feature, sends the copied text to Google's service. **Does WhatsApp translation work on WhatsApp Web or Desktop?** The announcement names Android and iPhone; it doesn't mention Web or Desktop (checked August 2026). Translate on the phone. **Does the translated message get saved?** The translated view is per reader; the chat keeps each message in the language it was written in, on each member's phone and backup — WhatsApp's servers delete messages once delivered. If the record itself has to be readable in each member's language, that's a space built for it rather than a messenger with a translate button. **How do I get the chat itself out of WhatsApp?** Export chat sends a copy to another app, with limits worth knowing before you rely on it — what it includes, what it drops, and what to do when the option isn't in the menu: [how to export a WhatsApp chat](https://intermind.com/blog/export-whatsapp-chat). --- *Sources: [WhatsApp blog — Introducing message translations](https://blog.whatsapp.com/introducing-message-translations){rel=""nofollow""}, [Meta Newsroom — Introducing Message Translations on WhatsApp](https://about.fb.com/news/2025/09/introducing-message-translations-whatsapp/){rel=""nofollow""}, [WhatsApp — How to turn voice message transcripts on or off](https://faq.whatsapp.com/241617298315321){rel=""nofollow""}, [WhatsApp — Privacy policy](https://www.whatsapp.com/legal/privacy-policy){rel=""nofollow""}, [Google Translate Help — Translate text in other apps (Android)](https://support.google.com/translate/answer/6350658?hl=en&co=GENIE.Platform%3DAndroid){rel=""nofollow""}. WhatsApp and Google change features and language lists over time; check their pages for the current state. All facts checked August 2026.* # Where one InterMIND meeting actually runs - **Every hop touching meeting content is EU at runtime.** Our own engine on OVH France, the meeting server in Paris, DeepL in Cologne, the AI gateway in an EU region. - **Domicile is the other question.** Microsoft, Google and Amazon behind the AI gateway are US companies operating EU regions; the engine most data flows through is our own. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, files and the recap. Guests join free by link, no account; you pay only for active members. Sooner or later someone on the host's side — a client's IT, a DPO, a cautious partner — asks the same question: *"Where does this data go?"* They want a sub-processor list, the vendors' domiciles and a diagram with arrows. We'd rather you have the full picture than ship it piece by piece over email. So here is the data path of one meeting — every external service it touches, where each one executes, and what data flows through it. Verified against the actual deployment configuration on 2026-05-28. Every path that touches meeting content is EU at runtime — including the AI steps, which run on the AI gateway your organization selects, in an EU region of our own tenant. The vendors behind that gateway are US companies operating EU regions; we say so plainly below, and we say which model sits outside the meeting entirely. *This post maps **where** your meeting runs. Its companion, [What one InterMIND meeting is built from](https://intermind.com/blog/what-one-intermind-meeting-is-built-from), maps **what it's built from** — which layers are our own code, which are open-source, and where we're pragmatic about proprietary SaaS.* --- ## What "where it runs" actually means Two things get conflated in sovereignty conversations and they are not the same thing: 1. **Runtime / data path.** Where the bytes of your meeting are physically processed during the request. This is what data-residency regulations and most DPAs are actually about. 2. **Vendor corporate domicile.** Where the SaaS vendor is legally incorporated. This is what CLOUD-Act discussions are about — the theoretical reach of a US compulsion against the vendor's parent entity, regardless of where the workload runs. Almost every "is this EU?" question is really one of these two, asked imprecisely. We answer them separately for every vendor below. --- ## The data path of one meeting Trace one call from join to follow-up email: 1. **Browser opens the meeting page.** SSR runs on Vercel, pinned to `fra1` (Frankfurt). All request/response data — session cookies, API payloads, server-rendered HTML — is processed in EU at runtime. 2. **WebSocket connects to our meeting server** in Paris (`cdg`). Meeting orchestration, presence, signalling — all EU. 3. **Speech recognition runs on our media server.** The audio arrives over WebRTC at our own engine — the Mind API on OVH, France — and is recognized there, word by word, on the same server that carries the call; no third-party speech service is in the loop. Voice notes in chat are the one exception: their speech-to-text runs on Azure AI Speech, the speech service of the default AI gateway (vendor table below). The pipeline itself is in [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines). 4. **Voice and chat translation hit our own engine on OVH France.** This is **`mind-sdk` + the Mind API** — our code, our hosts, in France. No third-party model is in the loop. One translation per target language present in the room, EU-resident at every hop. 5. **A document dropped into chat** (PDF, DOCX, DOC, PPTX, XLSX) goes server-side from the Paris ws-server to **DeepL** in Cologne. German company, German processing. Voice and chat do not touch DeepL. 6. **Application data** — users, teams, messages, meeting metadata — lives in **Neon Postgres on AWS Frankfurt** (`eu-central-1`). Snapshots in the same region. 7. **Recordings, attachments, exports** are stored on **Tigris**, S3-compatible storage on Fly. Edge-replicated; the bucket is configurable to multi-region EU for tenants who need it pinned tighter. 8. **Errors and performance traces** go to **Sentry's EU instance** (`de.sentry.io`). The US org was retired in May. 9. **Product analytics** go to **PostHog EU** (`eu.i.posthog.com`). 10. **Transactional email** (magic links, invites, receipts) goes via **Resend** out of `eu-west-1` (Ireland). Everything above is EU at runtime. The translation engine — the part most of your data actually flows through — is also our own code, not a third party's. The client SDK it runs on is open-source (BSD-3-Clause) and auditable today; self-hosting the engine itself is on the roadmap for a customer who needs it. --- ## The vendor map | Vendor | What it does | Runtime location | | -------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- | | **OVH** (`mind-sdk` + Mind API) | Voice + chat translation engine | France | | **Fly.io** | Meeting WebSocket orchestration | Paris (`cdg`) | | **Vercel** (Nuxt + Nitro APIs) | App shell, server APIs, SSR | Frankfurt (`fra1`) | | **Neon** | Application Postgres | AWS Frankfurt (`eu-central-1`) | | **Tigris** | Object storage (recordings, attachments) | Edge-replicated; EU-pinnable | | **DeepL** | Document translation (PDF/DOCX/PPTX/XLSX) | Cologne | | **Microsoft / Google / AWS** (the AI gateway your organization selects) | Recaps, document summaries, writing assistant, Ask AI, Mia | Azure OpenAI EU Data Zone (default) · Vertex AI EU multi-region endpoint · Amazon Bedrock Frankfurt — our own tenant in each | | **Microsoft** (Azure AI Speech, the speech service of the default gateway) | Voice-note speech-to-text — on the default gateway; Vertex AI and Bedrock organizations get the recording without a transcript for now | Sweden Central (EU), our own tenant | | **Sentry** | Error tracking | `de.sentry.io` (EU) | | **PostHog** | Product analytics | `eu.i.posthog.com` | | **Resend** | Transactional email | Ireland (`eu-west-1`) | | **Stripe** | Payments | Ireland (Stripe Payments Europe Ltd.) for EU customers | The two heaviest data flows by volume — voice/chat translation through our own engine on OVH and document translation through DeepL — also happen to be the two vendors whose parent entity is in the EU. That covers the bulk of meeting content. The full sub-processor list with corporate-domicile detail goes into the DPA as standard practice; the table above is the runtime view, which is what most data-residency clauses are about. --- ## The AI steps, named plainly After the call ends we run a few language-model steps on what was said: the **AI digest** (topics, decisions, action items, open questions), the **post-meeting summary**, and the **AI note-editor** (translate a note, or fix / extend / simplify it). During the call the same kind of step writes a **summary of every document dropped into chat** and answers **Ask AI** and **Mia**. These are the only places a general-purpose model touches meeting-derived content, and all of them go to one place: - **The AI gateway your organization selects.** One resolver in the code picks it for every call site; there is no second path. The default is **Azure OpenAI in the EU Data Zone**; from its settings an organization switches to **Vertex AI on the EU multi-region endpoint** or **Amazon Bedrock in Frankfurt**, or points every AI feature at **its own OpenAI-compatible endpoint** — vLLM in its own data centre, a deployment in its own tenant. Each hosted gateway runs in our own tenant, configured for zero data retention and no training on customer content; the fallback stays on the same gateway — a second EU region, or a second model of the same vendor — never another vendor. The [AI features docs](https://intermind.com/docs/settings/ai-features) list the gateways and regions. - The **summary** and the editor's **translate** action go through the translation tract, not the language model — the same path that translates live chat. - **AI can be switched off for the whole organization**: transcription and translation keep working; the digest, document summaries, the writing assistant and Ask AI stop. Real-time voice, real-time chat, notes, and document translation never go through any of these — they were EU-resident from the start. Where the vendors sit: Microsoft, Google and Amazon are US companies operating EU regions. That is stated plainly on the [trust page](https://intermind.com/trust), not hidden — it is the corporate-domicile question from the top of this post, answered for this hop the same way as for the plumbing. One model sits outside the meeting entirely: our public [translation-quality benchmark](https://intermind.com/benchmark) uses an LLM judge (Gemini, with Claude as fallback, via Vercel's AI Gateway) to score machine translations of [FLORES-200](https://github.com/facebookresearch/flores){rel=""nofollow""} reference sentences. That's a fixed, public dataset — not anyone's meeting. --- ## What this means for your DPA For most EU buyers — German Mittelstand, regulated industries running standard GDPR DPAs — the picture above answers the data-residency question directly: every runtime hop your meeting takes is in the EU. Vendor-domicile gets disclosed in the sub-processor list per normal practice; nothing surprising there. The residency map is one piece; for the rest of the data-protection obligations — erasure, retention, portability, consent — we ran the codebase through a full audit and [closed each item against the code](https://intermind.com/blog/gdpr-audit-what-we-closed). For French *souveraineté numérique* and SecNumCloud-grade procurement, vendor corporate domicile is itself part of the criterion, not just runtime location. That's a different conversation — an alternative deployment topology that keeps every component under European-jurisdiction vendors. We don't run that by default; we'll spin it up for a tenant that needs it and where the contract justifies the build. For US-domestic and most APAC buyers, the inverse is usually true — they want low latency from their region, which is a different problem. Today we run single-region in `fra1`. If your traffic justifies a US edge, we'll plan that with you. --- ## What this post commits us to This is the picture on 2026-05-28. We'll update it when the stack changes — vendor swap, region migration, a new external service. The current configuration is verifiable in our open `vercel.json`, the `mind-sdk` + Mind API engine running at OVH France, and every vendor's own dashboard. If something here looks wrong, or your DPO needs an answer this map doesn't give, write us. We'd rather correct a missing detail than have you discover it in a contract review. --- *Sources: runtime regions and model routing verified against the deployed configuration (`vercel.json`, `fly.toml`) and the shipped code; [Vercel AI Gateway](https://vercel.com/docs/ai-gateway){rel=""nofollow""} (the digest's provider-pinning path), [FLORES-200](https://github.com/facebookresearch/flores){rel=""nofollow""}; checked August 2026.* # Why translation-quality marketing is broken — and what we publish instead - **Language counts say nothing about your meeting.** Per-pair quality, sample size, judge and distribution over time are what buyers need; no marketing page shows them. - **Ask three things of any vendor.** Per-pair, per-month quality on real traffic; the judge and what it does not measure; what happens when a score drops. - **InterMIND keeps the whole meeting in each member's language and publishes the quality,** every pair, every month, on real traffic, judge named. Guests join free by link, no account; you pay only for active members. Open any live-translation vendor's site. You will see the same kinds of numbers: - "200+ languages" - "6,000+ language pairs" - "World's first" / "Highest accuracy" - "99% accurate" Now try to find — on any of those vendor pages — what those numbers mean for a meeting you are about to run. Per-language quality. Reproducible methodology. Sample size. Score over time. Honest disclosure of where the model is weak. You will not find it. Not in the marketing copy, and rarely in the docs. This is the equilibrium of the category. It exists because of three things: 1. **Most vendors do not own their translation engine.** They route through OpenAI, Google, DeepL, Microsoft, or some combination. Publishing per-pair quality data would be benchmarking someone else's model — there is no marketing value in that. 2. **Honest quality data is hard to put on a billboard.** A single score is noisy. A distribution is more useful but harder to compress. A `last-six-months trend` is more useful still, and even harder. 3. **Procurement has not pushed back yet.** Buyers accept the marketing numbers at face value, and so the equilibrium holds. The equilibrium will not hold. The next class of buyer — pharma, legal, financial, audit, public sector — is going to ask harder questions than "how many languages." We built [`/benchmark`](https://intermind.com/benchmark) because we think they should not have to take a vendor's word for it. --- ## What the marketing numbers don't tell you **"200+ languages"** means a vendor has a model that emits text in 200 languages. Quality across those languages ranges from production-grade for major pairs (EN↔DE, EN↔ES, EN↔FR) to barely usable for low-resource pairs. Without a per-pair breakdown, you cannot tell which side of that line your meeting will land on. **"6,000+ language pairs"** is `N × N` combinatorics on 80 source languages. Saying you support 6,000 pairs is the easy part. Saying any specific pair is good enough for a CAPA review, a contract negotiation, or an earnings call — that is the part not in the brochure. **"99% accurate"**, without specifying what was measured, against what reference, on what sample, by what judge — is content-free. Translation quality has no universal scalar. It has a distribution that depends on language pair, content domain, audio quality (for voice), latency budget, and what "good enough" means for the specific use case. --- ## What a buyer actually needs to know The questions a host should ask before trusting a pair with a client call: 1. **Per-pair quality** — how does this perform on DE↔EN, EN↔AR, JA↔KO, specifically? 2. **Sample size** — how many runs is your reported number based on? Ten? Ten thousand? 3. **Methodology** — who is judging the translations, against what reference, with what rubric? 4. **Distribution, not average** — what does the worst-case 10% look like? The best 10%? The median? 5. **Drift over time** — has a given pair gotten better or worse since you last published a number? 