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 los modelos de esta baseTodos los modelos del proveedoral proveedor

Precio, $ $7.00 / 1M caracteres

Contexto —

Acepta —

Última comprobación 04.11.2026 12:00:14 UTC

Fuente —