How it works
- Drop the video or audio file.
- Press Make captions. A 3 minute clip is free.
- Press TXT for plain text, or SRT if you want the times.
The transcript comes from Whisper running in your tab, so a private recording stays private. Nobody has to trust a server with a client call or an interview.
TXT gives one line per caption cue with no timestamps, ready to paste into a document. Punctuation and capital letters come from the model. Whisper is good at ordinary speech and weaker on strong background noise, overlapping voices and rare names, so skim the list while the video plays.
The caption list is also the editor. Click a line, correct it, and the exports update. For recordings over 3 minutes and up to 30, the monthly plan covers it, or the $5 pack if you have a few files.
Questions
How long can the video be?
3 minutes free, 30 minutes on a paid plan. Longer files can be cut into parts first.
Can it translate?
Yes. Tick the translate box and any supported language comes out as English text.