Text to Speech AI turns any sentence into natural speech using MOSS-TTS-Nano, a 0.1B multilingual model that runs fully on WebAssembly inside your browser. Nothing is uploaded: text and audio never leave your device. No signup, no quota, no watermark. Pick a built-in voice or upload a short reference clip to clone a voice, adjust speed and volume, then download MP3 or WAV. Runs on CPU, no GPU needed. Weights are fetched from Hugging Face and cached locally.