How to transcribe a conversation: from a recording to text

To transcribe a conversation, record it with everyone's consent, then either type it out while you replay it or give the recording to a speech-to-text tool and correct what it wrote. With a tool the steps are: get the recording as a file, let the tool write the words, fix the names and anything misheard, add who said what, and save the text. Burncaps does the writing in your browser, free for recordings up to ten minutes, with no sign-up, and it does not name the speakers for you.

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.

  • Free, no sign-up
  • Video never uploaded
  • Text, SRT or VTT
  • Up to three hours

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

Four ways to transcribe a conversation, and who each suits

Every way ends with the same job: a person reading the text against the recording. They differ in who writes the first draft, what it costs and where the recording goes.

The wayIt suits you whenWhat you getWorth knowing
1. Type it yourselfThe recording is short, or every pause and overlap matters to youExactly what you typed, in the form you choseThe slowest way. Play a few seconds, pause, type, and slow the playback if your player lets you.
2. A speech-to-text toolYou will read the draft against the recording anyway, and want it in minutesA draft of every word, with times, to correctTools differ on whether they name speakers, where the recording goes and what they cost. Burncaps writes the words in your browser and does not name speakers. Ten tools compared
3. An AI assistant such as ChatGPTThe recording is a few minutes long and you also want a summaryA transcript in the chat, then answers about itOpenAI's help page says audio uploads need a paid plan and, with the model it names, take up to 6 minutes per recording. Can ChatGPT transcribe audio?
4. A person, through a transcription serviceIt has to be right and you cannot check it yourselfA finished transcript, usually with speaker namesPaid by the minute of recording, and the recording is sent to the service. What one service charges

Before you record: tell everyone

The rules on recording a conversation differ from country to country, and in the United States from state to state; in some places everyone in the conversation must agree. Say that you are recording, get a yes, and keep that yes on the recording. This is not legal advice.

The steps with a tool, using Burncaps

This is way 2. It works the same on a computer and a phone, and nothing is installed.

  1. Get the recording as a file. A phone's voice recorder saves a sound file, often an M4A; a recorded video call is usually a video file such as an MP4. Burncaps takes a file. It does not record a call and does not listen live.
  2. Drop the file on the box at the top of this page, or tap it to choose a file on a phone. MP3, M4A and WAV work, and so do MP4 and MOV videos.
  3. Wait while it listens. Every word appears as a script under the player, and the language it heard is named above the script, with a one-click change if it guessed wrong.
  4. Fix the names and anything misheard. Click a word and type. One click changes it everywhere it was heard. Names, places and trade words are the usual misses.
  5. Save the text. Press Text for a .txt file in paragraphs. Tick Times in the Text file and each paragraph starts with its time in the recording, like [00:01:23]. SRT and VTT give a time on every line.
  6. Add who said what. Burncaps does not tell voices apart, so open the text file and put a name at the start of each turn. Its paragraphs follow pauses, not speakers, so check each break before you name it.

Text and subtitle files are free without limit for recordings up to ten minutes, with no sign-up. 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.

What makes a conversation harder than one voice

People talking at once

When two people speak over each other, a speech model writes one of them, or a mix of both. Mark those lines as you read through, and listen to them again rather than trusting the draft.

Names and trade words

A model writes the commonest spelling it knows. In Burncaps you can type the names it should spell right, and a correction you make once is applied everywhere and remembered by this browser.

A phone in the middle of the table

The far voice is the one that gets lost. If you can, put the recorder nearer the quietest person, away from a fan or an open window, before you start.

Every um, or a clean read?

Decide before you correct. A verbatim transcript keeps every um, repeat and false start. A clean one leaves them out and keeps the meaning. Burncaps gives the words as the speech model heard them, and speech models do not always write every um. For a clean read, click any filler you want gone and press Cut, and the Text file leaves it out. For strict verbatim, listen through and add what is missing.

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

How do I transcribe a conversation?

Record it with everyone's consent and get the recording as a file. Then either type it out while you replay it, or give the file to a speech-to-text tool, read its draft against the recording, fix the names and anything misheard, add who said what, and save the text.

How do I transcribe a conversation for free?

Drop the recording, an MP3, M4A or WAV, or an MP4 or MOV video, in Burncaps. It hears it in your browser and writes every word as a script; correct any word with a click, then press Text for a .txt file, or SRT or VTT. Text and subtitle files are free without limit for recordings up to ten minutes, with no sign-up.

Does it say who is speaking?

No. The Text file holds the words in paragraphs and does not name or label who is speaking, and it does not tell voices apart, so you add the names yourself. Its paragraphs follow pauses, not speakers, so check each break before you put a name at its start.

Can I transcribe a phone call or a voice memo?

Yes, if you have it as a file. A voice memo is usually an M4A, which Burncaps takes. Burncaps does not record calls: it takes a recording you already have.

Can it transcribe a conversation live, while people talk?

No. Burncaps takes a finished recording as a file. It does not join a meeting, record a call or write words while people are still talking.

How long can the recording be?

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.

Does the transcript have timestamps?

Only if you want them. The Text file is in paragraphs; tick Times in the Text file, under the file buttons, and each paragraph starts with its time in the recording, like [00:01:23]. For a time on every line, save SRT or VTT instead: each subtitle line is timed to the voice.

Is my recording uploaded?

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).

Which languages can it transcribe?

More than 60 languages, Chinese in Simplified or Traditional: the list in Listening settings. It listens first and names the language it hears above your script, with a one-click change. The Text file is in the language spoken; a translation of the lines goes into the SRT and VTT files.

Is it legal to record a conversation to transcribe it?

It depends on where you and the other people are. Some places let one person in the conversation record it; others need everyone to agree. Tell everyone and get a yes on the recording. This is not legal advice.

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.