Can Gemini transcribe audio? Yes, within the limits Google sets

Yes. Google's developer page for the Gemini API lists “Transcription and translation (speech to text)” and speaker diarisation among what Gemini does with audio. In the Gemini app, Google's help page says you can attach audio up to a total of 10 minutes, or 3 hours with Google AI Pro or Google AI Ultra, and ask about it; that page speaks of answers, summaries and insights, not of a transcript file or subtitles. This is what Google's pages said on 17 November 2026. We make Burncaps, a rival transcription and caption tool, so read the rest as a competitor's page.

or drop your video or podcast here
MP4 or MOV, or audio for subtitles.

The video never leaves your browser. On a computer, the sound is heard on your own device unless you choose our speech service or the computer is too slow to listen well; on a phone, it goes to our speech service unless you keep it on the phone. The service gets short pieces of sound, never the picture.

  • Read 17 Nov 2026
  • Written by a rival, said up front
  • Video never uploaded

Live preview, rendered on this page by the same engine that captions your video.

What Gemini does with sound, as Google's pages state it

QuestionGoogle's answer
Can I attach a recording in the Gemini app?Yes. “Gemini Apps support most file types.” On the web: Add files, then Upload Files, then Submit
How much audio?“Total audio length can be up to 10 minutes. Upgrade to Google AI Pro or Google AI Ultra to extend total attachment length to 3 hours.”
A video file?Each video can be 2 GB; a total of 5 minutes of video, or 1 hour with Google AI Pro or Google AI Ultra
How many files at once?Up to 10 in one prompt, “subject to availability”; files other than video can be 100 MB each
Is there a cap over time?“There are rolling limits for how much you can attach and analyze files in a period of time.”
Does the app page promise a transcript?It says you attach files “to get answers, summaries, and insights about your content”. It does not describe a timed transcript or a subtitle file
For developers, through the API?“Transcription and translation (speech to text)”, “Speaker diarization (identifying different speakers)” and “Analyzing specific segments with timestamps”; WAV, MP3, AIFF, AAC, OGG, FLAC, M4A, Opus and WebM among the formats; a limit of 9.5 hours of audio per prompt, counted at 32 tokens a second

Read on 17 November 2026: Attach & analyze files in Gemini Apps (Gemini Apps Help) and Gemini API, audio understanding (the address ai.google.dev/gemini-api/docs/audio now leads there). Neither page showed a date. Google's pages are the authority if they have changed. Something those pages do not state is not stated here.

What we did not do

We did not run a recording through Gemini, so this page says nothing about how accurate its transcripts are. It reports what Google's pages say Gemini accepts and does.

How to ask Gemini for a transcript

  1. Go to gemini.google.com and sign in; Google's page says the feature needs you signed in.
  2. Type what you want in the text box: for example, a transcript with the time of each paragraph and who is speaking.
  3. Click Add files, then Upload Files, pick the recording and click Submit.
  4. Check the length first. On the free plan the audio you attach can total 10 minutes, so a longer recording goes over that total.
  5. Read the names and numbers back against the recording before you use the text.

Where Gemini is the better choice: once it has the recording, you can ask questions about it, get a summary and draft notes in the same chat. Burncaps writes the transcript and the subtitle files, and stops there.

For a transcript: the Gemini app and Burncaps side by side

For a transcriptGemini appBurncaps
Audio without payingA total of 10 minutes, within rolling limitsText and subtitle files free for recordings up to ten minutes, no sign-up
Longest recordingA total of 3 hours with Google AI Pro or UltraThree hours and 10 GB
Video filesA total of 5 minutes free, 1 hour on those plansMP4 or MOV
What comes backAn answer in the chatText with paragraph times, SRT, VTT and ASS files
Fixing a misheard nameAsk again, or edit the text yourselfClick the word once and it changes everywhere
Speaker labelsListed on the developer page; the app page does not sayNone: you add them
Where the file goesTo Google, as an attachmentNowhere: it stays in your browser; the sound may go to our speech service
Summaries and questionsYes, in the same chatNo

Gemini's column from Google's pages, read 17 November 2026. A recording over ten minutes gives its first ten minutes free in Burncaps, and all of it as one of your free videos (2 every 30 days), in the 7-day Pro trial (free, no card) or on a paid plan.

