All models
dialogue

Sesame CSM-1B

Apache-2.0

The conversational speech model behind the viral Maya demo

CSM-1B is the open model from Sesame, whose 'Maya' assistant demo went viral for sounding uncannily present — breath, hesitation, tone shifts and all. It generates speech conditioned on conversation context, so replies sound like part of a dialogue rather than isolated lines. The open release is the base generation model behind that demo.

Voices

1 voice
Neutral
Context-conditioneddefault
—
NeutralEmotionalNumbers & Dates

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Install

git clone https://github.com/SesameAILabs/csm

Sesame CSM-1B FAQ

Do I need a GPU to run Sesame CSM-1B?

For practical speeds, yes — plan on roughly 8 GB of VRAM. If you'd rather not manage a GPU, hosted access to every model in this directory is coming via OpenSpeech Cloud.

Can Sesame CSM-1B clone voices?

Yes — Sesame CSM-1B supports voice cloning from reference audio.

What license is Sesame CSM-1B released under?

Sesame CSM-1B is released under the Apache-2.0 license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does Sesame CSM-1B support?

Sesame CSM-1B supports English.

Is there a hosted Sesame CSM-1B API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to Sesame CSM-1B and every other model in this directory. No CUDA, Docker, or GPU needed.