6. **What you don't measure** — what does your benchmark explicitly not capture? None of these are unanswerable. They are just not on anyone's marketing page. --- ## What we publish [`/benchmark`](https://intermind.com/benchmark) is our answer. The methodology is at [`/benchmark/methodology`](https://intermind.com/benchmark/methodology) — written before we knew you'd be reading this. Three things separate it from category norms. ### 1. Real traffic, not a curated suite Every score in the public benchmark comes from a real [`/demo`](https://intermind.com/demo) test run. We do not pre-select pairs that perform well. The same pipeline that serves a buyer's demo is the one being measured. ### 2. The judge is named Primary: `google/gemini-3.5-flash`. Fallback: `anthropic/claude-sonnet-5`. Both via Vercel AI Gateway. The judge is part of the methodology — disclosed by name. When we change the judge (we have, as models retire), historical rows carry the judge that actually scored them; old scores never get silently re-scored. ### 3. The distribution is the data, not the average Every published row shows median, p10, p90, min, max, and sample size — not a single number. A single number for a translation pair is noise. The shape of the distribution is the signal. --- ## Practices the category hasn't adopted - **Low-score pairs are not hidden.** The public index is gated on `≥ 10 distinct IPs, ≥ 10 runs, median ≥ 60` — but anyone can deep-link to any pair directly and see the real numbers, including the pairs that are doing badly this month. - **Known issues are documented.** When the chat-test harness was broken for a few weeks earlier in 2026, that period is suppressed from the index and noted in writing on the methodology page. History does not get silently rewritten. - **What we deliberately do NOT claim** is a full section on the methodology page. We say where the LLM judge itself is imperfect. We say what we do not measure (latency, cost, user satisfaction, ASR-side errors before translation even runs). We disclose that our own automated smoke tests are part of the traffic. --- ## A filter for the next vendor evaluation If you are evaluating any multilingual meeting platform — ours or another — the methodology is the page worth reading. The numbers themselves are the easy part. A practical filter for any vendor in this category: - **Ask for per-language-pair, per-month quality data on real traffic.** Not a curated benchmark. Not an aggregate. - **Ask what their judge is, what they explicitly do not measure, and what has changed in the last six months.** - **Ask what happens when a pair's score drops** — do they tell anyone, or do they fix it silently? If the vendor has all three answers in writing, evaluate them seriously. If they don't, you are buying marketing — not translation quality. --- ## Try it yourself - **[Try the live demo](https://intermind.com/demo)** — runs the production translation pipeline on your audio, scores it against the same judge that scores the public benchmark, and shows you the output. - **[See the benchmark](https://intermind.com/benchmark)** — every published language pair, every month, with the full distribution. - **[Read the methodology](https://intermind.com/benchmark/methodology)** — how the numbers are computed, what they include, what they do not. You will not need to take our word for any of it. That is the point. --- *Sources: the judge identifiers, gating thresholds and suppression rules above are verified against the shipped code and published at [/benchmark/methodology](https://intermind.com/benchmark/methodology); the judges are served via [Vercel AI Gateway](https://vercel.com/docs/ai-gateway){rel=""nofollow""}; the marketing claims quoted at the top are category-typical phrasings, not quotes of a named vendor; checked August 2026.* # Zoom alternatives for multilingual meetings (2026) - **Three axes, not video quality.** Who hears the meeting in their own language, who holds the license, what survives the call translated. - **Each incumbent fences an axis.** Zoom voices five languages behind an add-on, Teams meters its Interpreter per Copilot listener, Meet runs one English-anchored pair, Webex routes interpreters you staff. - **InterMIND keeps the whole meeting in each member's language,** voice, chat and the recap, next to Zoom rather than instead of it. Guests join free by link, no account; you pay only for active members. Search "Zoom alternatives" and you get the same comparison twenty times: gallery view sizes, meeting length caps on the free tier, whiteboards, breakout rooms. Useful if Zoom's video features are your problem. Useless if your actual problem is that **your meetings happen in more than one language** — because on those lists, every alternative is the same product: a room that assumes everyone shares a language. This is the other comparison. If you're leaving Zoom (or deciding not to) because of how it handles a Spanish-speaking customer, a German counsel, or a team spread across São Paulo, Warsaw and Jakarta, three axes decide the purchase — and none of them is video quality: 1. **Live: does every participant get the meeting in their own language — voice, not just captions — and simultaneously?** 2. **Economics: who has to hold a license or add-on for that to happen?** 3. **Afterwards: what still exists in each participant's language once the call ends?** Here's Zoom's own baseline on those axes, then the alternatives people actually evaluate — Microsoft Teams, Google Meet, Cisco Webex — then us, with a table to compare all five. Every competitor fact below comes from the vendor's public documentation, checked August 2026, linked in the footer. --- ## The baseline: what you'd be leaving Zoom's translation stack in 2026 is three separate features: - **Translated captions** — text, rendered per participant, in 36 languages. Included on Business Plus and Enterprise-tier Workplace plans; other paid plans need the Translated Captions add-on. - **Voice translator** — synthetic translated audio in five languages (English, Chinese, French, Japanese, Spanish), via the Live Translation add-on or ZoomMate, desktop app only, meetings only — no webinars. - **Language Interpretation** — audio channels for human interpreters you hire, brief and pay yourself. On persistence: Zoom's documentation for translated captions and the Voice translator describes live views and does not state that translated output is saved after the meeting (checked August 2026). The recording keeps the meeting as spoken. The full walkthrough is in [Zoom live translation](https://intermind.com/blog/zoom-live-translation). If that stack fits your meetings, staying is a defensible choice. The question is what the alternatives change. ## Microsoft Teams Teams ships the most machinery of the big three: translated captions in 31 languages, plus the AI **Interpreter agent** — synthetic translated speech in 10 languages. The documented fences: - Translated captions require the **organizer to hold a Teams Premium or Microsoft 365 Copilot license**. - The Interpreter agent is **licensed per listener** (Microsoft 365 Copilot) and **metered — 20 hours per user per month**, in scheduled meetings only: no instant meetings, no webinars, no town halls. - Nothing translated survives: captions aren't saved, translated transcripts exist only live, recordings keep **original audio only**. So as a Zoom alternative for multilingual work, Teams changes the language list and the licensing model — from Zoom's add-ons to per-seat Copilot licenses with a monthly meter. Details: [Teams live translation](https://intermind.com/blog/teams-live-translation). ## Google Meet Meet's Gemini-powered **speech translation** translates spoken audio in near real time, in a voice resembling the speaker's. The documented fences: - It runs **between English and five languages** (French, German, Italian, Portuguese, Spanish) — every pair includes English. - **One language pair per meeting.** A room with English, Spanish and German speakers picks one pair; that's the meeting. - It's a **beta capped at 90 minutes**, unavailable in recordings and live streams — and no audio is saved. - Translated captions (text) cover more languages on Business Standard+ Workspace editions. As a Zoom alternative, Meet trades Zoom's five-language add-on for a five-language English-anchored pair — a different shape of the same ceiling. Details: [Google Meet live translation](https://intermind.com/blog/google-meet-live-translation). ## Cisco Webex Webex is the enterprise-hardware answer on most alternative lists. On the language axes, its documentation describes: - **Translated captions as a paid add-on** — 16 spoken languages transcribed, translated into 120+ caption languages. Text, not voice. - **Human-interpreter audio channels** for meetings and webinars — you bring the interpreters. - **Message translation** in Webex spaces, and AI Assistant meeting summaries. Voice translation by machine isn't part of the documented stack — spoken translation means interpreter channels you staff. As a Zoom alternative it's a captions-plus-interpreters model at enterprise scale (up to 1,000 attendees documented). Feature-by-feature: [InterMIND vs Webex](https://intermind.com/compare/webex). ## A note on the notetakers Otter and Fireflies appear on Zoom-alternative lists, but they answer a different question — they join your meeting and write it down. [Otter](https://intermind.com/compare/otter) transcribes in six languages, [Fireflies](https://intermind.com/compare/fireflies) claims 100+; either way the live meeting stays untranslated and the transcript persists in the one language the meeting was held in. If your problem is multilingual *meetings*, a notetaker is a supplement, not an alternative. We've compared that category separately: [Otter alternatives](https://intermind.com/blog/otter-ai-alternatives), [Fireflies alternatives](https://intermind.com/blog/fireflies-ai-alternatives). ## InterMIND We build for exactly the case the lists skip, so here is our side of the same three axes — stated the same way: - **Live:** every participant picks their language on joining and **hears every speaker in it, simultaneously** — 23 languages for voice, chat and shared notes, in the speaker's own voice. There's no English anchor and no per-meeting pair: a Portuguese–Polish–Indonesian meeting is just a meeting. Documents translate too (30 languages). The numbers differ per pipeline on purpose — [there is no single honest answer](https://intermind.com/blog/how-many-languages-do-you-support). - **Economics:** the host's plan covers the room. **Participants pay nothing and need no account** — guests join by link. No per-listener license, no add-on, no meter. ([Why participation is free](https://intermind.com/blog/free-for-participants).) - **Afterwards:** the meeting persists as a channel — chat history readable in each member's language, a recap delivered to every signed-in member in their own language, documents in the same space. We wrote up the whole axis: [how much of your meeting still exists a week later](https://intermind.com/blog/the-meeting-a-week-later). And because "our translation is great" is exactly the claim you shouldn't take from any vendor, quality is published monthly, per language pair, on real traffic: [/benchmark](https://intermind.com/benchmark). --- ## The comparison, in one table | | Live voice translation | Languages | Per participant, simultaneously? | Who needs a license for translation | What survives the call, translated | | ------------------- | ---------------------------------------------------------------------- | ---------------------------------- | ------------------------------------------------- | ------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------- | | **Zoom** | Synthetic audio, 5 languages (add-on, desktop, meetings only) | 36 caption / 5 voice | Captions: yes. Voice: within 5 languages | Host plan tier or add-on; Voice via Live Translation add-on / ZoomMate | Not stated in documentation | | **Microsoft Teams** | Interpreter agent, 10 languages, scheduled meetings only | 31 caption / 10 voice | Captions: yes. Interpreter: per licensed listener | Organizer Premium/Copilot for captions; each listener Copilot for Interpreter (20 h/month) | Nothing — captions not saved, recordings original audio only | | **Google Meet** | Gemini speech translation, English ↔ 5 languages, one pair per meeting | 5 voice (English-anchored) | No — one pair for the whole meeting | Google AI Pro/Ultra or qualifying Workspace editions | Nothing — unavailable in recordings, no audio saved | | **Cisco Webex** | Human interpreter channels (you staff them) | 16 spoken → 120+ caption (add-on) | Captions: yes. Voice: per interpreter channel | Captions add-on; interpreters hired separately | Recording as spoken; summaries translatable | | **InterMIND** | Yes — every participant hears every speaker in their chosen language | 23 voice/chat/notes · 30 documents | Yes — each participant independently | Host's plan only; participants free, no account | Channel history, recap, documents — in each signed-in member's language | --- ## How to choose (including when not to switch) - **Your meetings are effectively English-only.** Stay where you are — a multilingual meeting product solves a problem you don't have. - **One presenter, many readers** — webinars where attendees follow along in text: Zoom's 36-language translated captions on a Business Plus plan are a real answer, in a tool you already run. - **A Microsoft shop where the multilingual few hold Copilot seats**: Teams' Interpreter agent covers 10 languages for exactly those seats, 20 hours a month, in scheduled internal meetings. - **Your meetings route through English anyway, with one other language**: Meet's speech translation covers English ↔ five languages, one pair at a time, while the beta caps suit you. - **Big staffed events with budget for interpreters**: Webex's interpreter channels at 1,000-attendee scale are built for that production model. - **The meeting itself is multilingual** — people interrupting each other in three languages, guests without your licenses, a team that needs to *reread* decisions in their own language next week: that's the case we built [InterMIND](https://intermind.com/chats) for. ## See it instead of reading about it - **[Try the live demo](https://intermind.com/demo)** — no signup; speak, and hear the room translated per listener in any of 23 languages. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, monthly translation quality on real traffic, with the methodology public. - **[Compare feature-by-feature](https://intermind.com/compare/zoom)** — InterMIND vs Zoom, with every competitor cell sourced. --- ## FAQ **What is the best Zoom alternative for multilingual meetings?** It depends on which axis is broken for you. If captions are enough, Zoom's own 36-language translated captions or Teams' 31 are the field. If participants need to *hear* the meeting in their own language, the documented options narrow fast: Teams' Interpreter (10 languages, per-listener Copilot license, 20 h/month), Meet's speech translation (English ↔ 5, one pair per meeting), or InterMIND (23 languages, per participant, host's plan covers everyone). **Which Zoom alternatives translate voice, not just captions?** Three documented machine options in 2026: Zoom's own Voice translator (5 languages, add-on), Microsoft Teams' Interpreter agent (10 languages, per-listener license), Google Meet's speech translation (English ↔ 5, one pair). Webex handles voice via human interpreter channels. InterMIND translates voice per participant in 23 languages as the room's default behavior. **Is Microsoft Teams or Zoom better for translated meetings?** Compare the fences, not the brands. Zoom: 36 caption languages, voice in 5 via a paid add-on, desktop only. Teams: 31 caption languages behind an organizer Premium/Copilot license, voice in 10 behind a per-listener Copilot license with a 20-hour monthly meter, scheduled meetings only. Neither saves anything translated after the call — that's documented on both sides. **Are there free Zoom alternatives with live translation?