chidiwilliams/buzz

Analysis updated 2026-06-21

★ 19,205PythonAudience · generalComplexity · 3/5Setup · moderate

Mindmap

mindmap
  root((buzz))
    What it does
      Offline transcription
      Audio to text
      Subtitle export
    Tech stack
      Python
      OpenAI Whisper
      CUDA Vulkan GPU
    Input types
      Audio files
      Video files
      Live microphone
      YouTube links
    Output formats
      TXT
      SRT subtitles
      VTT subtitles

mindmap root((buzz)) What it does Offline transcription Audio to text Subtitle export Tech stack Python OpenAI Whisper CUDA Vulkan GPU Input types Audio files Video files Live microphone YouTube links Output formats TXT SRT subtitles VTT subtitles

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Transcribe an interview recording to text on your own computer without uploading to any cloud service.

USE CASE 2

Generate subtitle files (SRT or VTT) for a video automatically from the spoken audio.

USE CASE 3

Caption a presentation or meeting recording offline when privacy is important.

USE CASE 4

Automate transcription of a folder of audio files using the built-in watch folder feature.

What is it built with?

PythonWhisperCUDAVulkan

How does it compare?

	chidiwilliams/buzz	swe-agent/swe-agent	iperov/deepfacelab
Stars	19,205	19,210	19,188
Language	Python	Python	Python
Setup difficulty	moderate	moderate	hard
Complexity	3/5	4/5	4/5
Audience	general	researcher	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

GPU acceleration requires CUDA (Nvidia) or a Vulkan-compatible GPU, CPU-only mode works but is significantly slower.

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

Using Buzz's CLI, write a shell script that watches a folder and automatically transcribes any new MP3 files into SRT subtitle files.

Prompt 2

How do I set up Buzz with GPU acceleration on an Apple Silicon Mac to speed up Whisper transcription?

Prompt 3

I have a 2-hour interview recording, use Buzz to transcribe it with speaker identification enabled and export as a plain text file.

Prompt 4

Walk me through using Buzz to transcribe a YouTube video link into a searchable text document.

Frequently asked questions

What is buzz?

A free offline desktop app that converts spoken audio and video into text using OpenAI's Whisper AI model, running entirely on your own computer with no data sent to any external server.

What language is buzz written in?

Mainly Python. The stack also includes Python, Whisper, CUDA.

How hard is buzz to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is buzz for?

Mainly general.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub chidiwilliams on gitmyhub

Verify against the repo before relying on details.