FL33TW00D/whisper-turbo

Health v2 · maintenance only

Adoption not part of the score

1794 stars · 82 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity active

speech-recognition machine-learning gpu-computing audio-processing speech-processing machine-learning web-development browser cross-platform wasm whisper webgpu transcription client-side typescript rust web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="FL33TW00D/whisper-turbo")