Record your voice, clone it, type some text, and hear it speak.
Runs entirely in your browser via ONNX and WebAssembly. No server. No API keys. Your data stays on your machine.
Voice Cloning
Record from mic or upload audio. The mimi encoder extracts voice embeddings.
Zero Server
ONNX models from HuggingFace CDN. Inference via WebAssembly. Nothing leaves your machine.
Streaming Audio
Hear audio as it generates via AudioWorklet. Save cloned voices and reuse anytime.
Record ~5s of speech or upload an audio clip to clone
My Voices
No saved voices yet. Clone a voice to save it.