Sesame CSM 1B

Generate from CSM 1B (Conversational Speech Model). Code is available on GitHub: SesameAILabs/csm. Checkpoint is hosted on HuggingFace.


Voices

Speaker A

Select a predefined speaker

Speaker B

Select a predefined speaker

Conversation content

Each line is an utterance in the conversation to generate. Speakers alternate between A and B, starting with speaker A.

Choose input method

GPU time limited to 3 minutes, for longer usage duplicate the space.