Buzz
Transcribe and translate recordings or live microphone audio on your own computer with Whisper models.
MIT · Downloads from github.com
- License
- MIT
- Open source
- Source
- GitHub
- chidiwilliams
- Verified
- 2026
About Buzz
Buzz runs OpenAI's Whisper speech-recognition models locally to turn audio and video files, or live microphone input, into text and translations. Transcripts can be reviewed alongside playback and exported as TXT, SRT or VTT subtitles.
Models are downloaded on first use, and processing speed depends heavily on your hardware and the model size you pick. GitHub releases include separate Apple silicon and Intel macOS builds, and a command-line interface is available for scripted jobs.
Information
- Source code
- chidiwilliams/buzz
- License
- MIT
- Website
- chidiwilliams.github.io
- Download
- github.com
- Category
- AI
- Evidence checked
- Tags
Maco links to each project’s official download. Check its release notes for macOS version and Apple silicon support. The verification date records our license and source review, not a security audit.
Sources and image credits
- github.com/chidiwilliams/buzz
- github.com/chidiwilliams/buzz/blob/main/LICENSE
- github.com/chidiwilliams/buzz/releases
- chidiwilliams.github.io/buzz
- icon.png: Chidi Williams and Buzz contributors. MIT repository asset; trademarks retained.
License and artwork notices