Whisper WebGPU
by Xenova / Hugging Face
GPU-accelerated Whisper inference in the browser via WebGPU.
Looking at Whisper WebGPU? Try this first.
Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min
TL;DR
Best for real-time Whisper transcription in the browser with on-device GPU acceleration. Pricing: free.
Category
Products
License
Apache-2.0
Stars
★ 16.2k
Last push
2026-07-31
Pricing
free
Platforms
Web (Chrome/Edge with WebGPU)
What it is
A WebGPU build of Whisper running through Transformers.js. Significantly faster than the WebAssembly path and the closest in-browser experience to native inference.
Best for: Real-time Whisper transcription in the browser with on-device GPU acceleration.
Watch out for: Requires WebGPU-capable browser (Chrome 113+, Edge); model weights cached after first download.
Watch out for: Requires WebGPU-capable browser (Chrome 113+, Edge); model weights cached after first download.
Install / use
Go to Whisper WebGPU huggingface.coFeatures
| Speaker diarization | No |
| Word-level timestamps | Yes |
| Streaming / real-time | No |
| Languages supported | 99 |
| HIPAA eligible | No |
Links
Whisper WebGPU vs Whipscribe
| Feature | Whisper WebGPU | Whipscribe |
|---|---|---|
| Category | Products | Transcription APIs |
| Pricing | Not verified | $4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup |
| Speaker diarization | Not verified | Yes |
| Word timestamps | Not verified | Yes |
| Streaming | Not verified | No |
| Languages | 99 | 99 |
| Platforms | Web (Chrome/Edge with WebGPU) | Web, API, MCP |
Alternatives to Whisper WebGPU
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.