#4,868 of 5,656 by stars
kyutai-labs/moshi
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
- Stars
- 11,264
- Forks
- 1,046
- Created
- 2y ago
- Last push
- 1mo ago
Momentum
- Per day
- +10
- Per 7 days
- +56
- Per 30 days
- +158
- Rank, 7 days
- +15
Stars over time
View as table
| Date | Stars |
|---|---|
| Sep 17, 2026 | 11,095 |
| Oct 5, 2026 | 11,175 |
| Oct 12, 2026 | 11,208 |
| Oct 19, 2026 | 11,264 |
Understand this repo
Open it in a tool that explains, diagrams or digests the code.
- Explain A plain-language walkthrough of what the project is and does
- Diagram An interactive architecture diagram of the codebase
- Ingest for AI The whole repository as one text digest to paste into an AI assistant
- Reverse prompt A prompt describing how to rebuild the project
These open independent third-party sites, which may be slow or unavailable for very large repositories.