HF Realtime Voice
Voice chat over WebSocket against a HF speech-to-speech
High-quality voice cloning TTS for 600+ languages
Upgraded to v1.0!
Generate speech from text using voice design, cloning or presets
Play with an AI dog that catches sticks you throw
Generate podcast and tiktok style video avatars
Generate or edit images from text and optional photos
Run Gemma 4 locally in-browser on WebGPU w/ Transformers.js