MisoLabs has released Miso TTS 8B, a new text-to-speech model built on the Sesame CSM architecture. This model utilizes a Llama 3.2-style backbone and an autoregressive audio decoder to generate high-quality conversational speech and continue voices from audio prompts. The model is available for local use via its GitHub repository, with a demo also accessible on the MisoLabs website. AI
IMPACT Enables new applications in voice generation and conversational AI with its advanced architecture.
RANK_REASON Release of a new model with technical details and inference code. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Hugging Face Trending Models →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
