Show HN: Speech-to-text in the browser with Whisper and Parakeet, no server

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}); }

Try it in the browser

Upload audio or video and transcribe in one step.

OPFS cache, manual model download, and live mic + VAD.