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. 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. 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, 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

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 not the sub-second, talk-over-able latency 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 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.)
• A sub-second latency budget, because 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, 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 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 60 minutes 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 — hear a real meeting translated live, per listener, in any of 23 languages, instead of one English-anchored pair — no signup needed.
• See the benchmark — per-pair, per-month translation quality on real traffic, with the methodology written down.
• InterMIND vs. the platforms you know — honest, feature-by-feature.
• Running a webinar or training across languages? The event workflow: events & webinars.
• Just need a record, not live translation? The notetaker head-to-head: 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 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 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 60 minutes 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, Google Workspace — Gemini updates, Google Meet — Use translated captions, Google Workspace — plans and pricing, 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. All facts checked August 2026.