- Live subtitles
- Built for Google Meet
Read a Google Meet call in your language while it is happening
Subtitles appear over the meeting window a moment after each phrase is spoken, and a translated voice reads them to you with the original audio turned down. Your own replies can be voiced in the other language too: turn on translation of your speech in the extension — it is off by default.
The trial gives you 30 minutes of live translation, no payment card required.
32 languages, any pair, chosen before you join.
The call this page was written for
A customer escalation gets moved up and you are on the call in forty minutes. The customer's engineers speak Polish to each other and switch to careful English for you, which means you catch about two thirds of what matters and ask them to repeat the rest. With subtitles running you read the Polish as it is spoken, and once you turn on translation of your speech, your answers reach them in Polish without you attempting any.
What this looks like during the call
Live transcript
ESENNear-real-time subtitles over the meeting window, read aloud to you, plus an optional spoken translation of your replies for the other side.
El proyecto piloto duró dos semanas más, así que las cifras finales solo llegan el jueves.
The pilot project ran two weeks longer, so the final numbers only land on Thursday.
Entonces movamos la revisión al viernes por la mañana. Hoy aviso al cliente.
Then let's move the review to Friday morning. I'll let the client know today.
Me sirve. Mándame el borrador la noche anterior, con el desglose de costes.
Works for me. Send me the draft the evening before, with the cost breakdown.
Action items
Built for Google Meet- Move the review to Friday morning
- Tell the client today that the numbers land Thursday
- Send the draft with the cost breakdown on Thursday evening
How to set it up
MeetVoice is a Chrome extension plus a companion desktop app. The extension reads the Google Meet tab you already have open and the desktop app coordinates the session from your machine, so no extra participant is added to the call.
Step 1Install MeetVoice before the call starts
Add the extension from the Chrome Web Store and install the desktop app. Speech recognition is included, so there is no key to obtain and nothing to configure on a first run.
Step 2Pick your language pair and a voice
Choose your language and the language of the other side, then pick a male or female voice for the spoken translation. Both settings live in the panel next to the meeting.
Step 3Start translation when you join
Subtitles appear over the Google Meet window shortly after each phrase and are read aloud to you. To have your own speech voiced for the other side, turn on translation of your speech in the extension — it is off by default. The other participants do not see the subtitle layer unless you share that tab or your screen.
What usually goes wrong
- Captions alone do not give you a reusable bilingual document; check the recording and export options before relying on them.
- Asking somebody to repeat a sentence three times costs more goodwill than getting it slightly wrong once.
- A caption in a language you do not speak is not help; it is the same problem in smaller type.
Why this holds up in a real call
- Subtitles are drawn in your own browser tab, so nobody else in the call sees what you are reading unless you share that tab or your screen.
- Incoming speech is subtitled and read aloud for you; turn on translation of your speech and the other side hears your replies in their language too.
- The original audio is turned down while the translated voice speaks, so the translation is easier to hear in your headphones.
How the three options compare
What Google Meet does on its own
Yes, as text. Translated captions depend on supported languages and an eligible plan. Standard captions transcribe speech; translated captions display translated text on eligible plans. Both are text features. Speech Translation is a separate feature for translated audio.
Standard captions transcribe speech; translated captions display translated text on eligible plans. Both are text features. Speech Translation is a separate feature for translated audio. Google announced general availability of Speech Translation on 4 February 2026. Current Help lists English paired with French, German, Hindi, Italian, Portuguese or Spanish: one pair per meeting, with a 90-minute limit. Access depends on an eligible plan, administrator settings, supported devices and participants allowing their voices to be translated. Speech Translation is not available in recordings or live streams. Where meeting recording is available, Record captions can include captions in the recording. Turning on captions alone does not automatically create a bilingual PDF, SRT or TXT export; availability and permissions depend on the plan and settings.
| What you are comparing | MeetVoice | Built-in Google Meet | Notetaker bot that joins the call |
|---|---|---|---|
| Can you follow the call while it is happening? | Yes — near-real-time subtitles in your language, read aloud to you; the other side hears your replies translated only once you turn that on. | Yes, as text. Translated captions depend on supported languages and an eligible plan. | No — notetaker bots are built for what happens after the call. |
| Is anything spoken back in the other language? | Optional — once you turn on translation of your speech in the extension (off by default), your replies are voiced in a male or female voice. Incoming speech is read aloud to you with the original audio turned down. | No — captions are text only. | No — the output is a written artefact produced later. |
| Who can see the subtitles you are reading? | Only you. They are drawn in your own browser tab; others see them only if you share that tab or your screen. | Only you, but each participant has to switch their own on. | Not applicable — nothing is shown during the call. |
| How many language pairs are available? | Any pair out of 32 languages, chosen before you join and changeable between calls. | Supported languages are listed in the Google Help link below. | Vendor-dependent, and usually applied to the written record rather than to the live call. |
Questions people ask before installing
How much delay is there between speech and subtitle?
Near-real-time: a phrase is recognised, translated and drawn while the speaker is still going. That is close enough to follow a conversation, not close enough to interrupt on an exact word.
Do the other participants see my subtitles?
No. The subtitle layer belongs to your own browser tab, unless you share that tab or your screen. The other side hears your replies as a spoken translation only if you turn on translation of your speech in the extension; it is off by default.
What happens if three or four languages are spoken in one call?
Switch on multilingual mode in the panel and pick up to four participant languages — this mode covers incoming speech only and uses your plan's included hours. Each segment is detected and translated into your language, with speaker names and colour tags so the thread stays readable.
Do I need my own speech-recognition key?
No. Recognition is included in the trial and in every paid plan, so there is no key to obtain or connect.
Follow a call in a language you do not speak, while it is still happening.
The trial gives you 30 minutes of live translation, no payment card required.
Page last reviewed