kyutai-labs/moshi
Daily GitHub growth and open-source AI ranking profile for 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.
kyutai-labs/moshi has 10506 GitHub stars, 975 forks, 8 stars gained in the last 24 hours, 36 stars gained in the last 7 days.
Repository ranking signals
- Total GitHub stars: 10506
- Forks: 975
- Stars gained in 24 hours: 8
- Stars gained in 7 days: 36
- Primary language: Python
- AI category: Models
- Subcategory: Audio/Speech models
- Keywords: Speech-to-text, Text-to-speech
- Top contributors: LaurentMazare, adefossez, FL33TW00D
- Last repository update: 2026-07-03
Why this page matters
AI Rank monitors kyutai-labs/moshi as part of a daily open-source AI leaderboard. The page is useful for tracking GitHub momentum, category placement, language, contributors, and recent repository activity without manually checking each project.