useVoice

useVoice(options?: UseVoiceOptions): UseVoiceResult

Defined in: src/react/useVoice.ts:200 

React hook for recording voice and transcribing it on-device using Whisper.

Transcription runs entirely in the browser via @huggingface/transformers (ONNX Runtime + WebAssembly). The Whisper model (~40 MB for tiny) is downloaded on first use and cached by the browser.

Parameters

Returns

UseVoiceResult

Example

const { startRecording, stopRecording, transcribe } = useVoice();
 
const handleStop = async () => {
  const recording = await stopRecording();
  const { text } = await transcribe(recording);
  // Send text to LLM via useChat
};