shreyask/KittenTTS-WebGPU

1---2title: KittenTTS WebGPU3emoji: 🐱4colorFrom: purple5colorTo: indigo6sdk: static7pinned: false8license: apache-2.09---10 11# KittenTTS WebGPU12 13Text-to-speech running entirely in your browser via WebGPU/WASM. No server needed.14 15## Credits16 17- **Models**: [KittenML](https://huggingface.co/KittenML) — ultra-lightweight TTS models based on StyleTTS 218- **Original Demo**: [KittenTTS-Demo](https://huggingface.co/spaces/KittenML/KittenTTS-Demo)19- **Transformers.js v4**: [huggingface/transformers.js](https://github.com/huggingface/transformers.js) — ML inference in the browser20- **phonemizer.js**: [xenova/phonemizer.js](https://github.com/xenova/phonemizer.js) — eSpeak-NG phonemization for the web by [Xenova](https://github.com/xenova)21- **ONNX Runtime Web**: [onnxruntime](https://onnxruntime.ai) — cross-platform ML inference22- **Kokoro Web**: [xenova/kokoro-web](https://github.com/xenova/kokoro-web) — reference implementation for browser TTS23 24## Development25 26```bash27npm install28npm run dev29```30 31## Build32 33```bash34npm run build35```36 37Output goes to `dist/` — deploy as a static HuggingFace Space or any static host.38