Sesame: CSM 1B

CSM 1B is a conversational speech model from Sesame. It accepts text input and produces English speech output, with voice options spanning conversational and read-speech styles. At 1B parameters, it is suited for dialogue-oriented applications such as voice assistants and interactive agents.

• Context window: 4,096 tokens
• Input: text
• Output: speech

View on OpenRouter. Model data sourced from OpenRouter.