European Open Source AI Index
DatabaseNewsGuidesAboutContribute

Conversational Speech Model

by Sesame AI

Model which seeks to produce speech with realistic elements.
Audio
Full
https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice
(undefined)
CSM-8B
Apache-2.0
Company seeking to make computers more life-like.
https://www.sesame.com
April 2025
Availability
Base Model Data
Data source listed as 'a large dataset of publicly available audio'. No links provided.
https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice
End User Model Data
Data source listed as 'a large dataset of publicly available audio'. No links provided.
https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice
Base Model Weights
Weights of a smaller variant of the model released.
https://huggingface.co/sesame/csm-1b
End User Model Weights
Weights of a smaller variant of the model released.
https://huggingface.co/sesame/csm-1b
Training Code
Repository exists, however contains no training code.
https://github.com/SesameAILabs/csm
Documentation
Code Documentation
No training code, so no documentation.
Hardware Architecture
No hardware architecture information found.
Preprint
Model only publicized through blog post.
https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice
Paper
No peer-reviewed paper found.
Modelcard
Model card only provides information about usage.
https://huggingface.co/sesame/csm-1b
Datasheet
No datasheet found.
Access
Licenses
Model available under Apache-2.0, an OSI-approved license.
https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice
Is this information not up to date?
Contribute here ->
Supported by the Centre for Language Studies and the Dutch Research Council. Website design & development © 2024 by BSTN. This version of the index generated 09 April 2026, website content last updated 11 March 2026.