Buzz
A desktop app under MIT that transcribes and translates audio and video files, YouTube links and a live microphone offline with Whisper, with speaker identification and SRT, VTT and TXT export.
What it does
Buzz "transcribes and translates audio offline on your personal computer", powered by Whisper. It handles audio and video files and YouTube links, and it has live microphone transcription with a presentation window for showing captions on a screen.
The README lists speaker identification in transcribed media, speech separation before transcription for noisy audio, several Whisper backends (CUDA, Apple Silicon, Vulkan through whisper.cpp) plus Hugging Face Whisper-type models, export to TXT, SRT and VTT, a watch folder that transcribes new files automatically, a command line, and a plugin system with an AI summary plugin. Which language model the summary plugin uses is not stated.
What it replaces
Buzz replaces Otter.ai and Fireflies.ai for recordings: drop a file in, get a transcript with speakers, export subtitles. With the microphone mode it covers a meeting you are in the room for.
Where it falls short: it does not capture system audio from a call in the README's description, so the far side of a video call is not covered the way Meetily and Vibe cover it. Push-to-talk dictation into other apps is not part of it.
How it runs
macOS and Windows installers from the project's SourceForge page, Linux through Flatpak, Snap or AppImage, or pip install buzz-captions with Python 3.12 and ffmpeg. NVIDIA CUDA support can be installed from inside the app on version 1.4.6 or later.
Who it fits
Anyone who transcribes files regularly, wants subtitles out, and wants nothing uploaded. Someone recording a live video call should look at Meetily, Vibe or OpenWhispr.
Limits the README states
"Buzz now requires Apple silicon. The last version to support Intel Macs is 1.4.5." The Windows build is unsigned, so the installer shows a warning.
Sources
- Buzz README and MIT LICENSE: github.com/chidiwilliams/buzz, read 2026-09-16.
More meeting transcription
A meeting assistant under MIT that records your microphone and system audio together, transcribes live on your machine with Whisper or Parakeet, and summarises with a language model you choose.
An offline transcription app under MIT that records system audio and the microphone, supports Whisper, Parakeet and Nemotron models, labels speakers, and exports SRT, VTT, TXT, HTML, PDF, JSON and DOCX.
Added September 16, 2026. Found an error on this page? Write to reveneau@licheo.com and it gets fixed in the next weekly pass.
Running one of these inside your own environment, with your own data and your own security rules, is the kind of work Reveneau does. Read how a forward deployed engagement works.