Drop your audio. Transcript in seconds. 30 free min, then $2 = 200 min
Buzz
A free, MIT-licensed desktop GUI around Whisper that runs on macOS, Windows, and Linux — file drop, live microphone, batch jobs, and offline transcription with no terminal required.
MIT-licensed cross-platform desktop app that wraps Whisper, whisper.cpp, and faster-whisper behind a single GUI. Runs entirely offline; supports file batches, live mic, YouTube URLs, and exports to TXT / SRT / VTT / CSV.
Best for non-technical users on Windows or Linux who want Whisper without a terminal, plus Mac users who'd rather click than type. Free Classic edition on GitHub; an optional paid Buzz on macOS ships on the App Store with a native UI.
What it is
Buzz is the open-source cross-platform desktop app for Whisper. File drop, live microphone, multiple model sizes, batch processing — all running locally. Free, MIT-licensed, and the closest OSS equivalent to MacWhisper across all three desktop OSes.
Watch out for: No native diarization; UI is functional rather than polished.
Install / use
pip install buzz-captions
Install paths · pick yours
Buzz ships through four channels — pick whichever matches your OS and packaging preference. Every card links to the canonical project / store page; no direct binary URLs.
The open-source Classic build for Intel + Apple Silicon. Free, MIT-licensed, ships every Whisper backend (Whisper, whisper.cpp, faster-whisper). Distributed through the SourceForge mirror linked from the official docs.
Latest stable: v1.4.4 · 2026-03-14
Native macOS rebuild with a Mac-style UI, transcript search, inline editing, and playback. Paid one-time license — Pro tier gets lifetime updates. Skip Classic if you want App Store sandboxing and signed updates.
Linked from the official Buzz Captions homepage
Official Windows installer published on SourceForge. The binary is unsigned, so SmartScreen will warn — click "More info → Run anyway" once and you're set. Same Whisper backends as the macOS Classic build.
12k+ weekly downloads · Open Source Excellence badge
Sandboxed Flatpak distribution on Flathub. One command and you're running, no Python deps to manage. Same MIT codebase as the other channels.
Updated alongside upstream releases
Snap channel maintained by the author. Pairs with a few apt deps for audio + GTK; install the prereqs once, then connect the password-manager-service plug so the app can persist its settings.
Stable channel · auto-updates via snapd
buzz-captions on PyPI. Useful if you want to script Buzz from a venv, embed it in a pipeline, or run it on a box where you can't install packaged GUIs. Needs Python 3.12 and a system ffmpeg.
Then run: python -m buzz
Setup recipes · pick one and copy
Three working configurations covering the most common Buzz deployments — GUI install on macOS, source build for hacking, and headless batch transcription from a terminal.
Free GUI build for Intel + Apple Silicon. Pulls all three Whisper backends; one-line install assuming Python 3.12 + ffmpeg.
# prereqs (Homebrew shown — any package manager works)
brew install python@3.12 ffmpeg
# install Buzz Classic from PyPI
python3.12 -m venv ~/.buzz-venv
source ~/.buzz-venv/bin/activate
pip install --upgrade pip
pip install buzz-captions
# launch the GUI
python -m buzz
For hacking on Buzz itself, or running an un-tagged build. Uses poetry for deps and the bundled Makefile.
# clone the repo
git clone https://github.com/chidiwilliams/buzz.git
cd buzz
# install Poetry + deps (Python 3.12 required)
pipx install poetry
poetry env use python3.12
poetry install
# pull bundled translations + run
make translation_mo
poetry run python -m buzz
Drop the GUI entirely. Useful for cron jobs, build pipelines, or running on a server. Outputs SRT/VTT/TXT next to each input.
# install once
pip install buzz-captions
# transcribe every audio file in ./inputs to SRT
for f in inputs/*.{mp3,m4a,wav,mp4}; do
[ -e "$f" ] || continue
python -m buzz \
--task transcribe \
--model-type whisper \
--model-size small \
--output-formats srt txt \
--output-directory ./transcripts \
"$f"
done
# swap --model-type to faster_whisper or whisper_cpp
# for ~4× speedup; small/medium/large-v3 sizes available
Features
| Speaker diarization | No |
| Word-level timestamps | Yes |
| Streaming / real-time | Yes |
| Languages supported | 99 |
| HIPAA eligible | No |
Links
- github.com/chidiwilliams/buzz ↗main repo · 19k+ stars · Python + PyQt6 · MIT
- chidiwilliams/buzz · releases ↗release index — version history, changelogs, contributor list
- chidiwilliams.github.io/buzz/docs ↗official documentation — installation, models, CLI flags, FAQ
- buzzcaptions.com ↗product homepage — links to Classic + the paid native-Mac App Store build
- pypi.org/project/buzz-captions ↗PyPI package · pip install buzz-captions · Python 3.12
- flathub.org · io.github.chidiwilliams.Buzz ↗Linux Flatpak — recommended on most distros
- snapcraft.io/buzz ↗Linux Snap channel · auto-updates via snapd
- chidiwilliams/buzz · discussions ↗Q&A + ideas — pinned threads on custom APIs and models
- ggerganov/whisper.cpp ↗one of Buzz's bundled backends — same engine, terminal-only
Buzz vs Whipscribe
| Feature | Buzz | Whipscribe |
|---|---|---|
| Category | Open source | Transcription APIs |
| Pricing | free | free beta |
| Speaker diarization | No | Yes |
| Word timestamps | Yes | Yes |
| Streaming | Yes | No |
| Languages | 99 | 99 |
| Platforms | macOS, Linux, Windows | Web, API, MCP |
Alternatives to Buzz
Frequently asked about Buzz
Is Buzz free?
Yes. Buzz is free and MIT-licensed. You can also grab Buzz Pro from the App Store if you want to pay to support development, but it's not required.
Does Buzz work on Windows and Linux?
Yes — Buzz is cross-platform. macOS users have a free Classic build via buzzcaptions.com and a paid native rebuild on the Mac App Store; Windows is available from SourceForge; Linux ships on Flathub and Snap. Python users can also pip install buzz-captions on any OS.
Does Buzz support speaker diarization?
No native diarization. Buzz transcribes audio and produces text + segment timestamps; it doesn't label speakers.
How does Buzz compare to MacWhisper?
Buzz is the open-source cross-platform equivalent. MacWhisper is macOS-only, closed-source, and more polished. Pick Buzz if you want free + cross-platform; pick MacWhisper if you're on Mac and want a more refined UX.
Can Buzz transcribe in real time from my microphone?
Yes. Buzz supports live microphone input in addition to file transcription.
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.