** For participants, InterMIND is free by design — guests join by link with no account, and the [live demo](https://intermind.com/demo) requires no signup either; the host's plan covers the room. On the incumbent platforms, translation sits behind paid tiers, add-ons or per-seat AI licenses on the host or listener side (documented per vendor above). **Does any Zoom alternative keep the meeting translated after it ends?** Among the platforms above, the vendors' documentation answers no — Teams states captions aren't saved and recordings keep original audio; Google states speech translation is unavailable in recordings; Zoom's docs don't state translated output persists. InterMIND is built the other way around: the meeting persists as a channel whose chat, recap and documents each member reads in their own language. The full audit: [the meeting, a week later](https://intermind.com/blog/the-meeting-a-week-later). --- *Sources: [Zoom — Enabling and configuring translated captions](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0059081){rel=""nofollow""}, [Zoom — Using the Voice translator for meetings](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""}, [Zoom — Using Language Interpretation](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0064768){rel=""nofollow""}, [Microsoft — Use live captions in Teams meetings](https://support.microsoft.com/en-us/office/use-live-captions-in-microsoft-teams-meetings-4be2d304-f675-4b57-8347-cbd000a21260){rel=""nofollow""}, [Microsoft — Interpreter in Teams meetings and calls](https://support.microsoft.com/en-us/office/interpreter-in-microsoft-teams-meetings-and-calls-c7efe2bb-535d-42ab-a5c4-d2d91619b46d){rel=""nofollow""}, [Microsoft Learn — Teams Premium licensing](https://learn.microsoft.com/en-us/microsoftteams/teams-add-on-licensing/licensing-enhance-teams){rel=""nofollow""}, [Google Meet — Learn about Speech Translation](https://support.google.com/meet/answer/16221730){rel=""nofollow""}, [Google Meet — Use translated captions](https://support.google.com/meet/answer/10964115){rel=""nofollow""}, [Webex — Show real-time translation and transcription in meetings and webinars](https://help.webex.com/en-us/article/nqzpeei/Show-real-time-translation-and-transcription-in-meetings-and-webinars){rel=""nofollow""}, [Otter — supported languages](https://help.otter.ai/hc/en-us/articles/360047247414-Supported-languages){rel=""nofollow""}, [Fireflies — supported languages](https://guide.fireflies.ai/articles/2973706448-learn-about-fireflies-supported-languages){rel=""nofollow""}. Vendors change plans, prices and language lists over time; check their pages for the current state. All facts checked August 2026.* # Zoom interpretation: how Language Interpretation works, what it costs, and when it's the wrong tool - **It works, and it does not interpret anything.** One audio channel per language; the interpreters are humans you book and pay yourself. - **Scheduled, staffed, desktop-managed.** No instant meetings, no breakout rooms, no managing from a phone; local recordings keep one channel. Right for a board meeting, not the weekly sync. - **InterMIND keeps the whole meeting in each member's language,** voice, chat and the recap, next to Zoom rather than instead of it. Guests join free by link, no account; you pay only for active members. If you searched "Zoom interpretation" or "Zoom interpreter," the short answer is: **Zoom has a built-in interpretation feature, it works, and it does not interpret anything.** Language Interpretation gives a meeting or webinar one audio channel per language and routes *your* interpreters into them. Zoom provides the channels; finding, booking and paying the humans who speak into them is entirely your job. It is the right tool for a specific meeting shape — a formal session with professional interpreters — and the wrong tool for most working calls. This guide covers the feature as Zoom documents it: requirements, setup, languages, what happens to recordings and breakout rooms, how it compares to Zoom's own AI translation features, and an honest line on when to use [AI simultaneous interpretation](https://intermind.com/features/simultaneous-interpretation) instead. > For everything Zoom can do about language — translated captions and the AI voice translator included — see [Zoom live translation: how it works, and where it stops](https://intermind.com/blog/zoom-live-translation). --- ## What Zoom interpretation actually is Language Interpretation creates **separate audio channels per language** inside a meeting or webinar. Interpreters listen to the floor audio and speak into their assigned channel; each participant picks a channel and hears the interpreter, with the original speaker ducked underneath — the original audio returns to 100% volume **8 seconds after the interpreter stops speaking**. Participants can also mute the original audio entirely. It is simultaneous interpretation *delivery* — the same job a booth-and-receivers rig does at a conference, minus the hardware. The interpreting itself is still done by people you bring. ## Requirements Everything below is from Zoom's own documentation (checked August 2026): - **Plan:** a Pro, Business, Education, or Enterprise account, with Language Interpretation enabled in account settings. - **A scheduled meeting or webinar.** Language interpretation cannot be used with a Personal Meeting ID, and **you can't add or start it in an instant meeting** — it is configured at scheduling time. - **Your own interpreters:** the host can designate **up to 20 participants** as interpreters, assigned by email when scheduling or manually during the session. In a webinar, anyone assigned as an interpreter automatically becomes a panelist. - **Desktop app for anyone managing or interpreting.** Language interpretation **can't be initiated or managed from the Zoom mobile app or web app** — mobile and web participants can only listen to a channel and view interpreted text. ## Languages - **9 default languages:** English, Chinese, Japanese, German, French, Russian, Portuguese, Spanish, Korean. - **Custom languages:** up to **5 custom languages per meeting or webinar by default**; accounts can request up to 25 custom languages when scheduling by contacting Zoom Support. In practice the constraint is never the channel list. It's finding two professional interpreters for each language pair you need. ## How to enable Zoom interpretation, step by step 1. **Turn the feature on:** account Settings → Meeting → In Meeting (Advanced) → Language Interpretation. Add any custom languages you need. 2. **Schedule the meeting or webinar** with an automatically generated meeting ID and tick *Enable language interpretation*; enter each interpreter's email and language pair. 3. **Start the session**, click *Interpretation*, confirm or reassign the interpreters, and click *Start*. 4. **Participants pick a channel** from the Interpretation menu and optionally mute the original audio. Mobile and web participants can listen; managing and interpreting need the desktop app. 5. **Interpreters swap** by the usual professional cadence (pairs, roughly 30-minute turns) — Zoom supports relay interpretation for indirect pairs. ## The limits that bite mid-meeting - **Breakout rooms lose interpretation.** Channels exist in the main session only. A multilingual workshop that splits into groups goes back to a common language the moment it splits. - **Recordings: cloud yes, local no.** Cloud recordings capture the original audio *and* the translation channels. A local recording captures only the audio the recording participant could hear — not multiple channels. If someone records locally, the "record" of a two-language meeting is one language. - **Instant calls are out** — interpretation is a scheduled-meeting feature by design. - **The interpreters are your problem:** sourcing, vetting, booking days ahead, and paying professional day rates — two per language, per the industry standard. Zoom solves routing, not staffing. What that staffing involves: [our plain-language guide to simultaneous interpretation](https://intermind.com/blog/simultaneous-interpretation-guide). - **Captions ≠ this feature.** Zoom's translated captions and voice translator are separate AI capabilities with their own plan gating — compared below. None of these are bugs. They are the shape of a feature built for formal, staffed, scheduled events. ## Zoom interpretation vs Zoom's AI translation vs an AI interpreter Zoom ships three language features, and "Zoom interpretation" searches usually mean one of the first two. Side by side, per the vendors' documentation: | | Zoom Language Interpretation | Zoom translated captions | Zoom Voice translator | InterMIND | | -------------------------------------- | -------------------------------------- | ------------------------------------------------------------- | ----------------------------------------------- | --------------------------------------------------------------------- | | Who translates | Human interpreters you hire | AI (text) | AI (synthetic voice) | AI (voice, chat, notes, documents) | | Plan | Pro, Business, Education, Enterprise | Business Plus / Enterprise, or the Translated Captions add-on | Live Translation add-on or ZoomMate | Any meeting; the host's plan, free for every participant | | Languages | 9 default + up to 5 custom per session | 36, plus 3 target-only | 5 (English, Chinese, French, Japanese, Spanish) | 23 on voice and chat, 30 on documents | | Each listener picks their own language | Yes, per channel you staffed | Yes | Yes | Yes | | Instant meetings | No — scheduled only | Yes | Yes (meetings only) | Yes | | Webinars | Yes | Yes | No | Interactive town halls up to 1,500 (Enterprise); no one-way broadcast | | Breakout rooms | No | — | — | — | | Mobile | Listen only | Yes | Desktop app only | Web, desktop, iOS, Android | | What survives the meeting | Cloud recording with channels | Captions during the meeting | — | Recap, transcript and history in each signed-in member's language | Sources for the Zoom columns are in the footer; the InterMIND column is what the product does today, not a roadmap. ## Who provides the interpreters for Zoom Zoom does not. "Zoom interpretation services" means one of two things: a language-services agency that supplies certified simultaneous interpreters who join your Zoom session as assigned interpreters, or a remote-interpreting platform that connects its interpreters into the meeting. Either way you contract the people, brief them on the agenda, and pay per interpreter, per language, per day — the cost structure is in [our guide to simultaneous interpretation](https://intermind.com/blog/simultaneous-interpretation-guide). Zoom's feature is the audio plumbing those services plug into. ## When Zoom's interpreter channels are the right call Use Language Interpretation when the event is **worth professional humans**: a board meeting with a certified interpreter, an AGM, a press briefing, a formal training session with contracted interpreters. If you're already paying interpreters, Zoom routes them competently and your attendees never install anything new. ## When it's the wrong tool The mismatch shows up on the meetings that were never going to book interpreters — the weekly sync with the Berlin and São Paulo teams, the ad-hoc sales call, the support escalation. For those, **AI simultaneous interpretation** does the interpreting itself, on demand, with no scheduling and no day rates. The shape of the trade, honestly: professional humans still win where a mistranslated clause is a liability — [we say so explicitly](https://intermind.com/blog/simultaneous-interpretation-guide). Everywhere below that bar, [an AI interpreter built into the meeting](https://intermind.com/features/simultaneous-interpretation) gives you what Zoom's channels can't: - **Every participant speaks and hears** — not one stage feeding an audience, but 23 languages, each listener picking their own, every speaker heard in their own voice. - **Nothing to staff or schedule** — interpretation is just *on*, for instant calls too, and guests join by link without an account. - **The rest of the meeting is translated** — chat, shared notes, and documents come back in each viewer's language, and the record isn't one audio channel. - **Quality you can check** — [published per language pair, monthly](https://intermind.com/benchmark), not claimed. The direct comparison, feature by feature: [InterMIND vs Zoom](https://intermind.com/compare/zoom). --- ## FAQ **How does Zoom interpretation work?** The host schedules a meeting or webinar with Language Interpretation enabled and assigns interpreters by email. During the session each interpreter speaks into their language channel; participants pick a channel and hear the interpreter over the ducked original audio, which returns to full volume 8 seconds after the interpreter stops. **How do I enable interpretation in Zoom?** Account Settings → Meeting → In Meeting (Advanced) → Language Interpretation. Then schedule a meeting with a generated ID, tick *Enable language interpretation*, add interpreters with their language pairs, and click *Interpretation → Start* once the meeting is running. **Is Zoom interpretation free? Which plan do I need?** The feature is included on Pro, Business, Education and Enterprise accounts — it is not available on Basic. The real cost is the interpreters: professional simultaneous work is billed per interpreter, per language, per day, typically two interpreters per language. **How many languages does Zoom interpretation support?** Nine default languages (English, Chinese, Japanese, German, French, Russian, Portuguese, Spanish, Korean) plus up to 5 custom languages per session by default, with up to 25 available on request to Zoom Support. A session can have up to 20 interpreters. **Does Zoom have AI interpretation?** Not in this feature — Language Interpretation is human-powered by design. Zoom's AI translation is translated captions (text, 36 languages plus 3 target-only) and the Voice translator (synthetic audio in 5 languages, meetings only). For AI simultaneous interpretation across 23 languages you're looking at [a different category of tool](https://intermind.com/blog/best-ai-conference-translation-tools). **Does Zoom interpretation work in webinars?** Yes. Assigned interpreters automatically become panelists, and attendees pick a channel the same way as in meetings. **Can I use Zoom interpretation in breakout rooms?** No — interpretation runs in the main session only. If your format depends on multilingual small groups, that's a structural blocker. **Is Zoom interpretation recorded?** Cloud recordings capture the original audio and the translation channels. Local recordings capture only what the recording participant could hear — a single channel. **Can participants use Zoom interpretation on mobile?** Mobile and web participants can listen to an interpretation channel and view interpreted text, but interpretation can't be started, managed, or performed from the mobile or web app — hosts and interpreters need the desktop app. **How do I get an interpreter for a Zoom meeting?** Hire one. Zoom doesn't supply interpreters; agencies and remote-interpreting providers do, and their interpreters join your session as assigned interpreters. For meetings that don't justify hiring, an AI interpreter built into the meeting removes the step entirely. --- ## Hear the alternative before you book anyone If the meeting you're trying to fix is a working call rather than a staffed event, test the AI route first — it takes two minutes and costs nothing: - **[Run the live demo](https://intermind.com/demo)** — hear a live meeting interpreted into another language — no signup needed. - **[Read the benchmark](https://intermind.com/benchmark)** — per-pair quality on real traffic, updated monthly. - **[InterMIND vs Zoom](https://intermind.com/compare/zoom)** — where each platform actually stands, feature by feature. — The Mind.com Team --- *Sources: [Zoom — Using Language Interpretation in your meeting or webinar](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0064768){rel=""nofollow""}, [Zoom — Enabling Language Interpretation](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058373){rel=""nofollow""}, [Zoom — Enabling and configuring translated captions](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0059081){rel=""nofollow""}, [Zoom — Using the Voice translator for meetings](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""}. Zoom expands plans and language lists over time; check the support pages for the current state. All facts checked August 2026.