Buzz

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

Features

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)
Supports Whisper, Whisper.cpp, and Whisper-compatible Hugging Face models

Installation

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

Mac (macOS 11.7 and above)

Install via brew:

brew install --cask buzz

Or, download and run the Buzz-x.y.z.dmg file.

Windows

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

How to use

Live Recording

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.

Field	Options	Default	Description
Task	"Transcribe", "Translate"	"Transcribe"	"Transcribe" converts the input audio into text in the selected language, while "Translate" converts it into text in English.
Language	See Whisper's documentation for the full list of supported languages	"Detect Language"	"Detect Language" will try to detect the spoken language in the audio based on the first few seconds. However, selecting a language is recommended (if known) as it will improve transcription quality in many cases.
Quality	"Very Low", "Low", "Medium", "High"	"Very Low"	The transcription quality determines the Whisper model used for transcription. "Very Low" uses the "tiny" model; "Low" uses the "base" model; "Medium" uses the "small" model; and "High" uses the "medium" model. The larger models produce higher-quality transcriptions, but require more system resources. See Whisper's documentation for more information about the models.
Microphone	[Available system microphones]	[Default system microphone]	Microphone for recording input audio.

Record audio playing from computer

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).

Install BlackHole via Homebrew
```
brew install blackhole-2ch
```
Open Audio MIDI Setup from Spotlight or from /Applications/Utilities/Audio Midi Setup.app.
Click the '+' icon at the lower left corner and select 'Create Multi-Output Device'.
Add your default speaker and BlackHole to the multi-output device.
Select this multi-output device as your speaker (application or system-wide) to play audio into BlackHole.
Open Buzz, select BlackHole as your microphone, and record as before to see transcriptions from the audio playing through BlackHole.

File import

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.

Field	Options	Default	Description
Export As	"TXT", "SRT", "VTT"	"TXT"	Export file format
Word-Level Timings	Off / On	Off	If checked, the transcription will generate a separate subtitle line for each word in the audio. Enabled only when "Export As" is set to "SRT" or "VTT".

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

Build

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

Poetry

Then:

Clone the repository

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

Install the project dependencies.
```
poetry install
```
(Optional) To use Whisper.cpp inference, run:
```
make buzz/whisper_cpp.py
```
(Optional) To compile the translations, run:
```
make translation_mo
```

Finally, run the app with:

poetry run python main.py

Or build with:

poetry run pyinstaller --noconfirm Buzz.spec

FAQ

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), or C:\Users\<username>\AppData\Local\Buzz\Buzz\Cache (Windows). The Hugging Face models are stored in ~/.cache/huggingface/hub.
What can I try if the transcription runs too slowly?

Try using a lower Whisper model size or using a Whisper.cpp model.

kenmillionaire/buzz