AI Dynamics

Global AI News Aggregator

About

Miso One: open-weights voice model with one-shot cloning

Miso One is live: an open-weights voice model built to sound like a real person reading, with actual warmth and pacing where most TTS still goes flat. 8B params, free on GitHub, with one-shot voice cloning from a short sample at 110ms latency. Self-host it and your audio data

→ View original post on X — @kimmonismus