mirror of https://github.com/chidiwilliams/buzz.git synced 2026-03-14 06:35:47 +01:00

No description

Python 99%
Makefile 0.8%
Inno Setup 0.2%

Find a file

Raivis Dejus 1346c68c72 Pre release polishes (#1416 )		2026-03-08 08:47:19 +00:00
.github/workflows	Add auto update check for Windows adn Mac (#1404 )	2026-02-28 14:39:04 +00:00
.run	fix: whisper binary missing in package	2024-01-10 09:28:30 +00:00
.vscode	Put FileTranscriber in QRunnable (#203 )	2022-12-04 18:30:24 +00:00
assets	chore: update logo	2024-03-15 01:28:59 +00:00
buzz	Pre release polishes (#1416 )	2026-03-08 08:47:19 +00:00
ctc_forced_aligner@1f0a5f860d	Add speaker identification2 (#1290 )	2025-12-02 21:39:24 +02:00
deepmultilingualpunctuation@5a0dd7f4fd	Add speaker identification2 (#1290 )	2025-12-02 21:39:24 +02:00
demucs_repo@4273070a70	Fix speech separation (#1301 )	2025-12-05 22:57:14 +02:00
dll_backup	Adding support for Vulkan for whisper.cpp (#1194 )	2025-07-20 16:53:36 +03:00
docs	Pre release polishes (#1416 )	2026-03-08 08:47:19 +00:00
flatpak	Add speaker identification2 (#1290 )	2025-12-02 21:39:24 +02:00
patches	Fix for windows crashes (#1387 )	2026-02-20 15:47:13 +02:00
readme	Update documentation (#1337 )	2026-01-05 06:37:30 +00:00
share	Live recording improvements (#1413 )	2026-03-07 14:48:41 +00:00
snap	Add auto update check for Windows adn Mac (#1404 )	2026-02-28 14:39:04 +00:00
testdata	Adding fix for multi-byte segments in whisper.cpp (#734 )	2024-05-14 23:29:43 +00:00
tests	Recording transcriber improvements (#1414 )	2026-03-07 19:26:29 +00:00
whisper.cpp@2eeeba56e9	Add cvs export (#1400 )	2026-02-27 14:14:18 +00:00
whisper_diarization@fcbd1930d8	Add speaker identification2 (#1290 )	2025-12-02 21:39:24 +02:00
.coveragerc	Additional tests (#1393 )	2026-02-22 18:00:23 +00:00
.gitignore	1292 fix speech dependencies (#1302 )	2025-12-06 16:51:40 +00:00
.gitmodules	Fix speech separation (#1301 )	2025-12-05 22:57:14 +02:00
.pre-commit-config.yaml	Add pip installation (#615 )	2023-10-28 18:32:31 +01:00
.pylintrc	Put FileTranscriber in QRunnable (#203 )	2022-12-04 18:30:24 +00:00
.python-version	Whispercpp cli uv (#1264 )	2025-11-01 18:31:01 +02:00
buzz.desktop	Fix terminal value in .desktop file (#487 )	2023-06-17 07:35:10 +01:00
Buzz.spec	1389 add folder import (#1398 )	2026-02-27 09:11:51 +00:00
CLAUDE.md	Fix chinease word level timestamps (#1355 )	2026-01-16 12:31:48 +00:00
CODE_OF_CONDUCT.md	Create CODE_OF_CONDUCT.md (#896 )	2024-08-31 07:29:28 +00:00
CONTRIBUTING.md	Update documentation (#1337 )	2026-01-05 06:37:30 +00:00
entitlements.plist	Fix audio entitlement (#53 )	2022-10-11 20:21:06 +00:00
hatch_build.py	Fix for windows crashes (#1387 )	2026-02-20 15:47:13 +02:00
installer.iss	Adding option to delete saved models and files on uninstall (#1291 )	2025-11-24 19:59:21 +00:00
LICENSE	Create LICENSE	2022-09-26 00:49:28 +01:00
main.py	Add Snapcraft (#486 )	2023-06-12 13:09:08 +01:00
Makefile	Adding VAD to whisper.cpp to reduce hallucinations on audio w silences (#1412 )	2026-03-07 05:58:04 +00:00
msgfmt.py	Fix for localizations, adding Latvian translatiosn (#752 )	2024-05-24 12:28:14 +03:00
pyproject.toml	Youtube download update (#1396 )	2026-02-26 20:24:35 +00:00
pytest.ini	Implemented presentation window for live transcripts #1306 (#1323 )	2025-12-23 19:29:34 +00:00
README.ja_JP.md	Fix for HF hub download certificates (#1353 )	2026-01-16 09:18:27 +00:00
README.md	Add auto update check for Windows adn Mac (#1404 )	2026-02-28 14:39:04 +00:00
uv.lock	Pre release polishes (#1411 )	2026-03-06 19:26:19 +02:00

README.md

[简体中文] <- 点击查看中文页面。

Buzz

Documentation

Transcribe and translate audio offline on your personal computer. Powered by OpenAI's Whisper.

Features

Transcribe audio and video files or Youtube links
Live realtime audio transcription from microphone
- Presentation window for easy accessibility during events and presentations
Speech separation before transcription for better accuracy on noisy audio
Speaker identification in transcribed media
Multiple whisper backend support
- CUDA acceleration support for Nvidia GPUs
- Apple Silicon support for Macs
- Vulkan acceleration support for Whisper.cpp on most GPUs, including integrated GPUs
Export transcripts to TXT, SRT, and VTT
Advanced Transcription Viewer with search, playback controls, and speed adjustment
Keyboard shortcuts for efficient navigation
Watch folder for automatic transcription of new files
Command-Line Interface for scripting and automation

Installation

macOS

Download the .dmg from the SourceForge.

Windows

Get the installation files from the SourceForge.

App is not signed, you will get a warning when you install it. Select More info -> Run anyway.

Linux

Buzz is available as a Flatpak or a Snap.

To install flatpak, run:

flatpak install flathub io.github.chidiwilliams.Buzz

To install snap, run:

sudo apt-get install libportaudio2 libcanberra-gtk-module libcanberra-gtk3-module
sudo snap install buzz

PyPI

Install ffmpeg

Ensure you use Python 3.12 environment.

Install Buzz

pip install buzz-captions
python -m buzz

GPU support for PyPI

To have GPU support for Nvidia GPUS on Windows, for PyPI installed version ensure, CUDA support for torch

pip3 install -U torch==2.8.0+cu129 torchaudio==2.8.0+cu129 --index-url https://download.pytorch.org/whl/cu129
pip3 install nvidia-cublas-cu12==12.9.1.4 nvidia-cuda-cupti-cu12==12.9.79 nvidia-cuda-runtime-cu12==12.9.79 --extra-index-url https://pypi.ngc.nvidia.com

Latest development version

For info on how to get latest development version with latest features and bug fixes see FAQ.

Support Buzz

You can help the Buzz by starring 🌟 the repo and sharing it with your friends.