![](\"https://i.imgur.com/ypVzqbg.png\")
\n\n \n
\n ![\"Documentation\"](\"https://img.shields.io/badge/Docs-blue?logo=ReadTheDocs&logoColor=white\"){kind=icon}
\n ![\"GitHub](\"https://img.shields.io/github/stars/OpenSourceAGI/qwksearch-research-agent\")
![\"NPM](\"https://img.shields.io/npm/dm/use-voice-control.svg\")
\n ![\"npm](\"https://img.shields.io/npm/v/use-voice-control.svg\")
\n ![\"NPM](\"https://img.shields.io/npm/dt/use-voice-control.svg\")
\n ![\"TypeScript](\"https://img.shields.io/npm/types/use-voice-control\")
\n
\n ![\"GitHub](\"https://img.shields.io/github/issues/OpenSourceAGI/qwksearch-research-agent?logo=github\")
![\"Open](\"https://img.shields.io/github/issues-pr/OpenSourceAGI/qwksearch-research-agent?logo=github&label=PRs\")
![\"Merged](\"https://img.shields.io/github/issues-pr-closed/OpenSourceAGI/qwksearch-research-agent?logo=github&label=PRs%20merged&color=8957e5\")
![\"GitHub](\"https://img.shields.io/github/discussions/OpenSourceAGI/qwksearch-research-agent\")
![\"GitHub](\"https://img.shields.io/github/last-commit/OpenSourceAGI/qwksearch-research-agent.svg\")
\n
\n ![\"Open](\"https://developer.stackblitz.com/img/open_in_stackblitz.svg\")
\n ![\"Bun\"](\"https://img.shields.io/badge/Bun-14151A?logo=bun&logoColor=white\"){kind=icon}
![\"TypeScript\"](\"https://img.shields.io/badge/TypeScript-3178C6?logo=typescript&logoColor=white\"){kind=icon}
![\"React\"](\"https://img.shields.io/badge/React-20232A?logo=react&logoColor=white\"){kind=icon}
![\"Vite\"](\"https://img.shields.io/badge/Vite-646CFF?logo=vite&logoColor=white\"){kind=icon}
![\"Vitest\"](\"https://img.shields.io/badge/Vitest-6E9F18?logo=vitest&logoColor=white\"){kind=icon}
\n NPM β’\n GitHub β’\n Discord\n
\n\n## use-voice-control\n\nReact hooks and components for seamless voice control and speech I/O (Speech-to-Text and Text-to-Speech). Build voice-enabled applications with client-side speech recognition and server-side or client-side speech synthesis.\n\n```bash\nnpm install use-voice-control\n```\n\nOr read a document aloud straight from the terminal, no install and no code:\n\n```bash\nnpx use-voice-control README.md -o readme.wav\n```\n\n---\n\n## π€ Features\n\n### Speech-to-Text (STT)\n- **Moonshine.js**: Fast, accurate client-side speech recognition running entirely in the browser\n- **WebRTC Audio Capture**: Real-time microphone input with automatic gain control\n- **Multi-language Support**: Recognize speech in 100+ languages\n- **Offline-First**: No external API calls required for STT\n\n### Text-to-Speech (TTS)\n- **Kokoro TTS**: Natural-sounding synthesis on Node.js/Edge with 16 pre-trained voices\n- **Deepgram TTS**: Enterprise-grade speech synthesis with 12 Aura voices\n- **Server & Client Support**: Run on backend or stream to client\n- **Multiple Output Formats**: WAV, PCM, or raw audio buffers\n\n### Markdown & Files\n\n- **Markdown aware**: `#`, `**` and backticks are never read out β headings are\n spoken as headings, code blocks are announced, links keep their text\n- **Files in, audio out**: `.md` and `.txt` files rendered to WAV from the\n [command line](#-command-line) or from Node\n- **Local synthesis**: Kokoro runs on the CPU, so document text never leaves the machine\n\n### React Integration\n- **Custom Hooks**: `useVoiceControl()`, `useSpeechRecognition()`, `useSpeechSynthesis()`\n- **Pre-built Components**: Audio recorder, voice selector, playback controls\n- **State Management**: Streaming, loading, error handling baked in\n\n---\n\n## π Quick Start\n\n### Installation\n\n```bash\nnpm install use-voice-control\n```\n\n### Basic STT Example\n\n```ts\nimport { useSpeechRecognition } from 'use-voice-control/hooks';\n\nexport function VoiceInput() {\n const { isListening, transcript, startListening, stopListening } = useSpeechRecognition({\n language: 'en-US'\n });\n\n return (\nYou said: {transcript}
\n