MOSS Audio 8B Thinking
🐢
26
Generate answers to audio or video prompts
MOSS-Audio
An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex
-
-
OpenMOSS-Team/MOSS-Audio-4B-Instruct
Audio-Text-to-Text • 5B • Updated • 29.3k • 73 -
OpenMOSS-Team/MOSS-Audio-4B-Thinking
Audio-Text-to-Text • 5B • Updated • 6.59k • 33 -
OpenMOSS-Team/MOSS-Audio-8B-Instruct
Audio-Text-to-Text • 9B • Updated • 7.73k • 45 -
OpenMOSS-Team/MOSS-Audio-8B-Thinking
Audio-Text-to-Text • 9B • Updated • 7.88k • 77 -
OpenMOSS-Team/MOSS-Music-8B-Thinking
Audio-Text-to-Text • 9B • Updated • 218 • 32 -
OpenMOSS-Team/MOSS-Music-8B-Instruct
Audio-Text-to-Text • 9B • Updated • 1.43k • 21 -
cstr/MOSS-Audio-4B-Instruct-GGUF
Audio-Text-to-Text • 5B • Updated • 623 • 1 -
MOSS-Audio Technical Report
Paper • 2606.01802 • Published • 2