AudioX is a unified framework for multimodal-conditioned audio and music generation with superior instruction-following capabilities.
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 21
HKUSTAudio/AudioX-MAF-MMDiT
Text-to-Audio • Updated • 311 • 8
HKUSTAudio/AudioX-MAF
Text-to-Audio • Updated • 435 • 6
HKUSTAudio/AudioX
Text-to-Audio • Updated • 125
HKUSTAudio/Llasa-3B
Text-to-Speech • 4B • Updated • 849 • 526
HKUSTAudio/Llasa-1B
Text-to-Speech • Updated • 8.34k • 102
HKUSTAudio/VidMuse
Updated • 54 • 6
HKUSTAudio/Llasa-8B
Text-to-Speech • 9B • Updated • 198 • 96
HKUSTAudio/Spark-TTS-0.5B
Text-to-Speech • Updated • 6
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech • 2B • Updated • 1.27k • 43
HKUSTAudio/xcodec2
Audio-to-Audio • 0.8B • Updated • 59.5k • 97