Video & audioRepo
Whisper
Turn audio into text on your own computer, in many languages.
// WHAT IT'S FOR
Whisper is OpenAI's open-source speech recognition model. You install it with Python, it needs FFmpeg, and in the terminal you type whisper and the file name to get the transcript. Use it to turn interviews, meetings or voice notes into text without uploading them to an outside service. Accuracy varies a lot by language.
ON GITHUB
- Stars
- ★ 110k
- Last change
- Aug 31, 2026
- License
- MIT
- Language
- Python
Data as of Oct 9, 2026
It runs in the terminal. If you've never opened one, start with this guide: use the terminal without being scared of it