MOSS-Audio Collection An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 7 items • Updated 4 days ago • 55
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 Dec 24, 2025 • 244
Llasa Collection TTS foundation model compatible with Llama framework (160k hours tokenized speech data released) • 11 items • Updated May 11, 2025 • 21
Running on Zero Agents 314 Llasa 3b Tts 🔥 314 Zero Shot voice cloning with llasa 3b (Unofficial Demo)
Running on CPU Upgrade Agents Featured 1.33k Open ASR Leaderboard 🏆 1.33k Explore and compare speech recognition model benchmarks