Upload a video and get a transcript with timestamps. It runs in your browser, so your video is not uploaded.
Use a direct link to a video file (.mp4, .webm). YouTube and Vimeo page links don’t work. The host must allow cross-origin access, or capture will be blocked; if so, download the file and use “Video from file”.
Checking the downloader connection...
Checking the downloader connection...
Shortcuts: ←/→ step one frame (Shift = 1 second), Space plays or pauses, S snaps the current frame.
If a Save button doesn’t start a download here, press and hold (or right-click) the image and choose “Save image”.
It is usually good for clear speech and gets worse with background noise, music, strong accents or several people talking at once. Always read through the result before you publish it.
You can choose English or Tagalog, or leave it on auto-detect. Auto-detect may also recognise other languages, with varying accuracy.
No. The audio is read and transcribed inside your browser. Only the speech model itself is downloaded from a public content network the first time you use it.
Your browser has to download the speech model once. It is saved on your device afterwards, so later runs start much faster. Long videos still take a few minutes because the work happens on your own computer.
Yes. Press Save .srt to download a subtitle file with timestamps, or Save .txt for plain text.
Videos up to about 20 minutes work best. Very long or very large files can use a lot of memory in the browser. If that happens, split the video into shorter parts.
Only need a picture from the video? Use the video frame extractor.