* # Zoom live translation: how it works, and where it stops - **Yes, three ways.** Translated captions per participant, a Voice translator in five languages behind an add-on, and interpreter channels for humans you hire. - **Zoom translates what the meeting reads, not what it hears.** The Voice translator covers five languages, desktop only, meetings only; long speech is translated after a pause. - **InterMIND keeps the whole meeting in each member's language,** voice, chat, files and the recap, next to Zoom rather than instead of it. Guests join free by link, no account; you pay only for active members. If you searched "Zoom live translation," the honest short answer is: **yes, Zoom can translate a live meeting — three different ways — and which one you get depends on your plan, your region, and whether you're willing to hire the interpreters yourself.** All three are real. None of them is a room where a German, a Japanese and a Brazilian participant each *hear* the meeting in their own language for as long as it runs. This post explains how each works, how to turn it on, and exactly where the ceiling is. > This is the platform how-to companion to our foundational guide, [*Real-time meeting translation: how it works, and how to evaluate one*](https://intermind.com/blog/real-time-meeting-translation). For the Google Meet and Microsoft Teams versions of this post, see [Meet](https://intermind.com/blog/google-meet-live-translation) and [Teams](https://intermind.com/blog/teams-live-translation). New to interpretation as a category? Start with [*Simultaneous interpretation: booth, RSI, or AI*](https://intermind.com/blog/simultaneous-interpretation-guide). --- ## The three features, and why they're not the same thing Zoom has shipped live translation in three distinct forms. They get conflated constantly, so separate them first: ### 1. Translated captions (text) The workhorse. Zoom's automated captions run live transcription; translated captions translate that text stream into each participant's chosen language. Two genuinely good things here: **the language list is long** — 36 fully supported languages, plus Greek, Norwegian and Welsh as target-only — and **every participant picks their own caption language independently**, without asking the host. It works in meetings *and* webinars. The catch is the gate: translated captions come with **Business Plus and Enterprise** Workplace plans. On Pro or base Business you need the paid **Translated Captions add-on** — this is the one AI feature Zoom did *not* fold into the AI Companion bundle that ships with every paid plan. And it's a reading experience. Captions translate what anyone *reads*, not what anyone *hears*. ### 2. Voice translator for meetings (audio) The 2025–2026 headline feature, announced with AI Companion 3.0 at Zoomtopia. This one speaks: it takes the translated-caption stream and renders it as **synthetic translated audio**, per participant, with a slider to balance the original voice against the translated one. Each participant picks their own speaking and listening language. It shipped through 2025–2026 as a tightly fenced beta and left beta exactly the way Zoom's docs predicted: as a purchase. It now requires the **Live Translation add-on or ZoomMate** (where advanced AI features draw AI Credit costs) — the details are in the limits section below. ### 3. Language Interpretation (humans, channels) The oldest feature, and the one event teams know: the host designates up to 20 **human interpreters**, Zoom opens an audio channel per language, and listeners pick a channel — original audio underneath at low volume. Zoom supplies the plumbing here, not the interpreters. You book those, brief them, and pay them yourself. It's available on Pro, Business, Education and Enterprise accounts, with nine default channel languages plus custom ones. (The full setup walkthrough, limits included: [*Zoom interpreter setup*](https://intermind.com/blog/zoom-interpreter).) --- ## How to turn each one on **Translated captions:** an admin enables automated captions and translated captions in account settings (Business Plus/Enterprise or the add-on). In the meeting, each participant clicks the captions control and picks their language — no host involvement needed. **Voice translator:** an admin enables it in account settings; the account (Basic through Enterprise) needs the Live Translation add-on or ZoomMate, and participants need the desktop app 7.0.0+. In the meeting, you pick your speaking language and the language you want to hear, and adjust the original/translated audio balance. **Language Interpretation:** the host schedules a meeting or webinar with interpretation enabled, assigns interpreters in advance (or in-meeting from the desktop app), and participants pick their audio channel once it starts. The friction isn't the toggles. It's what the toggles can and can't do. --- ## The limits that actually decide if it fits As of August 2026, by Zoom's own support documentation: - **Captions translate text, not the room.** The long language list and per-participant choice are real — but everyone is reading subtitles while the meeting's audio stays monolingual. Zoom also notes plainly that "translated captions may not be accurate," and dialects don't translate between each other (no French (France) ↔ French (Canada)). - **The voice translator speaks five languages and costs extra.** The full list: **English, Chinese, French, Japanese, Spanish**. Anything outside those five — Hindi ↔ English, for instance — isn't covered at any price; for that pair specifically, see the [Hindi to English voice translator](https://intermind.com/blog/hindi-to-english-voice-translator) guide. It's out of beta and priced as the Live Translation add-on or via ZoomMate with AI Credit costs. **Meetings only — no webinars.** Desktop app only. And on long speech it stops being simultaneous: extended turns are translated *after the speaker pauses* — consecutive interpretation with a synthetic voice. - **Language Interpretation needs your humans and your planning.** Scheduled meetings only — no Personal Meeting ID, no instant meetings, no breakout rooms — and the interpreters are professionals you source, book and pay per day, per language. That's not a flaw; it's a different product category, with [a cost structure of its own](https://intermind.com/features/simultaneous-interpretation). - **No machine voice translation in webinars at all.** A multilingual webinar on Zoom today means translated captions for readers, or human interpreter channels you staff yourself. Side by side with what Teams and Google Meet require for the same job: [what Teams requires for translated captions in webinars and town halls](https://intermind.com/blog/teams-live-translation). None of this makes Zoom's features bad. The caption stack in particular is broad and genuinely per-participant. But it makes Zoom's live translation **text-first, with spoken translation either a five-language paid add-on or staffed by people you hire.** --- ## The structural ceiling, in one sentence **Zoom translates what your meeting *reads* — broadly and well. What your meeting *hears* is either a five-language paid add-on, or human interpreters you bring yourself.** A genuinely multilingual meeting needs every participant *hearing* the room in their own language, for the whole meeting, wherever they are — and that's an architecture, not a longer language list. If your meetings are caption-friendly — presentations, webinars where attendees read along — Zoom's translated captions on a Business Plus plan may be all you need, in a tool you already have. If your meetings are *conversations* — people interrupting, deciding, thinking out loud in three languages — you've hit the ceiling. --- ## When you've outgrown captions and quotas This is the job we built InterMIND for: not subtitles under a monolingual call, but **every participant hearing the meeting in their own language, simultaneously, live.** Concretely, where Zoom's stack reads and its add-on speaks five languages: - **23 languages live on voice**, chat and shared notes — any mix, no English anchor, no regional gate, no five-language cap. ([The full end-to-end translation stack](https://intermind.com/features/realtime-translation) is its own page.) - **Per-listener audio, live.** Each participant hears the meeting in their own picked language at the same time — five people, five languages, one room. (How that works under the hood: [*Inside the four translation pipelines*](https://intermind.com/blog/inside-the-translation-pipelines).) - **Webinars and conferences included** — the room size follows the host's plan ([pricing](https://intermind.com/pricing)), each participant picking their own listening language. That's [simultaneous interpretation without the booth](https://intermind.com/features/simultaneous-interpretation), not an add-on — the full event workflow is at [events & webinars](https://intermind.com/use-case/events). - **Documents too** — drop a PDF or DOCX into the meeting and each viewer gets it in their language, 30 languages on files. - **Quality you can audit.** We publish per-language-pair scores on real traffic at [`/benchmark`](https://intermind.com/benchmark) — Zoom's accuracy claims are made in its own press releases; ours are reproducible. We're not claiming Zoom is bad — for caption-first meetings its translation stack is one of the broadest shipping. We're claiming it's a different shape of meeting. The feature-by-feature version is at [InterMIND vs. Zoom](https://intermind.com/compare/zoom). --- ## What stays after the call, and where it lands The live part is the half of the meeting a vendor demos; the other half starts when the call ends. What InterMIND keeps, and where it can go — each item has its own guide: - **The recap, in each member's language.** After every transcribed meeting the signed-in participants get the AI summary, the full transcript and the recording on one permanent, members-only link; each reads the summary in their own language, and a channel keeps the recap of every past session. — [Meeting recap: what you get after the call](https://intermind.com/blog/meeting-recap) - **A copy in your CRM or help desk, by email.** The host adds the tool's inbound address as a recap copy recipient, confirms it once through a test email, and every recap of that room is sent there as a hidden BCC. — [How to get a copy of every meeting recap in your CRM by email](https://intermind.com/blog/how-to-get-a-copy-of-every-meeting-recap-in-your-crm-by-email) - **Structured, into any system.** A Zapier trigger, a signed `recap.ready` webhook, and an API with an OpenAPI 3.1 contract for Make, n8n, Pipedream and AI agents. — [Zapier, a webhook, or the API](https://intermind.com/blog/how-to-send-meeting-recaps-to-your-crm-with-zapier-or-the-api) - **The channel's history.** A meeting that persists as a channel keeps its chat, files, document summaries and recaps, readable by every member in their own language — and a client outside the team can be a member of it by email. — [How to add an external client to a team chat channel](https://intermind.com/blog/how-to-add-an-external-client-to-a-team-chat-channel) - **What the team sends in from elsewhere.** Every channel has its own email address, so a ticketing system or a monitoring tool posts into it without a bot; a file shares in from any app's share sheet on a phone or a Mac. — [Email to channel](https://intermind.com/blog/email-to-channel-no-bot), [Share from any app](https://intermind.com/blog/how-to-share-a-file-into-your-team-chat-from-any-app) A guest of a meeting — a participant without an account — gets the live part in full and none of the record; the account is free, and it is what makes the record reachable. --- ## Try the other side of the ceiling - **[Try the live demo](https://intermind.com/demo)** — *hear* a real meeting translated live, per listener, in any of 23 languages — no signup needed. - **[Start your first meeting](https://intermind.com/chats)** — guests join by link, each in their own language. - **[See the benchmark](https://intermind.com/benchmark)** — per-pair, per-month translation quality on real traffic, with the methodology written down. - [InterMIND vs. Zoom](https://intermind.com/compare/zoom) — honest, feature-by-feature. - Just need a record, not live translation? The notetaker side of the market: [the 9 best Fireflies.ai alternatives](https://intermind.com/blog/fireflies-ai-alternatives). Zoom live translation is real, useful, and clearly fenced: captions for most, a five-language paid add-on for some, human interpreters for the rest. Knowing where the fences are is the whole decision. --- ## FAQ **Does Zoom translate audio or only captions?** Three features, three answers. Translated captions render the meeting as text in each participant's chosen language. The Voice translator speaks synthetic translated audio in five languages. Language Interpretation opens audio channels for human interpreters you hire yourself. **How many languages do Zoom translated captions support?** 36 fully supported languages, plus Greek, Norwegian and Welsh as translation targets only. Dialects don't translate between each other — no French (France) ↔ French (Canada). **What does the Zoom Voice translator require?** A Zoom account (Basic through Enterprise) with the Live Translation add-on or ZoomMate (AI Credit costs apply), and the desktop app 7.0.0 or higher. It supports five languages — English, Chinese, French, Japanese, Spanish — in meetings only, and long speech is translated after the speaker pauses. **Do translated captions cost extra on Zoom?** They're included when the host is on a Business Plus or Enterprise-tier Workplace plan; on other paid plans you need the Translated Captions add-on — it's not part of the AI Companion bundle. **What else should we look at if these limits are the problem?** The whole field on the same axes — who the translation reaches, what it costs per seat, and what survives the call — is laid out in [Zoom alternatives for multilingual meetings](https://intermind.com/blog/zoom-alternatives). **What if the conversation isn't in Zoom at all?** The same question comes up for a French, Spanish or Russian speaker talking to an Italian one: a phrase app handles a menu, a conversation needs a room where everyone speaks their own language. Our guides on the [French–Italian](https://intermind.com/blog/traduttore-francese-italiano-vocale), [Spanish–Italian](https://intermind.com/blog/traduttore-spagnolo-italiano-vocale) and [Russian–Italian](https://intermind.com/blog/traduttore-italiano-russo-vocale) voice translator draw that line, and the [Italian voice translator overview](https://intermind.com/blog/traduttore-vocale) covers the rest. — The Mind.com Team --- *Sources: [Zoom — Enabling and configuring translated captions](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0059081){rel=""nofollow""}, [Zoom — Viewing captions in another language](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0060844){rel=""nofollow""}, [Zoom — Using the Voice translator for meetings](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084896){rel=""nofollow""}, [Zoom — Enabling or disabling Voice translator for meetings](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0084897){rel=""nofollow""}, [Zoom — Using Language Interpretation in your meeting or webinar](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0064768){rel=""nofollow""}, [Zoom — Enabling Language Interpretation](https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0058373){rel=""nofollow""}, [Zoomtopia 2025 announcements](https://news.zoom.com/zoomtopia2025/){rel=""nofollow""}. Zoom expands plans and language lists over time; check the support pages for the current state. All facts checked August 2026.