Translate audio to English, free, as subtitles
Drop an audio recording in another language: an MP3, WAV or M4A, a voice note, or a video. Burncaps writes out what was said, translates every line into English with our AI, and gives you SRT, VTT and ASS subtitle files with the English lines and their times; a video can also have the English burned into the picture. It makes written English, not a spoken English voice: no dubbing, no live translation, and no link, because it takes a file. Translating is free and needs no account.
The file stays in your browser. On a computer, the sound is heard on your own device unless you choose our speech service; 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 file itself.
- Free, no sign-up
- MP3, WAV, M4A and more
- English SRT, VTT, ASS
- No dubbing, not live
Live preview of English captions, rendered on this page by the same engine that burns a video.
How to translate audio to English
Burncaps is a free audio translator to English that works inside the page. A recording in another language becomes English subtitles in three steps, with no account.
1. Drop the recording
An MP3, WAV or M4A, another audio file your browser can play, or a video. It opens straight on its script. Burncaps listens first and names the language it hears above your script, with a one-click change. It hears 59 languages, the list in Listening settings.
2. Choose English under Captions in
Each line is translated by our AI and laid over the moments it was said. Correct a misheard word in the script and only its line is translated again; one click fixes a word everywhere it was heard.
3. Save the English subtitles
Press SRT, VTT or ASS. Each file carries the English lines with their times, and its name ends in -en. From a video you can export an MP4 with the English captions burned in instead.
What leaves your device for a translation
Only the lines of text: each word numbered and a mark after the words where the speaker paused, with no times, sent to our server and passed to Anthropic's Claude, which processes API data under its commercial terms and does not train on it. We do not store the transcript. The audio file stays in your browser. On a computer, the sound is heard on your own device unless you choose our speech service, which is also offered for other languages and for recordings over ten minutes; on a phone the sound goes to our speech service unless you keep it on the phone. The service gets short pieces of sound, never the file itself, and passes them to Microsoft's speech recognition in the EU, which by Microsoft's terms for the service stores none of it. Ticking Keep everything on this device stops the translation, and the captions then stay as spoken. Transcribe without uploading shows how to check every request yourself.
What it does, and what it does not
| Ask | Burncaps |
|---|---|
| Which way does it translate? | From the language spoken into English, or into another language from the same list |
| Which files? | MP3, WAV and M4A, other audio your browser can play (AAC, OGG, FLAC, Opus), or an MP4 or MOV video |
| English subtitle files? | SRT, VTT and ASS carry the English lines with their times, free without limit for recordings up to ten minutes |
| The English as plain text? | There is no separate English text file: the Text file stays in the language spoken. An SRT file is plain text, so open it in any text editor to copy the English lines |
| English burned into a video? | Yes, from a video file: a new MP4 with the English in the picture, for a video up to ten minutes. An audio file has no picture, so it gives its script and subtitle files only |
| Clips? | Clips need a picture, so an audio file gives its script and subtitle files only |
| A spoken English voice? | No. Burncaps makes subtitles, not a dubbed voice |
| Live translation? | No. It works on a recording, not on speech as it is said |
| A link? | No. It takes a file from your device, never a link |
| Longer recordings? | Translation works on recordings up to ten minutes; the whole script of a longer recording stays in the language spoken |
| What it costs | Translating is free. Free: 2 videos every 30 days, each with captions and up to 3 clips, no watermark, no sign-up. Then try Captions + Clips free for 7 days, no card. Captions + Clips is $29 a month for unlimited clips and captions; Captions is $9.98 a month or $49 once. |
When another kind of tool is the right one
Tools that dub a recording into a spoken English voice, tools that translate a conversation as it happens, and a translator that reads a text translation aloud each do a job this does not. Burncaps is for written English from a recording you already have, with the words timed to the voice.
Which languages, and how well they are heard
It hears 59 languages, the list in Listening settings, and translates any of them into English. Two steps can go wrong, so each is measured where we have measured it: the speech step, which writes the words, and the English step, which turns them into English.
| Spoken language | Speech step, our speech service | English step, meaning kept | More |
|---|---|---|---|
| Spanish | about 97 in 100 words right | 6 of 6 recordings | Spanish captions · English subtitles |
| Portuguese | about 96 in 100 words right | 6 of 6 recordings | Portuguese captions · English subtitles |
| French | about 93 in 100 words right | not measured | French captions |
| German | about 99 in 100 words right | not measured | German captions |
| Arabic | about 87 in 100 words right | 5 of 6 recordings | Arabic captions · English subtitles |
| Hindi | about 90 in 100 words right | 6 of 6 recordings | Hindi captions · English subtitles |
| Tamil | about 79 in 100 words right | 6 of 6 recordings | Tamil captions · English subtitles |
| Malayalam | about 80 in 100 words right | 13 of 14 recordings | Malayalam captions · English subtitles |
| Japanese, Chinese, Russian, Korean and the other languages in the list | not measured | not measured | Japanese to English |
How to read the table
The speech figures are how many words in 100 our speech service wrote right, before any correction, on public test recordings (Google FLEURS) of that language, the numbers on each language page. The English figures are counts from 29 September 2026: 44 public recordings in six languages, each English result set beside a human English sentence, and the meaning was kept in 42 of 44. That is a small sample and we give it as a count, not a percentage. We give no figure for a step we have not measured. Translation is done by an AI model, so names, jokes and long compound words can go wrong: read the English once before you publish.
