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

• Real-time transcription and translation from your computer's microphones to text (Demo)
• Import audio and video files and export transcripts to TXT, SRT, and VTT (Demo)

To install Buzz, download the latest version for your operating system. Buzz is available on Mac and Windows.

• Download and open the Buzz-x.y.z-dmg file.
• After the installation window opens, drag the Buzz icon into the folder to add Buzz to your Applications directory.

• Download and run the Buzz-x.y.z.exe file.

To start a live recording:

• Select a recording task, language, quality, and microphone.
• Click Record.

Note: Transcribing audio using the default Whisper model is resource-intensive. If your computer is unable to keep up with real-time transcription, consider turning on GGML inference.

To record audio playing from an application on your computer, you may install an audio loopback driver (a program that lets you create virtual audio devices). The rest of this guide will use BlackHole on Mac, but you can use other alternatives for your operating system (see LoopBeAudio, LoopBack, and Virtual Audio Cable).

1. Install BlackHole via Homebrew

   brew install blackhole-2ch

2. Open Audio MIDI Setup from Spotlight or from /Applications/Utilities/Audio Midi Setup.app.

   

3. Click the '+' icon at the lower left corner and select 'Create Multi-Output Device'.

   

4. Add your default speaker and BlackHole to the multi-output device.

   

5. Select this multi-output device as your speaker (application or system-wide) to play audio into BlackHole.

6. Open Buzz, select BlackHole as your microphone, and record as before to see transcriptions from the audio playing through BlackHole.

To import a file:

• Click Import on the File menu (or Command + O on Mac, Ctrl + O on Windows).
• Choose an audio or video file. Supported formats: "mp3", "wav", "m4a", "ogg", "mp4", "webm", "ogm".
• Select a task, language, quality, and export format.
• Click Run.

(See the Live Recording section for more information about the task, language, and quality settings.)

(Default: off)

Turn this on to use inference from Whisper.cpp. Whisper.cpp runs faster than Whisper's original Python implementation but requires a different set of models for inference. Whisper.cpp currently does not support the "Detect Language" option, and transcription will fall back to the original Whisper inference if selected. See the Whisper.cpp documentation for more information.

To build/run Buzz locally from source, first install the dependencies:

1. Clone the repository

   git clone --recurse-submodules https://github.com/chidiwilliams/buzz

2. Install Poetry.

3. Install the project dependencies.

   poetry install

4. (Optional) To use Whisper.cpp inference, run:

   make libwhisper.so

Then, to run:

poetry run python main.py

To build:

poetry run pyinstaller --noconfirm Buzz.spec

1. Where are the models stored?

   The Whisper models are stored in ~/.cache/whisper. The Whisper.cpp models are stored in ~/Library/Caches/Buzz (Mac OS), ~/.cache/Buzz (Unix), C:\Users/<username>\AppData\Local\Buzz\Buzz\Cache (Windows).

2. What can I try if the transcription runs too slowly?

   Try using a lower quality or turning on GGML inference.