browser-whisper

v1.1.0

Native WebGPU audio transcription. Connects directly to WebCodecs (mediabunny) and Transformers.js for zero-server inference.

bun add browser-whisper
import { BrowserWhisper } from 'browser-whisper';

const whisper = new BrowserWhisper({ model: 'whisper-base' });

for await (const { text, start, end } of whisper.transcribe(file)) {
    console.log(`[${start}-${end}s]: ${text}`);
}
Model Languages language
whisper-tiny Multilingual · 99 languages ✓
whisper-base Multilingual · 99 languages ✓
whisper-small Multilingual · 99 languages ✓
moonshine-tiny English only —
moonshine-base English only —
distil-whisper-small English only —
parakeet-ctc-0.6b English only —
parakeet-tdt-0.6b-v3 25 European languages, auto-detected (WebGPU only) —

Model credits: Parakeet TDT 0.6B v3 by NVIDIA, licensed under CC BY 4.0. Changes: converted to ONNX and quantized by istupakov/ysdede; runs with parakeet.js (MIT). Parakeet CTC 0.6B by NVIDIA, licensed under CC BY 4.0. Changes: converted to ONNX and quantized by onnx-community. Whisper by OpenAI (MIT). Moonshine by Useful Sensors (MIT). Distil-Whisper by Hugging Face (MIT). Lite-Whisper by efficient-speech (Apache-2.0). ONNX exports by onnx-community. All third-party notices.

Pass any BCP-47 code as language to skip auto-detection — slightly faster and more accurate when the language is known.

afamarasaz babebgbnbo brbscacscy dadeelenes eteufafifo frglguhahaw hehihrhthu hyidisitja jwkakkkmkn kolalblnlo ltlvmgmimk mlmnmrmsmt mynenlnnno ocpaplpspt rorusasdsi skslsnsosq srsusvswta tetgthtktl trttukuruz viyiyozhyue