# chidiwilliams/buzz

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

Repository: https://github.com/chidiwilliams/buzz
Canonical: https://ross.abutalabs.com/products/chidiwilliams-buzz
Homepage: https://chidiwilliams.github.io/buzz
Language: Python
License: MIT
License Family: permissive
Topics: whisper
Last push: 2026-08-23T16:46:15+00:00

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 87, longevity 100
- inputs: {"age_days": 1439, "days_push": 10, "days_rel": 10, "gap_med": 50.5, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 21147, forks 1559 (observed 2026-08-28T04:11:30.601515+00:00)

## What it is
Buzz is a cross-platform desktop application that transcribes and translates audio and video offline using OpenAI's Whisper models. It offers a GUI plus CLI, live microphone transcription, speaker identification, and export to TXT, SRT, and VTT.

## Use cases
- transcribe audio files to text offline
- generate subtitles in srt or vtt format
- transcribe youtube videos
- live transcription from microphone during presentations
- identify speakers in recorded meetings
- translate foreign-language audio to english

## When to choose
- you need offline transcription without sending audio to the cloud
- you want a gui plus cli for batch or scripted transcription
- you need subtitle export and speaker diarization in one tool
- you have an nvidia gpu, apple silicon, or vulkan-capable gpu for acceleration

## When to avoid
- you need a server-side or headless transcription api at scale
- you require cloud-based accuracy or enterprise features
- you still use an intel mac (support ended at version 1.4.5)

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, audio-processing, gui, cli, machine-learning, llm-inference
- domain: speech-processing, media, developer-tools, cross-platform
- platform: windows, python
- tags: whisper, transcription, subtitles, offline, speaker-identification, captioning, audio, macos, linux, desktop, gpu

## Member repositories
- chidiwilliams/buzz (main) score 95

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:30.601515+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:58:29.191199+00:00, confidence not recorded.
  - readme: https://github.com/chidiwilliams/buzz (fetched 2026-08-28T04:11:30.601515+00:00, sha 6f2bf28219be)
  - homepage: https://chidiwilliams.github.io/buzz (fetched 2026-08-29T07:57:00.069576+00:00, sha 5527ff15434a)
- Data as of 2026-08-30T08:39:29.467469+00:00.