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.

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, 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

Enabling Translation

1. Join a meeting
2. Find the language button in the control bar: it shows the language you hear and read in, or Translation off. Click it to switch translation on or off (or press Alt+T)
3. Click the arrow next to it and pick your language from the Hear and read everyone in list
4. Start speaking — other participants will hear you in their chosen language

On a phone the control bar has no language button: Enable translation and the language list are in the More menu.

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, 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
• Several terms in one message — Mia reads them back as a list and adds them all on one «yes»
• A whole glossary at once — attach the spreadsheet or CSV in the ⌘/ panel (the paperclip, or drop the file on the panel; one column with the term, one column per language) and ask Mia to add its terms to the glossary: she reads the file, tells you how many rules it holds and adds them all on one «yes». A file already shared in a channel or meeting chat works the same way — name it with that channel open. The same term for the same language is replaced, so a re-upload corrects rather than duplicates

From the next translation on, recaps and their transcripts, shared documents, chat and notes render the term as told; the live captions of a call do not read the glossary yet. Ask Mia «what terms do you know» to read the list back — 40 terms at a time, every language of a term on its line, «more» for the next page, a word («what about UBS») for the terms carrying it — or «forget the rule about Atlas» to drop it in every language. Available to organizations with AI features on.

In This Section

• Choosing Languages — Choose and change the language you hear and read in
• Live Subtitles — Display translated text during meetings
• Transcription — Record and save meeting transcripts
• Usage & Limits — Translation time limits by plan, tracked on the Billing page