How it works
- Drop your MP4. MOV and WebM work too.
- Press Make captions.
- Press SRT to download the file.
Some MP4 files carry a subtitle track and a tool like ffmpeg can copy it out. Most do not, particularly phone recordings and screen captures. For those, the only route is speech recognition, which is what this does.
The audio is decoded in your browser, resampled to 16 kHz, and passed to Whisper. Each word gets a start and end time, and the cues are cut at pauses and sentence ends. The result is a file you can load in any editor or player, or upload to YouTube.
Check names and numbers in the list before you download. Those are where recognition slips most.
Questions
Does the MP4 have to be small?
Your browser has to hold it in memory. Files up to a few hundred megabytes usually work on a laptop.
Will it keep the language of the video?
Yes by default. Tick translate to get English instead.