Have the video too? Burn the English in, or cut clips
If the recording was filmed, drop the video instead of the audio: under Captions in, choose English, and Export the captioned video for an MP4 with the English captions in 60 animated styles. Translate a video to English covers that in full. Choose Clips, and Burncaps finds the best moments of a talk, podcast or interview and cuts each into a ranked, captioned 9:16 clip; each free video exports up to 3 of them, and Captions + Clips exports every clip, unlimited. Each clip is translated like a short video, so its captions can be in English too. Long video to Shorts shows it on a long recording.
What it costs
Free: 2 videos every 30 days, each with captions and up to 3 clips, no watermark, no sign-up. Then try Captions + Clips free for 7 days, no card. Captions + Clips is $29 a month for unlimited clips and captions; Captions is $9.98 a month or $49 once.
Questions, answered plainly
How do I translate audio to English for free?
Drop the audio file, such as an MP3, WAV or M4A, on this page. Burncaps writes out what is said in the language spoken, then under Captions in choose English: every line is translated and laid over the moments it was said. Press SRT, VTT or ASS to save English subtitles. Translating is free and needs no account.
Does it speak the English, or dub the audio?
No. Burncaps writes English subtitles. It does not make a spoken English voice, and it does not translate speech as it is said: it works on a recording you already have.
Which audio files can it translate?
MP3, WAV and M4A work, and so do AAC, OGG, FLAC or Opus files your browser can play. A video file, MP4 or MOV, works too. It takes a file from your device, never a link.
Which languages can it translate into English?
Any of the 59 in Listening settings, the languages it can hear. It listens first and names the language it hears above your script, with a one-click change. The same Captions in control also translates into another language from that list.
Can I get the English as plain text?
The English is in the SRT, VTT and ASS files, each line with its time. The Text file stays in the language spoken. An SRT file is plain text, so you can open it in any text editor and copy the English lines.
How long can the recording be?
Translation works on recordings up to ten minutes; the whole script of a longer recording stays in the language spoken. Subtitle files are free without limit for recordings up to ten minutes.
How accurate is the English?
There are two steps, and we measured each where we could. On public test recordings (Google FLEURS), the speech step wrote about 97 in 100 words right for Spanish, 96 for Portuguese, 93 for French and 99 for German, and fewer for some other languages, such as about 79 for Tamil. The English step was checked on 29 September 2026 on 44 public recordings in six languages: the meaning was kept in 42 of 44. French, German, Chinese, Japanese, Russian and Korean have no check of the English step, and we give no figure for them. Translation is done by an AI model, so names, jokes and long compound words can go wrong: read the English once before you publish.
What leaves my device for a translation?
Only the lines of text: each word numbered and a mark after the words where the speaker paused, with no times, sent to our server and passed to Anthropic's Claude, which processes API data under its commercial terms and does not train on it. We do not store the transcript. The audio file never leaves your browser, and ticking Keep everything on this device stops the translation.
Is the translation free?
Yes. Translating needs no account, and each connection has a generous daily limit against abuse. Subtitle files are free without limit for recordings up to ten minutes. Exporting a captioned video is free for 2 videos every 30 days, each with captions and up to 3 clips, no watermark and no sign-up. Then try Captions + Clips free for 7 days, no card. Captions + Clips is $29 a month for unlimited clips and captions; Captions is $9.98 a month or $49 once.
Can it translate a voice note or a call?
A voice note or a call you have saved as an audio file, yes: drop the file. A call as it happens, no. Burncaps does not join calls or translate live.
Can I translate a YouTube video or a podcast from its link?
No. Burncaps takes a file from your device, never a link. Save the audio or the video as a file first, then drop it here.
Burncaps facts, checked 3 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 3 clips, no mark and no sign-up; then the free 7-day Captions + Clips trial, no card (your email only); then Captions + Clips, $29 a month, gives unlimited clips and captioned videos, or Captions, $9.98 a month or $49 once, gives unlimited captioned videos. Captions paid once is not a subscription. Translations are free.
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 only if you choose it. 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. 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 as one of your free videos, in the trial or with Captions + Clips or Captions) and its clips (every one found and shown before you sign up; up to 3 from each free video exported free, every one in the trial or with Captions + Clips).
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 3 of them, and the 7-day trial and Captions + Clips export every clip, unlimited.
Languages and styles: captions in the language spoken, twelve Indian languages heard on your device, translation into 59 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.