What it costs

Free: 2 videos every 30 days, each with captions and up to 10 clips, no watermark, no sign-up. Then try Pro free for 7 days, no card. Pro is $29 a month for unlimited clips and captions; Starter is $11.98 a month for 6 videos and up to 50 clips. Text and subtitle files are free without limit for recordings up to ten minutes, with no sign-up.

Questions, answered plainly

Can Gemini transcribe audio?

Yes. Google's developer page lists transcription and translation (speech to text) and speaker diarization among what Gemini does with audio, and the Gemini app lets you attach audio and ask about it. Read on 17 November 2026.

Is Gemini free for transcription?

The Gemini app's help page sets a total of 10 minutes of attached audio on the free plan, within rolling limits, and a total of 3 hours with Google AI Pro or Google AI Ultra.

How long a recording can Gemini take?

In the Gemini app, a total of 10 minutes of audio, or 3 hours on Google AI Pro or Ultra. Through the API, the developer page gives a limit of 9.5 hours of audio per prompt.

Can Gemini transcribe a video?

The app takes video files of 2 GB each and a total of 5 minutes of video, or 1 hour on Google AI Pro or Ultra. Google's help page speaks of answers and summaries about the content, not of a transcript file.

Can Gemini make an SRT file?

Neither Google page we read describes a subtitle file. Burncaps saves SRT, VTT and ASS files timed to the voice, and a text file with paragraph times.

Does Burncaps use Gemini?

No. Burncaps sends nothing to Gemini. The words are heard on your device or by our speech service, which is Microsoft's speech recognition in the EU.

Is a transcript free in Burncaps?

Text and subtitle files are free without limit for recordings up to ten minutes, with no sign-up. A recording over ten minutes gives its first ten minutes free, and all of it as one of your free videos (2 every 30 days), in the 7-day Pro trial (free, no card) or on a paid plan.

Is my video uploaded?

No. Burncaps opens the video in your browser and never receives it. On a computer, the sound is heard on your own device unless you choose our speech service or the computer is too slow to listen well; on a phone it goes to our speech service unless you keep it on the phone (short pieces of sound, never the picture, to Microsoft's speech recognition in the EU, which by Microsoft's terms for the service stores none of it).

Burncaps facts, checked 17 November 2026

What it is: a browser tool that burns animated word-by-word captions into a talking video, or finds the best moments of a talk, podcast or interview and gives them back as ranked, captioned 9:16 clips.

Price: free for 2 videos every 30 days, each one recording with its captioned video and up to 10 clips, no watermark and no sign-up; then the free 7-day Pro trial, no card (your email only); then Pro, $29 a month, gives unlimited clips and captioned videos, or Starter, $11.98 a month, gives 6 videos every 30 days, each fully captioned, and up to 50 clips.

Privacy: the video never leaves your browser. The sound goes only to our speech service, on a phone unless you switch it off, on a computer if you choose it or if it is too slow to listen well. Because the video never reaches us, we cannot keep it or train AI on it, and we train no AI on anything you make.

Files: MP4 or MOV in, MP4 out. Captions on the whole video: up to ten minutes on Free, up to three hours on a paid plan, on a phone or a computer. On iPhones, a whole video over ten minutes has been tested in the iPhone simulator on a Mac (16 minutes at 1080p), not yet on a real iPhone. Clips: up to three hours, on a phone or a computer. SRT, VTT, ASS and text files are free without limit for recordings up to ten minutes; a longer recording, up to three hours, gives its script and those files (the first ten minutes free, all of it with one of your free videos, in the trial or on a paid plan).

Clips: about one clip for every two minutes of talk, up to 30, ranked, the ones we would post first circled, each showing the words it opens and ends on and the reason it was chosen; each cut to 9:16 with ums and dead air removed, an opening card and captions, framed on whoever is talking. Every clip of the whole recording is found and shown, free and with no sign-up; each free video exports up to 10 of them; Starter exports up to 50 clips every 30 days from its 6 videos, and the 7-day trial and Pro export every clip, unlimited.

Languages and styles: captions in the language spoken, twelve Indian languages heard on your device, translation into more than 60 languages, 60 caption styles.

After it listens: correct any word (one click changes it everywhere), add or cut words, one to six words at a time, position, size, text and highlight colours, and names this browser remembers, all free and without listening again.

Made by: Jordan Labs Ltd, UK company no. 17358646.

Against other tools: sixteen caption tools compared, from the vendors' own pages.