acestep-captioner

ACE-Step/acestep-captioner

Text to Audio10.7B parameterstransformersLicense: mit
Tracked by OpenModelStats since September 4, 2026View on Hugging Face ↗
Downloads 30D
1,841
Total downloads
68.5K
Gained 7D
+508(increase)
0.8%(up) vs baseline
Gained 30D
—
Likes
74
+3 in 7D
Rank · tracked models
#23,183
246(down 246 places)this week
Parameters
10.7B
Last source update
Feb 3, 2026
Momentum
69.5
  • acestep-captioner gained 508 downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

acestep-captioner is a text to audio model published by ACE-Step. OpenModelStats has tracked the model since Sep 4, 2026, most recently observing it Oct 4, 2026.

Published
Jan 23, 2026
Last updated
Feb 3, 2026
Library
transformers
License
mit
Task
Text to Audio
Parameters
10,732,225,408
Spaces
—
Derivative models
—
Velocity 7D/day
73
transformerssafetensorsqwen2_5_omnitext-to-audiomusicaudioarxiv:2602.00744license:mitendpoints_compatibleregion:us

Similar models

Models similar to acestep-captioner
ModelDL 30D
MiniMax-Music3-mxfp8mlx-community506
MiniMax-Music3-4bitmlx-community407
MiniMax-Music3-8bitmlx-community283
MiniMax-Music3-bf16mlx-community166
MiniMax-Music3-mxfp4mlx-community145
VibeVoice-Large-Q8FabioSarracino835
ACE-Step/acestep-captioner — Downloads, Growth & Stats | OpenModelStats