announcement
Releasing the MisoTTS
Achieving state-of-the-art emotive speech and dialogue generation with a hierarchical RVQ transformer. The Miso TTS is an 8-billion-parameter transformer model with open-source weights available on Hugging Face, and API access coming soon.
AT
CD
Aoden Teo & Cassidy Dalva · June 3, 2026 · 14 min