AudioX

zhangj1an/AudioX

Text to Audio2.8B parametersdiffusersLicense: cc-by-nc-4.0
Tracked by OpenModelStats since September 10, 2026View on Hugging Face ↗
Downloads 30D
2,240
Total downloads
3,673
Gained 7D
+604(increase)
23.9%(up) vs baseline
Gained 30D
—
Likes
0
+0 in 7D
Rank · tracked models
#20,715
998(up 998 places)this week
Parameters
2.8B
Last source update
Apr 17, 2026
Momentum
60.3
  • AudioX gained 604 downloads during the last seven tracked days.
  • It moved from #53 to #51 among tracked Text to Audio models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

AudioX is a text to audio model published by zhangj1an. OpenModelStats has tracked the model since Sep 10, 2026, most recently observing it Oct 4, 2026.

Published
Apr 6, 2026
Last updated
Apr 17, 2026
Library
diffusers
License
cc-by-nc-4.0
Task
Text to Audio
Parameters
2,820,370,292
Spaces
—
Derivative models
—
Velocity 7D/day
86
diffuserssafetensorsdiffusion_condaudio-generationmusic-generationtext-to-audioarxiv:2503.10522base_model:HKUSTAudio/AudioXbase_model:finetune:HKUSTAudio/AudioXlicense:cc-by-nc-4.0diffusers:AudioXPipelineregion:us

Publisher

zhangj1anView publisher statistics →

Derived from HKUSTAudio/AudioX (reported by the source; parent not yet tracked).

Similar models

Models similar to AudioX
ModelDL 30D
SongGeneration-v2-medium-4bitmlx-community35
SongGeneration-v2-medium-8bitmlx-community18
midashenglm-genmispeech200
musicgen-stereo-melody-largefacebook344
MiniMax-Music3MiniMaxAI7,420
acestep-v15-baseACE-Step3,745
zhangj1an/AudioX — Downloads, Growth & Stats | OpenModelStats