A browser-based implementation of KittenTTS using ONNX Runtime Web for client-side text-to-speech synthesis.

This implementation uses the following key technologies:

• React - UI framework
• TypeScript - Type safety and better development experience
• ONNX Runtime Web - Machine learning inference in the browser
• Vite - Build tool and development server

1. Install dependencies:

   pnpm install

2. Start development server:

   pnpm run dev

3. Open in browser: Navigate to http://localhost:5173

This project follows the same license as the original KittenTTS project (Apache 2.0).

• KittenTTS GitHub Repository
• ONNX Runtime Web Documentation
• Web Audio API Documentation