- Cascaded Voice
- Text-to-speech
- Speech-to-text
- Unmute
- Speech-Native
- Hibiki
- Moshi
- Vision
- CASA
- MoshiVis
- World Model
- MIRA
Publications
Blog
- Team
- Join us

← Back to Blog

CADRE: Rethinking Video Autoencoders for Interactive World Models

22 October 2026

Kyutai is funded by Iliad Group, CMA CGM Group and Schmidt Sciences. Many thanks to our generous donors.

Community

X/Twitter
LinkedIn
Newsletter

Resources

Blog
GitHub
Hugging Face
Privacy Policy

About us

Careers
Team
Contact (general)
Contact (press)