* # Native desktop and mobile apps, per-team SSO, and translation auto-detect This release ships our native desktop and mobile apps with full meeting, chat, and in-call parity. The translation page now auto-detects speech direction, per-team OIDC SSO is available, and admins can export a CSV audit trail. Post-meeting digests gain negotiation-protocol mode with per-point status tracking. ## New **Desktop app** — Native desktop application with screen-share and system-audio translation, native notifications, tray/dock badge, and calls that survive minimization and screen lock. Deep links (`intermind://join/`) open meetings directly; auto-update keeps you current. **Mobile app** — Full native experience for iOS and Android with branded splash and icon set: | Area | Highlights | | ---------- | ---------------------------------------------------------------------------------------------------------------------------------------- | | Meetings | Join/host with live video grid, schedule, recent list | | Chat | Reply-quote, side-by-side translation, search, file & image attachments, message actions (react, edit, delete, pin, copy), read receipts | | Channels | Member management, archive view | | In-call | Reactions, raise hand, participants sheet, live subtitles, end-for-all, in-call language change, chat overlay | | Moderation | Mute, kick, or rename participants | | Settings | Default meeting language, theme, sign out | | Sign-in | Email-code login, Google sign-in, guest join by link or code with host approval | | Background | Calls survive backgrounding via foreground service | **Per-team SSO** — Configure OIDC-based single sign-on per team. SP Details now shows the real redirect URI. **Team audit trail** — Admins can view and export a CSV audit trail of team activity. **Negotiation-protocol digests** — Post-meeting digests support a negotiation mode that marks each protocol point as agreed, open, or disputed, with drill-down to the corresponding transcript turn. **Translation page redesign** — Auto language-pair detection switches direction based on detected speech. "Translate to" header with an Auto target, centered and persistent captions, and audio muted by default to prevent feedback. **Benchmark page redesign** — /benchmark now shows per-language quarterly bars in a cleaner landing-style layout. ## Improved **Mobile ergonomics** — Tap-first conference footer with overflow menu, full-width footer sheets, coarse-pointer detection, ≥44px touch targets, and transparent system navigation bar. **Camera, mic & cockpit indicators** — Auto-reacquire camera and mic after forcible release, with state-colored cockpit buttons. Persistent translation-limit badge and clearer status when transcription auto-enable fails. **Meeting end flow** — Participants are nudged toward recording and summary locations; hosts redirect instantly when ending a meeting for all, removing a \~10-second delay. **Digest quality** — Map-reduce chunking for long meetings replaces last-4000-word truncation. Digest runs on EU-pinned Mistral via AI Gateway. **Live transcript** — Respects the "hidden" setting, labels speakers, and shows a brief explanation when collapsed. Collapse clamps by lines while keeping per-speaker breakdown. **Chat recap cards** — Recording and summary recap cards broadcast live to open channel chats. **Meeting performance & reliability** — Video subscription limited to visible filmstrip tiles, reducing bandwidth in large meetings. Redis fan-out lifts the high-frequency message limit, and self-healing of stopped servers plus orphaned-conference cleanup reduce dropped meetings. **Help & Ask AI** — Per-page contextual FAQs, ⌘/ shortcut in the Ask AI tooltip, localized help content across all supported locales, and localized doc screenshots per locale. **Theme & consent** — Color mode stored in a cookie so server-side rendering respects it, eliminating the post-load theme flash. Cookie banner via Usercentrics CMP with analytics gated on consent. ## Fixed **Audio glitch on translate page** — Fixed double mic-open that caused audio glitches during playback. **Blank share-link summary** — Share-link pages for meeting summaries no longer open blank. **Broken user avatars** — Avatars load reliably via a server-side proxy. **Cold deep-link bounce** — Cold deep-links to a meeting no longer bounce to the login page. **Name field sync** — The Join "Name" field tracks account-name changes while preserving manual edits. **Camera icon flicker** — Stopped camera-icon flicker from same-id camera reselection. **Stale meeting cache** — Meeting cache resets on identity change to prevent showing data from a previous session. **Storage upgrade link** — Storage-limit CTAs now point to the correct upgrade page. **Security hardening** — Fixes from our ongoing security review. # Desktop app, mobile redesign, and simpler meeting controls This week we shipped our new desktop application and a redesigned mobile experience with picture-in-picture. We also simplified meeting controls across web and mobile, and made document translation usage easier to track. ## New **Desktop app** — A dedicated desktop client is now available for download, including a universal macOS build. **Mobile conference layout** — The mobile in-call view now uses a single-column layout with tap-to-fullscreen and a draggable picture-in-picture window. **Mobile web bridge** — The mobile app can now open authenticated web pages natively, letting you manage billing and integrations directly from the app. **Mobile organization management** — You can now manage users natively in the mobile app's Organization settings. **Meeting time limit alerts** — You will now see a notification when a meeting is approaching its time limit. **Document translation tracking** — The billing interface now tracks document translations as a per-period file quota, while text translation remains free on paid plans. ## Improved **Simpler meeting controls** — Leaving a meeting is now a single click or tap. The option to end the meeting for everyone is moved into the overflow menu and is only visible to moderators. **Mobile chat layout** — The standalone chat and in-call chat headers are now unified, with the call button moved to the composer. ## Fixed **Screen-share stability** — Resolved regressions where sharing your screen could cause your self-video to drop, overlap with other tiles, or fail to reconnect properly. **Accurate document quota** — Translation word counts no longer include HTML markup, which previously inflated your usage statistics. **Seat counting** — Workspace owners are no longer double-counted as members in seat usage calculations. **Guest access stability** — Late guest approvals or expirations no longer affect already-approved guests, and mid-meeting authentication errors for guests have been resolved. **Mobile mute and join flow** — Fixed microphone acquisition when unmuting after being muted by a host, and resolved issues with participant join and mute flows on mobile. **Live presence accuracy** — The mobile meetings list now refreshes automatically when you focus the app, ensuring the live-presence dot reflects actual headcount. **Security hardening** — Fixes from our ongoing security review. # 10 new UI languages, mobile push notifications, and improved chat This week brings major language expansions and mobile stability improvements. You can now rename meetings, receive mobile push notifications, and use InterMIND in 10 additional languages, including Japanese, Korean, and Russian. ## New - **10 new UI languages** — Added Italian, Polish, Dutch, Ukrainian, Russian, Japanese, Korean, Indonesian, Vietnamese, and Turkish interface options. - **Live language switcher preview** — The language switcher now shows a live translation preview as you select a new locale. - **Mobile push notifications** — Receive mobile alerts when guests are approved to join and when new chat attachments are shared. - **Rename meetings** — Update meeting titles directly from your meeting list. - **Editable mobile display name** — Change your display name on mobile directly from the Settings menu. ## Improved - **Video grid layout** — Refined the mixed-grid layout to better handle portrait and landscape video streams across all screen sizes. - **Participant labels** — Participant tiles now consistently show "Role · Language" on both web and mobile. - **Web chat scrolling** — Inverted the chat list for more natural scrolling, with improved auto-scroll logic and initial rendering to prevent flashes. - **Host-configurable recaps** — Meeting hosts can now set a custom word threshold for recap summaries. - **Ask AI persistence** — Conversations in the Ask AI drawer now persist when you close and reopen the panel. - **Android notification icons** — Dedicated small icons ensure Android push notifications render correctly in the status bar. ## Fixed - **Mobile chat reliability** — Fixed disconnects on resume, added a watchdog for stale sockets, and improved auto-scroll and list refreshes. - **Mobile incoming speech translation** — Resolved an issue preventing incoming speech translation from activating on mobile. - **Recap timestamps** — Fixed broken drill-down timestamps in recap summaries and improved underlying link processing. - **Safari file uploads** — Resolved an issue where Safari blocked the chat file dialog. - **Meeting roster on reconnect** — Eliminated duplicate participant entries and removed stale connections when reconnecting. - **Mobile SSO flow** — Enhanced the mobile SSO flow to handle provider mismatches gracefully. - **Security hardening** — Fixes from our ongoing security review. # External chat invites, recap updates, and improved translation stability This week brings external chat participants, email invites, and a redesigned meeting recap experience that posts summaries as chat notes. We also improved device handling, idle participant behavior, and translation stability across the platform. ## New - **External channel participants and email invites** — You can now add external participants to chat channels and invite them via email. Invitees require a consent gate, while users you've met before are added without approval. - **Roster indicators and in-app notifications** — The chat roster now shows pending invites and distinguishes between users you've met and external users. You also receive an in-app notification when someone adds you directly. - **Periodic running recap** — Meetings now generate a periodic running recap instead of a real-time transcript. Summaries are automatically posted as chat notes after the meeting. - **Recap quality signals** — You can leave a 👍/👎 on meeting summaries to provide direct, measurable feedback on recap quality. - **Single sign-on preview** — Google and Microsoft login options are now available in preview. ## Improved - **Idle participant behavior** — Idle participants are now auto-muted and marked as "away" instead of being kicked from the meeting. - **Mobile chat rows** — Chat list rows on mobile have been redesigned for clearer visual structure. - **Device management** — Audio and video device lists are now consistent across the app. Speaker selections made in the Speaker Test modal now sync directly into the main cockpit. - **Support address** — Our support email address is now . ## Fixed - **Manual language switching** — Changing your language manually now correctly updates your participant language and chat translations. - **Translation stability and locales** — Translations are now more robust to structured-output drift, and we recovered missing locale translations. We also fixed hardcoded English on localized surfaces and added missing Italian, Polish, Dutch, and Ukrainian locale rules. - **Native-to-native translation** — Stopped unnecessary native-to-native translation on the on-demand chat path. - **Session takeovers and reconnect ghosts** — Fixed an issue where joining a meeting on the same device caused a session takeover or a reconnect ghost. - **Intrusive video tooltips** — Removed intrusive title tooltips on video tiles; this information is now contained in the modal view. - **Billing and storage counts** — Fixed an issue where conferences treated post-v2 Pro subscribers as basic. Storage now correctly counts toward the team pool. - **In-page anchors during translation** — In-page links now have stable anchors so they survive translation. - **Guest-knock delivery** — Improved out-of-room guest-knock delivery reliability and sound on the web. - **Demo invites** — Demo invites now correctly join the same room, and self-lookup no longer throws a 403 error. - **Join and accept-page errors** — Improved distinct error messaging for join-fail toasts and the accept-invitation page. - **Admin user panel** — Fixed sorting and false data on the admin users panel. - **Mobile org invite UI** — Fixed visual issues with the mobile organization users invite interface. - **Moderator admit rights** — Unified moderator admit rights and ensured fresh meetings are watched immediately. - **Security hardening** — Fixes from our ongoing security review. # Recap redesign, mobile screen sharing, and Microsoft Calendar sync This week brings major upgrades to calendar reliability, meeting recaps, and mobile screen sharing. You can now connect Microsoft Calendar, edit scheduled meetings directly on the web, and view recaps in a dedicated tabbed interface. ## New - **Microsoft Calendar sync** — Connect Microsoft Calendar alongside Google Calendar to keep your schedules synchronized. - **Edit scheduled meetings on web** — Modify existing scheduled meetings directly from the web UI without needing to recreate them. - **Mobile screen sharing** — Send and receive screen shares on mobile, featuring gesture-based zoom and landscape mode support. - **Recap redesign** — Meeting recaps open from the /meetings panel into a dedicated page with Summary and Transcript tabs, a rich text editor, and correct speaker name attribution. - **Billing usage by host** — The /billing/usage page now attributes voice, chat, and document quotas to specific hosts. - **Arabic and Hindi translations** — Added Arabic and Hindi to the translation language picker, bringing the total to 24 supported languages. - **Member role navigation** — Members now see only Meetings, Chats, and Settings. Backup & Restore and Calendar options have been moved into Settings. ## Improved - **Calendar sync reliability** — Scheduled meetings now mirror your calendar exactly. Past and canceled events move to Recent, sync status updates live across devices without reloads, and sync pulls are no longer all-or-nothing. - **Meetings list interface** — The web meetings list shows accurate titles, per-row agendas, and hides secondary actions behind a "⋯" menu for a cleaner layout. - **Sidebar navigation** — Reorganized navigation into two groups, renamed Organization to Billing, and display your active languages in the account card. - **Translation language access** — Moved the translation language selector directly into the web meeting cockpit's "More" menu for easier access during calls. - **Channel invite notifications** — You now receive in-app and push notifications when invited to a channel, with invite actions unified into a single, clearer drawer. - **Onboarding and login** — The "Get started" checklist is expanded by default and auto-checks items, while email login errors are now fully localized. - **App update indicator** — Replaced disruptive update toasts with a passive dot on your avatar that prompts you to reload when a new version is ready. - **Mobile laser pointer** — Smoothed the fading effect of the laser pointer for a more natural drawing experience. ## Fixed - **Audio translation after language change** — Translated audio now resumes correctly if you change your own language mid-meeting. - **Device selection resets** — Microphone, camera, and speaker choices no longer revert to defaults unexpectedly. - **Meeting finalization failures** — Lost close events or digest failures no longer leave meetings permanently stuck without a final summary. - **Mobile Join screen keyboard overlap** — The join form is no longer covered by the on-screen keyboard on mobile devices. - **Calendar OAuth popups** — Fixed an issue where the calendar connection popup failed to open correctly in Safari and Firefox. - **Guest join errors** — Guests joining a non-existent meeting now see a "Meeting not found" message instead of an infinite waiting screen, and post-approval joins have a retry screen. - **Security hardening** — Fixes