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.
— Chubby♨️ (@kimmonismus) 3 juin 2026
8B params, free on GitHub, with one-shot voice cloning from a short sample at 110ms latency.
Self-host it and your audio data… https://t.co/JKiEL5TiIh
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