Models
MOSS-Audio
OpenMOSS/MOSS-Audio
An open-source audio understanding model family for speech, environmental sound and music. The release provides 4B and 8B Instruct and Thinking weights for captioning, timestamped ASR, audio QA and reasoning.
Topics
Related projects
voxcpm41.3kAn open-source 2B tokenizer-free multilingual TTS model for voice design, controllable cloning, and studio-quality synthesis.
MOSS-TTS4.3kAn open-source speech model family for long-form TTS, dialogue synthesis, voice design, and streaming speech.
magenta-realtime1.9kGoogle's open-weights model for real-time music generation, shipped with a Python inference library, a C++ streaming engine plus example apps and DAW plugins.
wemm-embedding1.8kTencent's family of universal multimodal embedding models, released in 2B, 4B and 9B sizes, mapping text, images, videos and visual documents into a shared retrieval space.
SALMONN1.6kByteDance's family of multimodal large language models for speech, audio and audio-visual understanding, released with model checkpoints and inference and training code.
CrisperWhisper1.5kA multilingual speech recognition model for verbatim and intended transcription with precise word-level timestamps, distributed as model weights plus a Python inference package.