Google Meet live translation (2026): how it works, what it costs, and where it stops

Does Google Meet translate in real time? Yes, two ways — translated captions (90+ languages) and Gemini speech translation, 63 languages with automatic language detection since October 2026. Which Workspace plan each needs, what it costs, how to turn it on, the 90-minute and 8-hour caps, and what the translation leaves behind when the call ends.

The Mind.com Team

  • Yes, two ways. Translated captions as text in 90+ languages and Gemini speech translation of the audio in 63 languages, both behind a Workspace or Google AI plan.
  • Any pair, detected automatically, since October 2026. 90 minutes per meeting on most plans, 8 hours on AI Ultra; not in 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.
Try the live demoA real meeting, translated live. No signup.
Google Meet live translation (2026): how it works, what it costs, and where it stops

Google Meet live translation (2026): how it works, what it costs, and where it stops

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. What neither does is keep anything translated once the call ends. This post explains how each works, how to turn it on, what changed in October 2026, and exactly where the edge is now — 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. 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 and Teams. New to interpretation as a category? Start with Simultaneous interpretation: booth, RSI, or AI.


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 or Teams' interpretation channels, not Meet.

2. Speech translation (audio)

The newer, Gemini-powered feature. It launched in 2025 with six language pairs, every one of them anchored on English, and one pair configured for the whole meeting. On October 22, 2026 Google expanded it to 63 languages, any combination, with the spoken language detected automatically — the rollout reaches Scheduled Release domains from November 2, 2026. It 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. The limits moved with the October update, so it's worth being precise about where they sit now.


How to turn on speech translation in Google Meet

  1. Someone 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 the AI Expanded Access add-on. Google's help says the host needs an eligible plan for a scheduled meeting, and at least one participant for a direct call; on Workspace, an admin may need to enable it.
  2. In a meeting, open the captions/translation controls, turn on speech translation, and pick the language you prefer to hear. Meet identifies the speaker's language automatically — there is no language pair to set for the meeting any more.
  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 how long the toggle lasts and what it leaves behind.


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, and lifts the per-meeting cap to 8 hours.
  • Google AI Pro / Ultra — consumer subscriptions that also unlock speech translation for personal accounts; Ultra carries the 8-hour cap, Pro the 90-minute one.

So the translation itself is free at the point of use; the gate is which plan the account is on — the host's for a scheduled meeting, any one participant's for a direct call — and which cap that plan carries.

The two features side by side

Translated captionsSpeech translation
What you getOn-screen text in your languageSpoken audio in your language, in a voice resembling the speaker's
Languages90+63, any combination; the spoken language is detected automatically (since October 2026)
Who picks the languageEach participantEach listener picks the language to hear; nobody sets a pair for the meeting
PlanBusiness Standard and above; AI Pro for EducationBusiness Standard and above, Frontline Plus, AI Pro for Education, Google AI Pro/Ultra, AI Expanded Access
Time limitNone stated90 minutes per meeting; 8 hours on Google AI Ultra and AI Expanded Access
Recordings / live streamsCaptions can be embedded in a recordingNot 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 November 2026, Meet's speech translation is, by Google's own documentation:

  • 63 languages, any combination. The help page lists them — from Afrikaans to Vietnamese, with Arabic, Chinese, Japanese, Korean, Russian, Ukrainian and Brazilian Portuguese among them — and Meet detects which one is being spoken. The English anchor of the 2025 version is gone: a Spanish speaker and a German speaker translate directly.
  • Per listener, in one direction. Each participant picks the language to hear; what they say is detected and translated for everyone else who turned the feature on. Participants under 18 are not translated.
  • A cap by plan. 90 minutes per meeting on Google AI Pro, Business Standard and Plus, Enterprise Standard and Plus, Frontline Plus and AI Pro for Education; 8 hours on Google AI Ultra and AI Expanded Access. Not available in live streams or recordings. In a room with Meet hardware, people outside the room are translated for the room, but speech from the room's hardware is not translated for anyone.
  • 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 translation of the moment: the live audio, for the length of the call, on the plan that carries it — and, by Google's own documentation, nothing translated once the call is over.


Where the edge moved

Until October 2026 the edge was the language list: six pairs, all through English, one pair per meeting. That edge is gone. The edge that remains is time and record. The translation lives inside the call and stops with it — at 90 minutes on most plans — and it is not in the recording, so the colleague who missed the meeting, the client who wants to reread the decision, and the chat that ran beside the call all get the original language, not theirs.

