Can ChatGPT transcribe audio? Yes, on paid plans, within limits

Yes, on a paid plan. OpenAI's help page says you can attach an audio file to a chat and ask for a transcript, that audio uploads are not available on the Free plan, and that with the model it names for this, GPT-6 at Instant, a recording can be up to 6 minutes long. A video file is not accepted as an audio upload. Its Mac app can also record a meeting live, with a cap of 4 hours a session, and transcribe that. This is what OpenAI's pages said on 15 November 2026. We make Burncaps, a transcription and caption tool, so read the rest knowing that.

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 15 Nov 2026
  • Written by a toolmaker, said up front
  • Video never uploaded

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

What ChatGPT does with audio, as OpenAI's help pages state it

QuestionOpenAI's answer
Can it transcribe an audio file I attach?Yes: attach the recording in a chat and ask for a transcript
On the Free plan?No. Audio uploads are for paid subscriptions and workspaces, and are not available on Free
How long can the recording be?Up to 6 minutes per recording with GPT-6 at Instant in Chat, the model the page names for it
What about a longer recording?It may be processed in smaller sections when Data Analysis is available. The page calls this best-effort and says very long recordings may time out
How big can the file be?Up to 512 MB
Which files?WAV, MP3, OGG, FLAC, AAC, M4A, PCM, and WebM or MP4 that hold sound only
Can I attach a video and get its transcript?Not as an audio upload: WebM and MP4 files identified as video are not supported
Does it name the speakers?The page says speaker identification may be unreliable, and that transcripts may contain errors
Everywhere in ChatGPT?In Chat. The page says uploaded-audio transcription is not currently available in Work or Codex, and that availability varies by region and app version
Can it record and transcribe live?Yes, with record mode: the macOS desktop app only, on Plus, Pro, Business, Enterprise and Edu, with a cap of 4 hours a session and speakers labelled

Read on 15 November 2026 in OpenAI's Help Center: Uploading files and audio to ChatGPT and ChatGPT Record. OpenAI's pages say limits can change, and they are the authority if they have. A setting or a limit that these two pages do not state is not stated here.

If you write code: the API is a separate thing

OpenAI also sells speech to text to developers through its API, which is not ChatGPT. Its guide says a file can be up to 25 MB, in formats including MP3, MP4, M4A, WAV and WebM. OpenAI: file transcription guide, read 15 November 2026.

How to get a transcript from ChatGPT

  1. Check your plan. Audio uploads need a paid ChatGPT plan or workspace.
  2. Check the length. Up to 6 minutes per recording with the model OpenAI names. Cut a longer one into parts first.
  3. Check it is a sound file. If you have a video, save its sound as an MP3, M4A or WAV first.
  4. Attach it in a chat and ask for a transcript. OpenAI's page suggests GPT-6 at Instant in Chat if you have it.
  5. Read it against the recording. OpenAI's page says transcripts may contain errors. If a file uploads but will not transcribe, the page suggests converting it to WAV and trying again.

Where ChatGPT is the better choice: once it has the words, it can summarise them, answer questions about them and turn them into notes or an email in the same chat. Burncaps writes the transcript and stops there.

When the recording is longer, is a video, or you are on Free

Burncaps writes the transcript in your browser. Drop an MP3, M4A or WAV, or an MP4 or MOV video, and every word appears as a script you can correct, then save as a text file, with times if you tick them, or as SRT or VTT. To have ChatGPT summarise a long recording, save the text file here and attach that: documents and text files can be uploaded on ChatGPT's Free plan, by the same help page.

For a transcriptChatGPTBurncaps
Without payingNo audio uploads on FreeText and subtitle files free for recordings up to ten minutes, no sign-up
Longest recording6 minutes with the model named; longer is best-effortUp to three hours and 10 GB
A video fileNot accepted as an audio uploadMP4 or MOV
Timed filesNot stated on the help pageText with paragraph times, SRT, VTT and ASS
Speaker namesMay be unreliable for uploads; record mode labels speakersNone: you add them
Where the recording goesUploaded to ChatGPTThe file stays in your browser; the sound may go to our speech service
Summaries and questions afterwardsYes, in the same chatNo

ChatGPT's column from OpenAI's help pages, read 15 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. 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.

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 ChatGPT transcribe audio?

Yes, on a paid plan. OpenAI's help page says you can attach an audio file in a chat and ask for a transcript, with recordings up to 6 minutes long on the model it names, GPT-6 at Instant, and files up to 512 MB. Audio uploads are not available on the Free plan. Read 15 November 2026.

Can the free version of ChatGPT transcribe audio?

Not from an uploaded file. OpenAI's help page says audio uploads are available with paid subscriptions and workspaces and are not available on the Free plan at this time (read 15 November 2026).

How long an audio file can ChatGPT transcribe?

Up to 6 minutes per recording with GPT-6 at Instant in Chat, by OpenAI's help page. It says longer recordings may be processed in smaller sections when Data Analysis is available, that this is best-effort, and that very long recordings may time out (read 15 November 2026).

Can ChatGPT transcribe a video?

Not as an audio upload. OpenAI's help page says WebM and MP4 files identified as video are not supported by audio uploads, so save the sound as an MP3, M4A or WAV first. Its page on video attachments says ChatGPT may not accurately interpret a video's audio (read 15 November 2026).

Can ChatGPT record a meeting and transcribe it?

Yes, with record mode. OpenAI's help page says it is in the macOS desktop app only, for Plus, Pro, Business, Enterprise and Edu, with a cap of 4 hours a session, and that it can tell several speakers apart with labels such as Speaker 1 (read 15 November 2026).

How accurate is ChatGPT at transcribing?

OpenAI publishes no accuracy figure on these pages. They say transcripts may contain errors, that speaker identification may be unreliable, that performance may vary across languages, and that important details should be checked against the recording.

How do I transcribe a long recording for free?

In Burncaps, drop the recording and it writes every word as a script in your browser. Up to ten minutes, a recording's text and subtitle files are free, as often as you like. A longer one, up to three hours and 10 GB, 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.

Can I give ChatGPT a transcript made somewhere else?

Yes. OpenAI's help page lists TXT among the files ChatGPT takes, on Free and paid plans, and summarising a document and pulling quotes from it among the things it does. Save the Text file from Burncaps and attach it.

Is my recording uploaded when I use Burncaps?

The file itself stays in 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 (short pieces of sound to Microsoft's speech recognition in the EU, which by Microsoft's terms for the service stores none of it).

Burncaps facts, checked 15 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.