from our ongoing security review. # Message forwarding, recap BCC, Telegram routing, Chrome extension, mobile translator This release adds message forwarding between chats, recap BCC recipients for CRM delivery, a Chrome side-panel extension, a dedicated mobile translator app, and Telegram routing — alongside faster channel opening, a recap picker redesign, and reliability fixes across the translation engine and mobile apps. ## New **Forward messages between chats** — Forward messages from one channel to another. A staging draft appears over the target chat's input so you can add a comment before sending. Recap documents forward as links; their read access stays controlled by the original meeting. **Recap BCC recipients** — Send meeting summaries to any CRM or tracker via incoming email with no integrations. Add up to 10 addresses per host; new addresses must be confirmed via a test email before BCC is sent. Addresses can apply to all your meetings or to a specific channel or meeting. **Android share sheet** — Share text and files into InterMIND from any Android app. Files up to 25 MB each are sent as individual messages to your Inbox or a chosen channel. **Telegram routing** — Incoming Telegram messages route to InterMIND channels: group messages go to the channel with the matching name, and messages from a linked personal account go to channels by binding. Name matching is exact and case-insensitive; ambiguous names go to your Inbox. **Mobile translator app** — A dedicated app for person-to-person translation. Languages auto-detect from greetings, audio is buffered so translation doesn't interrupt the speaker, and direction follows the speaker. **Chrome side-panel extension** — InterMIND opens as a Chrome side panel with login handoff, a meetings hub, and a screen-share picker. The panel preserves your theme, locale, and preferences across sessions. **Public status dashboard** — Real-time service status is available at status.intermind.com, covering application, realtime channel, translation engine, and authentication. **Screen scroll and zoom on shared tabs** — When a participant shares a browser tab, anyone can scroll and zoom the shared content with their mouse wheel. **Stage sync and Present button** — The presenter's main-area share now follows to everyone automatically. An explicit "Present to everyone" button replaces the previous implicit click-to-sync. Shared recap on stage renders the full session shell with both tabs; timestamps open the transcript in place. **Android screen share** — Share your screen from the Android app during a meeting using Android's screen-capture permission. **Meeting countdown** — Upcoming meetings show "In N min · 15:00" starting 30 minutes before start, with a live ticker that updates without a page refresh. **Drag-and-drop files** — Drop files anywhere on the app window to upload them to a chat. A collapsed sidebar opens automatically during the drag and closes after. **Drag-select and bulk delete messages** — Select multiple chat messages by dragging with the mouse, then delete them together. Selection locks are visible and explained inline. ## Improved **Chat channel opening speed** — Channels now open in about 0.9 s instead of 2.5–4 s. **Chat roster and contact field** — Channel rosters show the host first, then participants alphabetically — matching the meetings hub. The shared contact picker gains a one-click "clear all" button, two-line name + email entries, and a search icon that hides when recipients are selected. **Meetings hub** — A split "New meeting | calendar" button lets you create and join instantly or schedule without entering. Join by link or ID from the search field. The web hub on mobile no longer shows a redundant title bar. **Mobile settings and SSO** — Settings use inset card grouping with a dedicated Profile sub-screen for name editing and account deletion. SSO login no longer shows a second dialog. **Mobile translation** — Several fixes across platforms: | Fix | What changed | | --------------------------------- | ------------------------------------------------------------------------------- | | Both directions | Translation works in both directions; the speaker's language follows the speech | | Single-language silence | Original audio is muted only when participant languages differ | | Pool exhaustion | When the host's translation pool is exhausted, the phone hears the original | | Settings not reaching conferences | Translation language set in Settings now reaches conferences | | Overwrite by original | Translated text no longer gets overwritten by the original message | **Translation engine** — Engine timeouts are now terminal: no retry duplicates, and the translator job is deleted to free GPU. Completed translation phrases stream to chat as they arrive. **Recap picker and confirmation** — The recap address picker uses the same chip grammar as the contact field: chips live inside the input, paste adds multiple addresses at once, and status is shown by chip color. A counter in the channel menu shows how many addresses are attached. Confirmation from the email redirects into the app with a success toast — no dead-end page. **Recap cleanup** — Empty recaps without a summary no longer spam chat and email. Links expire when their surface is hidden, archived, or deleted. The session rail is restored for channel recap pages. **Conference UI** — Video tiles show a large centered avatar when the camera is off. Toasts follow a consistent spec with the requester's real avatar on knock notifications. A close button is added to the live subtitles field. **Onboarding empty states** — Empty pages across the app now show getting-started steps, documentation links, and live translation previews. **Benchmark page** — A quarterly picker in the hero switches the entire page, with comparison deltas against the previous quarter. **Pricing and billing** — Paddle checkout and portal are live as merchant of record. Prices reflect your region in local currency with PPP adjustments. **Downloads page** — Reframed around two paths: browser for guests and one-off meetings, desktop and mobile apps for daily channel users. **Browser extension polish** — The "tabs" permission is removed (it triggered an unnecessary "Read your browsing history" warning). Icons use transparent alpha. The panel opens the meetings hub for logged-in users. **Accessibility** — Read-receipts and star-rating containers now have proper role="img" and aria-labels. ## Fixed **Security hardening** — Fixes from our ongoing security review. **Lost first click after deploy** — The first navigation click after a new deployment no longer reloads the current page instead of the target. **Database overload from stale assets** — Stale asset requests after deploy no longer exhaust the database connection pool; they return a cheap 404 without database access. **Mobile rejoin unmute** — Rejoining a meeting no longer unmutes the microphone when the UI shows it as muted. **Android screen resize crash** — A deadlock triggered by screen rotation during a call is fixed (upstream SDK patch adopted, vendor workaround removed). **Microsoft calendar sync** — Push subscriptions for Microsoft calendars now create correctly (the TTL was just above the Graph API ceiling). **Demo transcription** — Mind ASR on the demo path is re-enabled; it had been silent since early July. # AI document summaries in chat, email-in channels, macOS Share Extension This week we shipped AI document summaries in chat, email-in to chat channels, a macOS Share Extension, and a new Trust Center page. We also refined the chat sidebar and conference settings, and resolved several call-reliability, translation-timing, and recap issues. ## New **AI document summaries in chat** — When you attach a document in chat, text is extracted on your device and an AI summary appears on the file card. Tapping a file opens the summary first, with document preview one step behind. Meeting recaps now incorporate all chat content, not just transcripts. Available on web and mobile. **Email-in to chat channels** — Each chat channel now has a unique `@in.intermind.com` address. Emails sent there land in the channel's Inbox with attachments intact; signatures and quoted reply tails are stripped automatically. **macOS Share Extension** — InterMIND now appears in the macOS system Share menu, so you can share files directly into the app from Finder or other applications. **Chat scroll hotkeys** — Use ↑/↓ to move by row, PageUp/PageDown by screen, and Home/End to jump to the top or bottom of chat history. **Inbox pin banner for Telegram** — Messages from unpinned Telegram groups now show a banner in Inbox with a direct pin action, so you can route them to the right channel without hunting through context menus. **Usage limit email alerts** — You now receive email notifications when you approach storage limits (triggered by recording events) and translation-minute limits (first occurrence). **Trust Center page** — A new /trust page consolidates verified data-residency facts and displays the CSA STAR Level One badge. ## Improved **Chat sidebar** — The collapsed sidebar now shows chat avatars with per-chat unread badges instead of an empty rail. Separators between rows were removed for cleaner spacing, and active-chat highlighting was refined. **Navigation** — The Resources menu was reordered by intent: high-value actions first, then help, then content and proof, with diagnostics last. Trust Center was added to the header dropdown and footer. **Conference settings** — The invite block moved from Settings to the Participants panel. Settings now collapses by content, and network statistics are available in the Devices section. **Empty states** — /meetings, /chats, and Inbox now share a unified empty-state composition with consistent layout and messaging. **Desktop app entry** — The desktop app opens directly to the login screen instead of the marketing site, so it feels like an application rather than a browser wrapper. **New account theme** — New accounts start with System theme instead of defaulting to Dark. **Mobile sign-in** — Removed a custom consent alert and switched to native Sign in with Apple for App Store compliance. ## Fixed **Mid-call device recovery** — Switching your camera or microphone mid-call no longer leaves the call without audio or video. The engine now reacquires devices from the live registry with retries. **Mic button reliability** — The mic button no longer shows false desync indicators during designed mute states such as idle-away, host-mute, or unmute restriction. **AI Help responses** — AI Help no longer stalls for several seconds or cuts off mid-sentence. The underlying model was silently consuming the output budget on reasoning tokens. **Live message delivery to open chats** — Messages sent via Telegram, email-in, and mobile REST now arrive live in open chats instead of appearing only on refresh. **Closed-chat translation timing** — Sidebar previews of closed chats now show translated text immediately after ingestion instead of remaining on the original language. **Chat-only meeting recap** — Meeting recaps for chat-only sessions with no transcript are no longer dropped by the schema. All timestamp fields are now optional. **Multi-file document extraction** — Uploading multiple documents at once now processes all files correctly. Grouped file cards were missing the extraction pipeline. **Chat attachment size enforcement** — Uploads are capped at 25 MB with server-side signed verification. Quota now counts true file sizes instead of relying on client-reported values. **Voice language detection** — Gaps in the ASR language cache were closed. Unsupported language codes no longer reach the translation engine. **Email verification rate limiting** — After 10 failed verification attempts, email verification is rate-limited for 15 minutes. **Content and contact accuracy** — PDF links in site content no longer 404 due to router interception. Stale FAQ entries were swept, two incorrect factual claims corrected, and the privacy contact address updated to . **Telegram connection feedback** — Connecting a Telegram bot when the binding is already in use now shows a clear message instead of silently failing. **Export accuracy** — An empty auto-created Inbox no longer makes an empty account appear to have exportable content. **Security hardening** — Fixes from our ongoing security review. # InterMIND iOS app lands in the App Store, plus major updates to the demo experience This week brings the InterMIND iOS app to the App Store and the browser extension to the Chrome Web Store. We also significantly upgraded the demo experience with a realtime conversational AI and video avatar, alongside fixes for mobile landscape layouts, meeting chat, and recap recipients. ## New - **InterMIND iOS app** — Version 1.0 is now live and available for download from the App Store. - **Chrome browser extension** — The InterMIND side-panel extension is now published and available in the Chrome Web Store. - **Live AI demo companion** — The demo experience now features a realtime speech-to-speech AI named Mia, complete with a live video avatar, replacing the previous recorded samples. - **Conversational barge-in** — You can now interrupt the AI demo companion naturally while it is speaking, and it will pause and respond without cutting off your audio. - **Recap contact integration** — You can now select recap recipients directly from your contact list when sending meeting summaries. - **Network statistics for all** — The in-meeting network statistics panel is now available to all participants, not just moderators. ## Improved - **Demo language memory** — The AI demo companion now remembers the language of your last spoken phrase and continues the conversation in that language until you switch. - **Mobile landscape mode** — Android and iOS apps now support landscape orientation for meetings, with an improved participant grid and side rail that maximizes stage height. - **Meeting device menu** — Audio and video device selections have been moved into a cleaner submenu within the in-call interface. - **Fact-based demo answers** — The AI demo companion can now answer pricing and competitor comparison questions using verified product facts rather than generating responses. ## Fixed - **Chat paragraph translation** — Translated chat messages no longer incorrectly merge separate paragraphs into a single block of text. - **Telegram channel pinning** — Pinning a chat to a Telegram channel no longer displays archived channels or technical IDs in the selection menu. - **iOS earpiece audio** — In-meeting audio on iOS now correctly routes to the earpiece instead of the loudspeaker. - **Meeting tile loading** — Participant tiles no longer display incorrect placeholder initials while loading user names. - **Microsoft token refresh** — Resolved an issue where Microsoft Calendar and OneDrive integrations would fail to refresh their connection tokens. - **Billing currency and checkout** — Local currency is now displayed correctly next to yearly pricing, and a checkout error preventing buyer email prefill has been resolved. - **Account deletion data cleanup** — Avatar and imported file data are now fully purged from backend storage when an account is deleted. - **Security hardening** — Fixes from our ongoing security review. # Desktop auto-update, iOS share sheet, and Arabic meeting language withdrawn This week ships a desktop auto-updater with a visible version number, an iOS share extension for sending content into InterMIND, and a pre-join prompt to open meetings in the desktop app. Arabic is withdrawn as a meeting language while it remains below our quality bar. Several recap, chat, demo, privacy, and mobile fixes improve reliability. ## New - **Desktop auto-update** — The desktop app now checks for updates on launch and every 6 hours, shows the current version in its menu, and notifies you with a single "click to restart" prompt when a new version is ready. Manual update checks always respond with a dialog. - **iOS Share Extension** — You can now share text, links, images, videos, and files into InterMIND directly from the iOS share sheet, without switching apps first. - **Pre-join desktop app offer** — When you open a meeting link in a Mac or Windows browser, the