AI makes the first draft
Speech recognition produces timed text from the audio in your video. It can miss names, overlap or quiet speech. The editor gives you direct control over the final words and timing.
A draft you can work with
Play, correct, split and merge subtitle lines. Choose an appearance and add your own text or logo layers before rendering. Your project uses cloud storage and processing; the video does not stay exclusively on your device.
One video, different outputs
Export MP4 for visible captions, or use paid SRT/VTT/TXT downloads for another editor or a switchable caption track. For existing subtitle files, the free local tools need no video upload.