# FL33TW00D/whisper-turbo

Cross-Platform, GPU Accelerated Whisper 🏎️

Repository: https://github.com/FL33TW00D/whisper-turbo
Canonical: https://ross.abutalabs.com/products/whisper-turbo
Homepage: https://whisper-turbo.com
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: machine-learning, rust, webgpu, whisper, audio, speech-recognition, windows
Last push: 2024-02-27T14:38:23+00:00

## Health v2 (maintenance only)
Score: 19/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 79
- inputs: {"age_days": 1111, "days_push": 918, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1794, forks 82 (observed 2026-08-28T04:05:37.362538+00:00)

## What it is
Whisper Turbo is a fast, cross-platform, GPU-accelerated implementation of OpenAI's Whisper speech recognition model, built on the Ratchet Rust/WebGPU library. It is designed to run entirely client-side in the browser or Electron apps, transcribing audio without a server.

## Use cases
- transcribe audio recordings in the browser
- run whisper speech-to-text fully client-side
- gpu accelerated transcription in an electron app
- add offline speech recognition to a web app
- convert voice recordings to text without uploading to a server
- record audio and transcribe it in the browser

## When to choose
- you need privacy-preserving, fully client-side speech-to-text
- you want GPU acceleration via WebGPU in Chromium browsers
- you're building a browser or Electron app that transcribes audio
- you want to avoid server costs for transcription

## When to avoid
- you need server-side batch transcription of large audio volumes
- your users are on browsers without WebGPU support (e.g. Firefox, Safari, Linux)
- you need the smallest possible model download (models range from ~50MB to ~1GB)
- you need production-grade stability guarantees

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, machine-learning, gpu-computing, audio-processing
- domain: speech-processing, machine-learning, web-development
- platform: browser, cross-platform, wasm
- tags: whisper, webgpu, transcription, client-side, typescript, rust, web-server

## Member repositories
- FL33TW00D/whisper-turbo (main) score 19

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:37.362538+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 2026-08-30T03:22:52.457123+00:00, confidence not recorded.
  - readme: https://github.com/FL33TW00D/whisper-turbo (fetched 2026-08-28T04:05:37.362538+00:00, sha ea3a6c7476ea)
  - homepage: https://whisper-turbo.com (fetched 2026-08-29T11:01:53.064180+00:00, sha 2ac9f17210bf)
  - registry_npm: https://registry.npmjs.org/whisper-turbo (fetched 2026-08-29T11:01:53.073017+00:00, sha c134e4ac8266)
- Data as of 2026-08-30T08:39:29.467469+00:00.