In simple English
This tool turns speech from audio and video files into written text. It runs entirely on your own computer without sending your data to the cloud. You do not pay any subscription fees to use it. It can process files or listen to your microphone in real time. It needs a modern computer to run fast, especially if you use a graphics card.
What it is
Buzz is a desktop application and command-line tool powered by OpenAI's Whisper (an artificial intelligence model that converts spoken words into text). It lets you transcribe media, identify different speakers, and export subtitles.
What it is good for
Content creators and solo builders who want to transcribe interviews, meetings, or videos into text without paying for a cloud transcription service.
- Runs completely offline to keep your audio files private.
- Supports live microphone transcription during events or presentations.
- Exports transcripts to common formats like TXT, SRT, and VTT.
- Large AI models need significant RAM and a powerful graphics card to run quickly.
- Windows and macOS builds may trigger security warnings because the app is not code-signed.
- Older Intel Macs are no longer supported in recent versions.
Paid cloud transcription services like Otter or Descript for basic offline use
FFmpeg (a command-line tool for converting and processing audio and video files)
- openai/whisper111k stars
OpenAI's official command-line tool for the Whisper speech recognition model, but without a graphical interface.
- ggml-org/whisper.cpp55k stars
A lightweight C++ port of Whisper that runs very quickly on local hardware, though it is primarily a command-line utility.
- snapcast/snapcast8.0k stars
A server and clients that play one audio stream in several rooms, kept in time with each other.
- MusicPlayerDaemon/MPD2.8k stars
A background music player with no interface of its own, controlled over a network by separate client programs.
- AcademySoftwareFoundation/OpenTimelineIO2.0k stars
An interchange format and library for editing timelines: the order and length of cuts, and references to the media, but not the media.
flatpak install flathub io.github.chidiwilliams.Buzz