Buzz Chidi Williams
winget install --id=ChidiWilliams.Buzz -e Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
Buzz is a powerful audio transcription and translation tool designed to process audio files offline on your personal computer. Leveraging OpenAI's Whisper technology, Buzz offers seamless transcriptions and translations in multiple languages.
Key Features:
- Offline Processing: Transcribe and translate audio without an internet connection for enhanced privacy.
- Multi-Language Support: Handle various languages, making it versatile for diverse users.
- File Flexibility: Works with numerous audio file formats, ensuring compatibility across different devices.
- Whisper Integration: Utilizes Whisper's advanced models for accurate results.
- Installation Options: Install easily via winget or other methods for convenience.
Audience & Benefit: Ideal for privacy-conscious individuals, content creators, linguists, educators, and professionals needing efficient audio processing. Buzz empowers users to manage audio files independently, enhancing productivity without relying on external services.
Buzz is a reliable tool for those seeking efficient, offline audio solutions, offering flexibility and accuracy in transcription and translation.
README
[简体中文] <- 点击查看中文页面。
Buzz
Documentation | Buzz Captions on the App Store
Transcribe and translate audio offline on your personal computer. Powered by OpenAI's Whisper.
Buzz is better on the App Store. Get a Mac-native version of Buzz with a cleaner look, audio playback, drag-and-drop import, transcript editing, search, and much more.
Installation
PyPI
Install ffmpeg
Install Buzz
pip install buzz-captions
python -m buzz
macOS
Install with brew utility
brew install --cask buzz
Or download the .dmg from the releases page.
Windows
Download and run the .exe from the releases page.
App is not signed, you will get a warning when you install it. Select More info -> Run anyway.
Alternatively, install with winget
winget install ChidiWilliams.Buzz
GPU support for PyPI
To have GPU support for Nvidia GPUS on Windows, for PyPI installed version ensure, CUDA support for torch
pip3 uninstall torch torchaudio
pip3 install torch==2.2.2+cu121 torchaudio==2.2.2+cu121 nvidia-cublas-cu12==12.1.3.1 nvidia-cuda-cupti-cu12==12.1.105 nvidia-cuda-nvrtc-cu12==12.1.105 nvidia-cuda-runtime-cu12==12.1.105 nvidia-cufft-cu12==11.0.2.54 nvidia-curand-cu12==10.3.2.106 nvidia-cusolver-cu12==11.4.5.107 nvidia-cusparse-cu12==12.1.0.106 nvidia-nccl-cu12==2.19.3 nvidia-nvtx-cu12==12.1.105 --extra-index-url https://download.pytorch.org/whl/cu121 --extra-index-url https://pypi.ngc.nvidia.com
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
sudo snap connect buzz:password-manager-service
Latest development version
For info on how to get latest development version with latest features and bug fixes see FAQ.
Screenshots
