MOSS-Audio Collection An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 13 items • Updated 23 days ago • 67
Running on Zero Agents Featured 297 LongCat-Video-Avatar 1.5 🎤 297 Audio-driven talking-head video generation (Meituan LongCat)
Moshi v0.1 Release Collection MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 16 items • Updated 19 days ago • 245