pre-join screen shows an "Open in desktop app" button next to Join. The page never auto-navigates away — if the app isn't installed, you can still join in the browser or download it. ## Improved - **Meeting link sharing** — The meeting room now has two clear buttons — **Copy link** and **Share link** — replacing the previous "Copy Link" plus a long, unreadable Meeting ID string. Copy link always works in one click; Share link uses your browser's native share sheet where available. - **Security page documentation** — The /security page now explicitly documents media encryption (WebRTC DTLS-SRTP to our engine in France), at-rest encryption (Neon AES-256, Tigris SSE), and why end-to-end encryption isn't available (translation requires processing on our engine). ## Fixed - **Arabic meeting language** — Arabic has been withdrawn from voice and chat translation after sustained degradation below our quality bar. The Arabic website remains available; Arabic stays in our weekly benchmark and will return when it meets the threshold. - **Recap reliability** — Three fixes: the recap address picker no longer goes unresponsive before the page fully loads, the first version of a recap now shows full text instead of only a diff, and recaps with a language tag that doesn't match their text are regenerated rather than shown untranslated. - **Unread badge with recap documents** — The unread message badge no longer stays stuck on when the last message in a chat is a recap document. - **Demo companion behavior** — Mia no longer switches to Ukrainian on a misdetected language tag from Russian speech, and no longer goes silent when the avatar is active. - **iOS Universal Links** — Meeting invite links now open the iOS app directly instead of falling back to Safari. A team-ID mismatch in the app association file silently disabled the feature. - **Inbound email translation** — Inbound emails are now attributed to the external sender and translated into the reader's language, instead of being treated as the host's own messages and left untranslated. - **Mobile share and upload** — The mobile share screen now shows upload progress, guards against accidental navigation away during upload, and displays readable error messages. - **Privacy: account deletion and exports** — Account deletion and expired data exports now permanently remove data from storage rather than marking it as hidden. Storage snapshots are purged by version ID. - **Pricing label truncation** — "per user/month" and "paid yearly" labels no longer get cut off next to longer localized prices (e.g. BRL). - **Partner page claims** — Removed white-label promises from the partner page. The interface, meeting links, and recap emails carry the InterMIND name; everything beyond that is per contract. - **Directory picker fields** — The participant picker now shows job title and department; dead legacy fields have been removed. - **Security hardening** — Fixes from our ongoing security review. # Mia joins your meetings, voice notes, and a live whiteboard This week introduces Mia as an active participant in your meetings, voice notes in team chats, and a collaborative whiteboard. We also shipped a public API with an MCP connector, desktop passkey support, and a test room for pre-meeting checks. ## New - **Mia as a meeting participant** — Mia now joins your meetings as an agentic participant. Hosts and moderators can command her directly, she proactively posts relevant notes to the chat, and licensed participants of paid plans can ask her questions by voice or in the private mode of the meeting chat. Asked aloud, she answers aloud in each participant's translation language. *Update, 19 September 2026: Mia in meetings went back to preview — she is tested inside InterMIND and is not switched on for customer organizations until the preview ends.* - **Voice notes in chat** — You can now record and send voice messages in team channels and meeting chats. Transcripts are automatically generated and translated into each reader's language. - **Live whiteboard** — A real-time whiteboard is available in meetings on paid plans. All participants can draw simultaneously, and the scene is saved for anyone who joins late. - **Public API and MCP connector** — You can now connect AI assistants like Claude, ChatGPT, and Copilot to InterMIND via the Model Context Protocol. The connector lets your assistant schedule meetings, search recaps, read channels, and list documents using your own API keys. - **Desktop passkey login** — The desktop app now uses your system browser for login. This allows you to use passkeys and saved identity provider sessions for a faster, more secure sign-in. - **Meeting test room** — You can now test your camera, microphone, speakers, screen sharing, and network in a dedicated test room before joining a meeting. - **Host transfer in live calls** — Hosts and team admins can transfer the host role to another licensed team member during an active meeting without anyone needing to rejoin. - **Presenter modes for screen sharing** — When sharing your screen, you can now choose between different presenter layouts, similar to standard video conferencing tools. - **Browser extension for Edge** — The InterMIND browser extension is now available in the Edge Add-ons store, letting you see the call while presenting in Microsoft Edge. ## Improved - **Chat interface on mobile** — The in-meeting chat is now a layer over the video stage on mobile devices, letting you view messages and the call simultaneously. The chat composer also matches the mobile web layout. - **Landing page experience** — The homepage now features a live room preview with Mia. First-time visitors can start a conversation directly, and returning users see the full landing page. - **Onboarding checklist** — The setup checklist now includes steps for adding your name and recording a voice sample for translation in your own voice. - **Product emails** — All transactional emails, including onboarding nudges and recap notifications, are now sent in your chosen translation language. - **Mobile landscape layout** — The meeting cockpit moves to a vertical rail on the right side of the screen when viewing in landscape on touch devices, keeping controls accessible. ## Fixed - **Desktop notifications** — Clicking a new message notification on the desktop app now opens the correct channel instead of just focusing the main window. - **Meeting loading** — Replaced multiple loading indicators with a single full-screen loader from the moment you open a meeting until the participant grid appears. - **Expired demo sessions** — Demo rooms no longer mount a broken meeting interface when the session token expires, preventing error loops. - **Mobile chat button visibility** — Icon-only buttons in the mobile web app now maintain correct sizing and spacing, preventing layout overflow on small screens. - **Whiteboard sharing** — Images uploaded to the whiteboard now sync correctly for all participants, and the laser pointer works across all viewers. - **iOS demo audio** — Resolved an issue on iOS where a single tap was insufficient to start audio, requiring a double tap to hear Mia. - **Avatar initials** — User avatars now correctly display initials for names containing emojis or complex characters, preventing room crashes. - **Polling on expired tokens** — The app now stops polling for participant data after repeated authentication failures, preventing infinite loading loops. - **Security hardening — fixes from our ongoing security review.** # InterMIND for Slack, Fair Billing, private chat, and Mia upgrades This week shipped the InterMIND app for Slack, Fair Billing based on active members, and a private mode for Mia conversations inside meeting chat. Mia also gained web search, threads outside meetings, and answers that follow your question's channel — voice questions get voice answers, chat questions get private replies. We added compare pages for four competitors, an iOS translator build, and Amazon Bedrock as a third AI gateway. ## New - **InterMIND for Slack** — `/intermind` in Slack creates a meeting from your linked account and posts the join link in the channel; recaps return in the message thread or a channel you choose. Connect your workspace in Settings; the public `/slack` page documents every command and permission. - **Mia web search and off-meeting threads** — Mia can search the web to answer questions about current information; org admins can toggle this in Settings. You can also ask Mia in a thread from `/chats` without starting a meeting — answers stream back in the same thread. - **Private Mia conversations in meetings** — A lock button in the composer opens a dark panel for a private thread with Mia, stored per room and per user. Chat questions get private replies visible only to you; voice questions get voice answers to everyone. Address Mia through the private composer mode; no prefix is needed. - **Cross-device draft sync** — Unsent text, reply targets, and attachments sync across your devices. Start typing on desktop, switch to mobile, and your draft is there. - **Fair Billing** — You're billed for active members, not licenses. Activity means joining a meeting, sending a message, or asking Mia within 28 days. You receive an email three days before renewal showing who is active. - **Security: live sessions and admin controls** — Settings shows your live sessions with device and login location; end any single session or all others at once. In `/admin/users`, email addresses are masked by default and admins can end all of a user's sessions in one action — both audited. - **Slack export import** — Upload a standard Slack export and it converts to an InterMIND archive: channels, threads in chronology, reactions, and pins all map across. - **iOS translator app** — The InterMIND translator is now available on iOS via TestFlight, alongside the existing Android build. - **Amazon Bedrock as AI gateway** — Organizations can choose Amazon Bedrock (Frankfurt) as their account brain, alongside Azure OpenAI EU Data Zone and Vertex AI EU. ## Improved - **Mia conversation and access** — In one-on-one meetings, Mia responds without needing her name. In groups, each answer extends the dialogue and closes after a pause. Mia is now available to licensed participants on paid plans — the right belongs to each participant, not just the host. - **Meeting room layout** — Presenter mode reverts to Content-only at viewers when the presenter turns off their camera. On portrait phones, participant tiles sit in a horizontal strip above shared content instead of overlapping it. Pinning a tile in a collapsed sidebar no longer expands the filmstrip. - **Chat list is push-based** — The chat sidebar updates in real time via a push channel; the 10-second polling refresh is gone on both web and mobile. - **Desktop app** — After restart, the shell reopens on your last page with the same window size and position. The web layer reloads silently during idle so updates apply without prompts. Desktop releases now happen weekly instead of on every deploy. - **Translation engine split** — Chat and shared notes translate through Azure AI Translator (dedicated EU endpoint). Voice-note transcription runs on Azure AI Speech. Documents go through your organization's AI gateway. - **Knowledge search** — Hybrid search (keyword + vector) with an HNSW index improves recap and Mia search speed and relevance for larger accounts. - **Website pages** — New compare pages: head-to-head pages for Slack, Mattermost, Rocket.Chat, and Element, plus Slack vs Microsoft Teams with InterMIND as a third column. Each page includes a "Where the data lives" row. Feature pages now play their own use-case videos instead of a generic promo. Pricing card items open a popover instead of navigating away. The footer's compare column is now "Alternatives" with guides and a link to all comparisons. - **MCP tools** — `search_recaps` matches word forms, so "pricing" finds "pricing and timeline." `list_recaps` works for both hosts and participants. - **Telegram group mirror** — A connected Telegram group now follows your current Telegram account, not a snapshot from when the bot was added. ## Fixed - **"Failed to start demo"** — A read-only database flag leaked through the connection pooler and broke the homepage demo, calendar sync, and inbound mail. - **Messages lost during server restart** — A message sent in the seconds a meeting server was draining could disappear silently. The client now waits for server confirmation before showing success. - **OAuth popups losing connection** — Popups for Copilot, Teams, and calendar integrations no longer lose their link to the InterMIND window on certain browsers. - **Desktop silent reload loop** — A stale cached response caused the desktop shell to reload every 2–5 seconds. - **Duplicate API keys on re-authorization** — Re-authorizing the same MCP client (ChatGPT, Claude, Copilot) replaces the existing key instead of adding a duplicate. - **Two-phrase voice command to Mia** — "Mia, note the decision. We go with vendor B." no longer loses the second sentence to a pause gap between phrases. - **Chat sidebar and website rendering** — File-message previews in the channel sidebar no longer show raw storage URLs; sidebar headers, alignment, and search-field styling are cleaned up. The pricing page no longer scrolls horizontally on 360px viewports. Localized blog cover images load correctly after a redirect fix. The admin users page no longer returns a 500 on load. - **Security hardening** — Fixes from our ongoing security review. # Card-free Pro trial, undo send in chat, and Samsung and Huawei app stores This period you can try Pro for 14 days without a card, and recaps now carry open action items into the next session. Chat gains undo send, a resizable sidebar and a jump-to-latest button on phones, and the Android app is listed in two more stores. Joining as a guest on a phone and the pre-join screen are simpler, and a long list of fixes covers mobile, desktop, recaps and billing. ## New - **Pro trial without a card** — The Pro button on /pricing starts 14 days of Pro with no card form. When you reach a free-plan limit on your own account, the trial is offered right there, and you get emails 3 days before the trial ends and on its last day. Without a card, the account returns to Basic when the trial ends. - **Open action items carried over** — A room's next recap opens with a "Carried over" section listing the previous session's open action items. Items the transcript shows as done are closed, and Mia names the open ones in her opening note. - **Task statuses in recaps** — Action items show as to do, done, or not done with a reason. Status chips carry icons and labels in the reader's language, and each room shows totals for the last 30 days and for all time. - **Undo send in the meeting chat** — Messages sent in the meeting chat wait 5 seconds before delivery, so you can take them back, as in Gmail. The same release adds a personal-message check. - **Meeting rating on exit** — Hosts and guests, on the web and in the mobile apps, can rate a meeting 👍 or 👎, with one-tap reasons after 👎. The screen is not shown on every exit: it appears in your first 3 meetings with other people, then only after a detected problem or at most once every 7 days. Two unanswered prompts in a row pause it for 30 days. - **Notices when translation changes under you** — If participants' languages diverge while your own translation is off, you see a "Translation is off for you" notice with an "Enable translation" button. If everyone in the room ends up on the same language, everyone sees "Translation paused: everyone here is set to :language[".] - **Resizable chat list** — Drag the right edge of the chat sidebar to resize it. At minimum width it collapses into a rail, a click on the border toggles it, and the rail shows a magnifier instead of an expand button. - **Jump to the latest on phones** — A button over the message list takes you to the end of the chat, in both the web and native phone chat. - **Hub settings follow you across devices** — Pinned and hidden meetings in the hub, subtitle and translation on/off, and meeting aliases are now stored with your account. They stay the same on web, desktop and mobile, and other signed-in devices update when you