Tool
Sesame CSM
Conversational Speech Model for emotional expressiveness
About
A Conversational Speech Generation Model. Contribute to SesameAILabs/csm development by creating an account on GitHub.
Features
- Platform AI CODE CREATION GitHub Copilot Write better code with AI
- GitHub Copilot app Direct agents from issue to merge
- MCP Registry Integrate external tools
- DEVELOPER WORKFLOWS Actions Automate any workflow
- Codespaces Instant dev environments
- Issues Plan and track work
- Pricing
- Open Source
- Pricing detail
- Open conversational speech model CSM-1B
- Platforms
- Local
Alternatives from our catalog
Tools on the same shelves as Sesame CSM, ordered by shared tags and our own comparisons. Not vendor endorsements.
- StyleTTS 2Open Source · Local
MIT; style transfer for speech
also in AI Audio
- BarkOpen Source · Local
Suno’s open model; still used for creative SFX speech
also in AI Audio
- ZonosOpen Source · Local, API
Local TTS quality discussions mention it when people want fidelity over tiny models
also in AI Audio
- ChatTTSOpen Source · Local
Dialogue-first model for product voice mockups
also in AI Audio
- Hume AIFreemium · API, Web
Emotion steering under-discussed vs ElevenLabs
also in AI Audio
- Cartesia SonicFreemium · API, Web
Latency leader for voice agents; less “consumer famous” than ElevenLabs
also in AI Audio