Buzz
Buzz is an MIT-licensed desktop app that transcribes and translates audio and video files, YouTube links and a live microphone offline with Whisper. It identifies speakers, separates speech from noise before transcribing, exports TXT, SRT and VTT, watches a folder for new files, and has a command line and a plugin system. It runs on Apple Silicon Macs, Windows and Linux, or installs with pip.
What does Buzz do?
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.
Key facts
- Licence: MIT.
- Inputs: audio and video files, YouTube links, and live microphone transcription with a presentation window for on-screen captions.
- Speaker identification in transcribed media, and speech separation before transcription for noisy audio.
- Whisper backends: CUDA, Apple Silicon and Vulkan through whisper.cpp, plus Hugging Face Whisper-type models.
- Exports: TXT, SRT and VTT. A watch folder transcribes new files automatically.
- A command line, and a plugin system with an AI summary plugin whose model the README does not name.
- Installs: macOS .dmg and a Windows installer from SourceForge, Linux via Flatpak, Snap or AppImage, or pip install buzz-captions with Python 3.12 and ffmpeg.
- Buzz now requires Apple Silicon; the last version for Intel Macs is 1.4.5. The Windows build is unsigned, so the installer shows a warning.
What does it replace, and where does it fall short?
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 does Buzz run?
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 is Buzz for?
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.
What limits does the README state?
"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.
Questions people ask
Is Buzz open source?
Yes. Buzz is MIT licensed, an OSI approved licence with no use restrictions. It builds on OpenAI's Whisper, whose code and weights are also MIT, and on whisper.cpp for its local backends.
Does Buzz work offline?
Yes. The README's own description is "Transcribe and translate audio offline on your personal computer." The Whisper model runs locally through whisper.cpp or the Hugging Face model family, so files and microphone audio stay on the machine.
Can Buzz record the other side of a video call?
The README describes live transcription from the microphone, with a presentation window for captions. It does not describe capturing system audio, so the far side of a call playing through speakers is not covered the way Meetily and Vibe cover it.
How does Buzz compare with Otter.ai?
For recordings and files, Buzz does the transcription, speaker labels and subtitle export locally with no upload and no subscription. Otter joins live calls as a bot and shares searchable notes across a team, which Buzz does not. The alternatives to Otter.ai page places Buzz as the pick for recordings, files and YouTube links.
Which Macs does Buzz run on?
Apple Silicon only in current versions. The README states that the last version to support Intel Macs is 1.4.5, which remains downloadable. On Windows and Linux there is no such cut-off, and NVIDIA CUDA support can be installed from inside the app on 1.4.6 or later.
Sources
- Buzz README and MIT LICENSE: github.com/chidiwilliams/buzz, read 2026-09-16.
Compared with the others
On the open-source alternatives to Otter.ai page, Buzz is the pick for recordings, files and youtube links. MIT. Transcribes and translates files and links offline with Whisper, identifies speakers, and exports TXT, SRT and VTT, with a watch folder and a command line.
Also on that page: Meetily for live calls, entirely on your machine, OpenWhispr for call detection and speaker labels, Vibe for system audio and document exports.
On the open-source alternatives to Fireflies.ai page, Buzz is the pick for recordings, files and youtube links. MIT. Transcribes and translates files and links offline with Whisper, identifies speakers, and exports TXT, SRT and VTT, with a watch folder and a command line.
Also on that page: Meetily for live calls, entirely on your machine, OpenWhispr for call detection and speaker labels, Vibe for system audio and document exports.
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. Every claim above comes from the project's README, LICENSE or model card, read on September 16, 2026, or from the GitHub API on the date shown in the panel. Found an error? Write to reveneau@licheo.com and it is fixed in the next weekly pass. Repository: github.com/chidiwilliams/buzz.
Want Buzz running on your own servers?
Reveneau sets it up on your hardware, connects it to your product, and builds the software around it.