explaingit

chidiwilliams/buzz

📈 Trending19,278PythonAudience · vibe coderComplexity · 2/5ActiveLicenseSetup · moderate

TLDR

Free desktop app that converts spoken audio to text offline using OpenAI's Whisper, with no data sent to servers.

Mindmap

mindmap
  root((Buzz))
    What it does
      Transcribe audio files
      Translate to languages
      Real-time microphone
    Features
      Speaker identification
      Noise separation
      Watch folder automation
    Export formats
      TXT files
      SRT subtitles
      VTT subtitles
    Tech stack
      OpenAI Whisper
      GPU acceleration
      CUDA and Vulkan
    Platforms
      macOS
      Windows
      Linux
    Use cases
      Captioning presentations
      Interview transcription

Things people build with this

USE CASE 1

Transcribe interviews, podcasts, or meetings into searchable text files on your computer.

USE CASE 2

Create subtitles for videos by transcribing audio and exporting as SRT or VTT format.

USE CASE 3

Automatically transcribe new audio files as they arrive in a folder using the watch feature.

USE CASE 4

Build automation scripts that convert speech to text via the command-line interface.

Tech stack

PythonOpenAI WhisperCUDAVulkanPyQt

Getting it running

Difficulty · moderate Time to first run · 30min

Whisper model download and CUDA/GPU setup are the main bottlenecks; CPU fallback available but slower.

Free and open-source software; you can use, modify, and distribute it freely.

In plain English

Buzz is a free, offline desktop app that converts spoken audio into text (transcription) and can translate it into other languages, all without sending your audio to any external server. It runs entirely on your own computer, which is useful if privacy matters or you do not have a reliable internet connection. It is powered by OpenAI's Whisper, an open-source speech recognition model. You can use it to transcribe audio and video files, YouTube links, or live audio captured from your microphone in real time. The transcription viewer lets you search the text, control playback speed, and export results as TXT, SRT (subtitle format), or VTT files. It also supports speaker identification, background noise separation for better accuracy, and a watch folder feature that automatically transcribes new files as they appear. GPU acceleration is supported for Nvidia cards (via CUDA), Apple Silicon Macs, and most other GPUs via Vulkan. You would reach for Buzz any time you need to turn audio into text on your own machine, captioning a presentation, transcribing an interview, creating subtitles for a video, or building automation scripts via its command-line interface. It runs on macOS, Windows, and Linux.

Copy-paste prompts

Prompt 1
How do I set up Buzz to transcribe audio files on my Mac without sending data to the cloud?
Prompt 2
Show me how to use Buzz's watch folder feature to automatically transcribe new recordings.
Prompt 3
What command-line options does Buzz have for batch transcribing multiple audio files?
Prompt 4
How do I export Buzz transcriptions as SRT subtitle files for my video project?
Prompt 5
Can I use Buzz to transcribe a YouTube video and get speaker identification?
Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.