Transcribe speech from your microphone into text notes in real time — right in your browser. Everything runs locally in your browser so your voice never leaves your computer.
Speech is transcribed with OpenAI's Whisper models, run by Transformers.js 3.5.1 on ONNX Runtime Web — using WebGPU when available, else CPU.
Microphone audio is captured with the Web Audio API, resampled to 16 kHz mono, and transcribed in short windows that are committed to your notes as you pause.
Everything runs on your machine — no server, no upload. The model is loaded from a CDN and downloads once, then is cached by the browser.