CSM 1B · deepinfra

CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Preço, $ $7.00 / 1M caracteres

Contexto —

Aceita —

Última verificação 04.11.2026 12:00:14 UTC

Fonte —