If your meetings are "one call, everyone present, under the cap," Meet's speech translation may be all you need, and it's built into a tool you already have. If the meeting has a before and an after — a channel where the team keeps talking, files, a recap someone has to act on — that is where the question becomes which tool keeps that in each person's language.


What InterMIND does differently

This is the job we built InterMIND for: not the call alone, but the whole space the team works in, in each member's language. Concretely:

  • The translated space persists. A channel keeps the history of every meeting held in it — recaps, chat, files — readable by each member in their own language. Meet's speech translation is not available in recordings, and no audio is saved.
  • 23 languages live on voice, chat and shared notes, each participant independently, and 30 languages for documents dropped into the chat. (The full end-to-end translation stack is its own page; how it works under the hood is in Inside the four translation pipelines.)
  • Free for participants. The host provides the space; guests join by link, without an account and without a plan of their own, and hear the meeting in their language.
  • Pay only for active members. Each renewal counts the members active in the previous 28 days; a quiet member keeps access at no cost.
  • Quality you can audit. We publish per-language-pair scores on real traffic at /benchmark, rather than asking you to take a launch post's word for it.

We're not claiming Meet is bad — for the call itself, voice-preserving speech translation in 63 languages is a strong feature. We're claiming it covers a different scope: the call, versus the work around it. The honest comparison is in Real-time meeting translation and across our platform comparisons.


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
  • 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
  • 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
  • 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
  • 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, Share 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 edge

Google Meet live translation is a real, useful feature with a clearly drawn edge. Knowing where that edge is — the length of the call, and nothing translated kept after it — 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 November 2026: 63 languages, in any combination, with the spoken language detected automatically — the list on Google's help page runs from Afrikaans to Vietnamese and includes Arabic, Chinese, Japanese, Korean, Russian and Ukrainian. Until October 2026 it was six pairs, each 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 or Teams 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 prefer to hear — Meet detects the language being spoken — 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. Since October 2026 it covers 63 languages in any combination; it is capped at 90 minutes per meeting on most plans (8 hours on AI Ultra and AI Expanded Access) 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, AI Pro for Education, or the AI Expanded Access add-on); the host needs it for a scheduled meeting, at least one participant for a direct call, and on Workspace an admin may need to enable it.

How long can a translated Google Meet meeting run?

Speech translation runs for up to 90 minutes per meeting on Google AI Pro and the Business Standard/Plus, Enterprise Standard/Plus, Frontline Plus and AI Pro for Education editions, and up to 8 hours on Google AI Ultra and AI Expanded Access. It doesn't work in live streams or recordings, and participants under 18 are not translated.

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, Spanish–Italian and Russian–Italian voice translator draw that line, and the Italian voice translator overview covers the rest.

— The Mind.com Team


Sources: Google Meet — Learn about Speech Translation (checked November 2026), Google Workspace Updates — Real-time speech translation in Google Meet expands to 63 languages with automatic language detection (October 22, 2026), Google Workspace — Gemini updates, Google Meet — Use translated captions, Google Workspace — plans and pricing (checked August 2026), Google Meet — Record a video meeting (checked October 2026). Google expands supported languages and plan bundles over time; check the help and pricing pages for the current state.

Microsoft Teams live translation (2026): how it works, what it costs, and where it stops
Live translation

Microsoft Teams live translation (2026): how it works, what it costs, and where it stops

Can Teams translate in real time? Yes, three ways — live translated captions, the AI Interpreter agent, and human interpretation channels. Which license each needs (Teams Premium, Microsoft 365 Copilot), what it costs per user, how many languages, how to turn it on, and the limits that decide whether it fits your meeting.

The Mind.com Team

Zoom interpretation: how Language Interpretation works, what it costs, and when it's the wrong tool
Live translation

Zoom interpretation: how Language Interpretation works, what it costs, and when it's the wrong tool

Zoom interpretation explained: what the Language Interpretation feature requires (plan, scheduled meeting, your own interpreters), how to enable it, the 9 default languages, how recordings and breakout rooms behave, how it differs from Zoom's AI translated captions and voice translator — and when AI simultaneous interpretation fits better.

The Mind.com Team

AirPods Live Translation: what it does well, and where a meeting needs more
Live translation

AirPods Live Translation: what it does well, and where a meeting needs more

AirPods Live Translation is a genuinely good face-to-face translator — one person, in your ear, on your device. Here's how it works, its language and hardware limits, and why a group call is a different job.

The Mind.com Team

Get new posts and product updates by email

One email a month with new posts and product updates. Unsubscribe anytime.