sesameListed Mar 15SEcsm-1bCSM (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…1BNo reported scoreNo reported scoreListed from $0.007/ 1K characters · USDDeepInfra1,000 input characters+Compare
fal-aiListed Mar 13FACSM-1BCSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.1BNo reported scoreNo reported scoreListed from $0.03/ 1K characters · USDfal+Compare