xenova/whisper-web

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

3338 stars · 427 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A browser-based speech recognition app that runs OpenAI's Whisper models entirely client-side using Transformers.js. It transcribes audio without any server-side processing, with an experimental WebGPU branch for GPU acceleration.

Use cases

• transcribe audio recordings in the browser
• run whisper speech-to-text locally without a server
• private offline speech recognition
• add subtitles to audio files client-side
• demo in-browser machine learning transcription

When to choose

• you need privacy-preserving transcription with no audio leaving the device
• you want a zero-backend, browser-only speech-to-text demo or app
• you're showcasing Transformers.js / WebGPU capabilities

When to avoid

• you need high-accuracy or long-audio production transcription at scale
• you need server-side batch processing or API integration
• you need broad browser compatibility including older Firefox versions

Facets

application · maturity active

speech-recognition machine-learning audio-processing speech-processing artificial-intelligence web-development browser whisper transformersjs client-side-ml transcription webgpu vite web-server javascript

Member repositories

For agents

markdown · JSON · MCP: product_card(name="xenova/whisper-web")