Drop a talking video and the captions write themselves: every word heard, timed and animated as it is said, then burned into a new MP4. You check the words; the rest is done for you, on your own device.
Live preview, rendered on this page by the same engine that burns your video.
OpenAI's Whisper model listens in your browser, or our speech service if you choose it, and times each word as it is spoken. It names the language it hears, from 37, and you can change it in one click.
Words are grouped into captions that break at the end of a sentence, at a pause, or at the number of words you chose, one to six words at a time, so the captions follow the way you speak.
Each word lands or lights up as it is said, in whichever of the twenty styles you pick, and the export draws the captions into the picture as a new MP4, made on your own device.
Names, brands and words a speech model has rarely heard are where it slips. Type them into Names to spell right and our AI spells them right in the script (only the text goes), or click any word to correct it: one click fixes every other place it was heard, and this browser remembers the fix. For a strong accent or a noisy room on a computer, Max accuracy in Listening settings is free, a 1.4 GB download once.
| Part | Done for you | Yours to change |
|---|---|---|
| Words | Every word heard and timed | Click to correct; one click fixes every copy |
| Language | Named from what it hears | One click to change, or captions translated into another language |
| Lines | Broken at sentences and pauses | One to six words at a time |
| Look | Keyword: heavy capitals, the word that carries the meaning in colour | 20 styles, the text colour and the highlight colour |
| Place | About two thirds of the way down the frame | A position slider and a size slider |
| Behind you | As recorded | Blurred, a studio colour, your own picture or a green screen |
| Price | Free to use: two videos every 30 days with no mark, or $49 once for unlimited videos. | |
Yes. Free to use: two videos every 30 days with no mark, or $49 once for unlimited videos. The free videos have every feature, and subtitle files (SRT, VTT, ASS and text) are free without limit for videos up to ten minutes.
Clear English speech comes out very well. Other languages, strong accents, music under the voice and noisy rooms cause more mistakes, which is why every word opens in a script you can correct before you export, and why names you type are spelled right.
37. It listens first and names the language it hears, with a one-click change. The captions can also be translated into another of the 37 languages; for that, only the transcript text goes to our AI.
No. Burncaps is a web page with no account. The MP4 export is fastest in Chrome or Edge on a computer, and many phones export too; subtitle files work in most browsers, phones included.
Yes. The same automatic captions download as SRT, VTT, ASS or plain text, for YouTube, a video editor or the player on your own website, free for videos up to ten minutes.
No. The video is captioned and exported in your browser and never leaves your device. The sound leaves only if you choose our speech service, in short pieces to Microsoft's MAI-Transcribe in the EU, and nothing is kept. You can check this in your browser's network tab.
What it is: a browser tool that burns animated word-by-word captions into a talking video, or cuts it to its best 30 or 60 seconds.
Price: free with every feature, for two videos every 30 days with no mark; Pro, $49 once, gives unlimited videos with no mark. Pro is not a subscription.
Privacy: the video never leaves your browser. The sound leaves only if you choose our speech service.
Files: MP4 or MOV up to ten minutes in; an MP4 with the captions burned in out. SRT, VTT, ASS and text files are free without limit for recordings up to ten minutes. A longer recording, up to 90 minutes on a computer, gives its script and those files: the first ten minutes free, all of it with Pro.
Languages and styles: captions in the language spoken, twelve Indian languages heard on your device, translation into 37 languages, 20 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: fifteen caption tools compared, from the vendors' own pages.