change them. - **Read state shared between devices** — Reading a chat on any device clears its push notifications on mobile and closes its tray notifications on desktop. The mobile badge follows the unread count kept on the server. - **Billing period history** — /billing now lists your paid billing periods. The pre-renewal email links to that page and names the members who will be billed, not only the inactive ones. - **Sign in with Apple "Hide My Email" no longer creates a second account** — The first time you sign in through Apple's relay address, the Apple ID is linked to your existing account. The Apple button now sits last in the list. - **One integrations page** — Personal connections moved from Settings to a single /integrations page. Admins also get a Team block there, split by plan. - **Samsung Galaxy Store and Huawei AppGallery** — The Android app is now listed in Samsung Galaxy Store and Huawei AppGallery, and Huawei phones are pointed to AppGallery instead of Google Play. The Galaxy Store version is updated roughly once a quarter, so Samsung users who want the newest version should use Google Play. - **Phone browser hands off to the app** — On a smartphone the web is for guests. /login, the cabinet and invite links open the app in one tap, and the store opens only if the app isn't installed. The meeting page has no app button of its own, because your browser offers the app itself. The phone join screen asks for camera and microphone when you tap Join, shows a "signed in as" line for accounts, and its language list has no search field. - **One-screen pre-join** — The four-step setup wizard is replaced by one screen with camera, microphone and speaker test cards in a scrollable window. Join waits for your browser's camera and microphone permission. If you dismissed the permission prompt earlier, it asks again in place instead of sending you to the address bar. - **Guests stay on the meeting page** — A guest opening a link is asked for name and language on the meeting page itself. After leaving, a guest sees a "You left" screen with "Knock again". A dropped connection gets a 60-second grace period, and an approval given during the gap is applied when the guest returns. - **Clearer waiting screen for closed meetings and channels** — Knocking on a closed channel no longer looks like a hang. The waiting screen names the closed channel, says the host has been notified, counts down 5 minutes, shows the account you are using, and lets you knock again. - **Private Mia chat on mobile** — The mobile app now has the private mode of the meeting chat with Mia. ## Improved - **More interface languages** — The interface is available in Hebrew, Thai, Hindi, Bengali, Czech, Kazakh, Urdu and Greek. Docs, blog, changelog and covers are in Thai, Hebrew, Hindi and Bengali. - **One door to Mia** — The right panel (⌘/) is now Mia when you are signed in, and the "Mia" row is gone from /chats. The lock on a channel reads "Ask Mia about this channel". - **Mia can read PDFs from links** — When answering, Mia can open a linked PDF up to 1 MB. - **Demo with Mia** — The demo shows a collapsed sidebar of video tiles instead of a small overlay covering Mia's face, and one button now answers voice with voice and text with text. - **Benchmark page** — The "Test the translation" button opens a two-panel demo you can try yourself. The data table expander is now a visible card with an outlined button, and the page ends with five host questions, starting with why the index doesn't rise all the time. - **Subtitle panel close button** — The close button is a solid dark circle on the panel corner, with a light ring and white cross on hover. - **Recap email in each group's language** — The summary in the recap email is written in the language of each language group. - **Voice sample card** — After you save a voice sample, the card hides the saved state behind a "Record again" button. - **Desktop recap and transcript** — A recap or transcript opens in its own window, and the menu has a History item, so you no longer close the app to leave a document. - **iOS sign-in** — Google and Microsoft sign-in and calendar connection open in a private browser session, so the iOS prompt asking to use intermind.com to sign in should no longer appear. You enter your provider account each time. - **Sign-out takes effect right away** — When a session is revoked, the web and mobile apps now sign out immediately. - **Invite-a-guest reminder** — The reminder shows only to the host when they are alone in the room, once per meeting in the browser. - **Sidebar link** — The "Downloads" item is now "Get apps and extensions" and links to /connect. - **Guest name screen in the app** — The form sits at the top above the keyboard, without a card, duplicate heading or Back button. - **Help center** — New screenshots on the chat translation, files, document translation, document summaries, More menu, subtitles and transcript pages, and more. Screen sharing has a short video about presenting to everyone, and the whiteboard has its own docs page and features page. ## Fixed - **Promo discount matched to checkout** — The −50% offer on /pricing is now one rule for pricing and Checkout: it applies to your first payment. People with an expired trial no longer see −50% and then get the full price. - **Checkout keeps your language** — Returning from Stripe or Paddle Checkout or from sign-in no longer switches you back to the English pricing page. - **Android 10–11 links** — The app no longer takes over all intermind.com links on these versions, so Google and Microsoft sign-in works again. - **Connect buttons for integrations** — Closing the authorization window frees the Connect button after 1.5 seconds instead of 5 minutes, and cancelling the dialog is no longer reported as a connection error. - **Desktop Connect** — Connecting an integration in the desktop app no longer hangs on "Completing authorization…". - **Phone back in meeting controls** — Mia's voice replies, host mute, permission sync and the laser pointer reach the mobile app again. - **"End for all" from a phone** — It ends the meeting again, so the recap is produced and Mia stops posting. The recap title in the compact feed is shown in the reader's language. - **Mobile sign-in lasting only a week** — Mobile sessions are now renewed, so you are not signed out every 7 days. - **Older iOS builds** — Old app versions are no longer signed out right after login. - **Chat history after a network drop** — History that failed to load on a network drop is requested again when the connection returns. - **Wrong translation shown to readers** — When no version exists in your language, you see the author's original instead of someone else's translation. - **Recap email recipients** — The recap email goes to the meeting's participants, not to the whole room. - **Mixed-language emails** — A product email is now entirely in your language or entirely in English. - **Text typed before the page finished loading** — The guest name on the join page and the email on /login are no longer erased. - **Guest language after rejoin** — A guest's in-meeting language choice now survives rejoining. - **Accepted guests** — An accepted guest no longer gets a 403 from the participants list. - **Host hears knocks earlier** — The host is notified of a knock from the moment the meeting page opens, and the push goes to moderators and the host's team. - **Leave and Cancel while waiting** — "Leave" while waiting for approval acts immediately, and "Cancel" and "Go back" in the app now work from a cold deep link. - **Dead microphone** — A microphone that died while its button showed "on" is captured again. - **Mia's answers** — An interrupted answer from Mia is no longer cut off by the tail of her own question. - **Voice sample "Too short"** — Recording a voice sample no longer shows "Too short" while every number lights up, and the English sample now counts "ten" even when it is transcribed as "Then". - **Desktop notifications in a burst** — Desktop notifications no longer arrive all at once after a window reload. - **Message selection** — Escape no longer clears your selection while a message's context menu is open. - **Notes AI suggestions for guests** — AI suggestions in notes work again for meeting guests. - **Stale profile after team changes** — After leaving a team on /pricing, or accepting an invite on /invite, your profile is read fresh from the server. - **First sign-up with Google or Microsoft** — New accounts no longer hit a run of authorization errors on first load. - **Directory invites** — Members added from the directory now get real pending invites. - **Profile name in sessions** — People appear under the name in their profile instead of the name the session was opened with. - **Security hardening** — Fixes from our ongoing security review. # Meeting links open in the app after install, plus a faster pre-join dialog This week, opening a meeting link on your phone takes you straight into the InterMIND app, including right after you install it. The pre-join dialog is quicker, and the docs are easier to navigate. We also fixed a docs loading problem and a few smaller issues. ## New - **Meeting links open in the app after install** — When you open a meeting link on your phone, the link now hands off to the InterMIND app. If you had to install the app first, the link opens in it automatically once it launches, on Android, iPhone and Huawei. ## Improved - **Faster pre-join dialog** — The pre-join dialog now appears right away and responds immediately. It is also a single column, without the test-room cards. - **Easier docs navigation** — Docs section pages are now linked from the sidebar, and every docs page shows a breadcrumb trail. Blog, docs and changelog entries also link to related reading. - **More site languages** — Czech, Kazakh, Urdu and Greek now have translated site content. The Benchmark page is fully localized. ## Fixed - **Docs pages failing to load** — Some docs pages and blog posts returned an error when opened directly. They now load normally. - **Host waiting screen in the mobile app** — The waiting-for-host card now follows your current theme. It has one exit button instead of two. - **Links keep your language** — Links in blog and changelog pages, and in the header and footer for some languages, now stay in the language you are reading. # Team status pages, colleagues at sign-up and a redesigned channels sidebar This week adds team status pages built from your meetings and shows open tasks in the next recap, where members can give a verdict on each one. Channels get a new sidebar on desktop and phone, and the pre-join screen has been redesigned. Many smaller fixes landed across the mobile app, calendar and chat. ## New - **Team status pages** — Facts your organization's meetings stated (tasks, problems, money at stake, requests by cohort) are collected from recaps into team pages, each fact with a verbatim quote. There is a new Overview page and a Team pages card, and AI assistants connected over MCP can read the pages with the new `list_team_pages` and `read_team_page` tools. A call made through an assistant counts as activity for that member. - **Open tasks carried into the next recap** — Your organization's open tasks carry into the next recap, judged from what was said in the meeting. Members can give a verdict on a task right from the recap, and tasks are now included in the `recap.ready` webhook. - **Colleagues when a team is created** — When a team is created, the payer sees which people from the company's email domain are already here and can invite them by name. A newcomer whose colleague already runs a team can ask to join it instead of starting a second subscription. - **Add a channel to your calendar** — The channel menu now has "Add to calendar", so a channel can be scheduled on your Google or Microsoft calendar. - **Phone opens the app, computer opens the pre-join** — Links opened on a phone take you straight to the app. A guest on a computer lands on the pre-join screen, where the name is asked. - **Resizable Mia panel** — On desktop you can drag the edge of the Mia panel (⌘/) to resize it, up to half of the content area. A collapsed panel leaves a labelled tab at the right edge that opens on click or drag. ## Improved - **Channels sidebar on desktop** — The header now has one search field and a "New" menu, and a "Today" block at the top lists the day's meetings with the event description and time. Right-click a Today row for "Open in calendar" and "Participant permissions". The "+" menu starts with the channel options: new channel, schedule, link and start now. The sidebar can't be narrowed below phone width, and the /meetings page is still available. - **Channels tab on phone** — The tab follows the desktop sidebar: one search field that only finds channels, a "New" menu that works step by step, and a "Today" block. "Start now" and "Schedule" offer your recent renamed rooms, and an unnamed room shows as "New meeting". - **Chat feed** — Your messages sit on the right and others' on the left, grouped in series with day separators and unread markers. Each message has a single hover button in its top-right corner, and the "jump to latest" button sits in the bottom-right corner. - **Pre-join screen** — The layout is now two columns, with the camera preview on the left and a room bar over the video. Camera and microphone buttons open a device menu, a Language button shows your language (or a highlighted "Translation off"), and the menu offers "Give Feedback". "Check camera and sound" opens in the same tab, with a "Back to meeting" button on the test page. - **Language button in the room** — The language button on the room bar now sits to the right of the microphone, as on the pre-join screen. It shows the short name, for example "Portuguese". - **Longer meetings on Basic** — The meeting length limit on Basic goes from 60 minutes to 24 hours. The upsell at the time limit is removed, and the cooldown screen states the cap in hours. - **Invite field badges** — The three groups of people in the invite field now carry badges, so it is clear who you are adding. - **Calendar sync details** — A meeting link is now found in the event's location as well as its title. The first manual sync no longer waits on existing rows, and the avatars of the host and invitees show in the Today row before the first call. - **Mia's documentation search** — Mia now ignores filler words, prefers help docs over blog posts, and returns at most two sections per page. ## Fixed - **Scheduled room stays scheduled** — Joining a scheduled meeting no longer removes its room from the schedule. - **Removed members' sidebar** — A member removed from a chat now loses it from their sidebar right away. - **Browser page translation** — Browsers no longer offer to translate the app's own screens, which could garble the interface. - **Cyrillic names on video tiles** — On mobile, a name with Cyrillic letters no longer shows as garbage on the video tile. - **Billing and Integrations from the mobile app** — These now open in the browser instead of sending you back into the app. - **Mobile polish** — The join screen is dark without the native header. The chat name comes from the meeting record, and the host can rename it from the gear icon. The search icon no longer has a square behind it, "Back" looks the same on every screen, and text and button rows in Settings and Integrations line up as in Directory. - **Google Workspace Studio step** — The "Create an InterMIND meeting" step no longer fails in Flows when the title is left empty. - **Desktop window recovery** — The desktop app now reloads a window whose renderer crashed, failed to load or hung. - **Chat sender without an account** — A sender without an account no longer receives a viewer's profile, and an image that fails to load keeps its frame. - **Task carryover with outside participants** — Open tasks are no longer carried into a session that includes a participant from outside the organization. - **Cooldown screen wording** — The cooldown screen now states the cap in hours rather than "1440 minutes". - **Security hardening** — Fixes from our ongoing security review. - **Mia search ranking** — Documentation results no longer crowd out the relevant page with extra sections.