Supertonic now supports 5 languages:
한국어 · Español · Français · Português · English
It’s built to run locally across a wide range of setups—from browser-based inference with WebGPU to small devices like mobile phones and Raspberry Pi.
Here are key features:
(1) Lightning fast — RTF 0.006 on M4 Pro
(2) Lightweight — 66M parameters
(3) On-device TTS — Complete privacy, zero network latency
(4) Flexible deployment — Runs on browsers, PCs, mobiles, and edge devices
(5) 10 preset voices — Pick the voice that fits your use cases
(6) Open-weight model — Commercial use allowed (OpenRAIL-M)
We hope Supertonic is useful for many applications. Thank you!
Demo: https://huggingface.co/spaces/Supertone/supertonic-2