stable-audio-3-medium

cocktailpeanut/stable-audio-3-medium

Text to Audio2.3B parametersstable-audio-3License: other
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
Downloads 30D
2,607
Total downloads
10.3K
Gained 7D
+596(increase)
7.1%(up) vs baseline
Gained 30D
—
Likes
2
+0 in 7D
Rank · tracked models
#17,940
128(up 128 places)this week
Parameters
2.3B
Last source update
May 21, 2026
Momentum
57.7
  • stable-audio-3-medium gained 596 downloads during the last seven tracked days.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

stable-audio-3-medium is a text to audio model published by cocktailpeanut. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it 8h ago.

Published
May 21, 2026
Last updated
May 21, 2026
Library
stable-audio-3
License
other
Task
Text to Audio
Parameters
2,305,495,793
Spaces
—
Derivative models
—
Velocity 7D/day
85
stable-audio-3safetensorsaudio-generationmusicsound-effectsdiffusiontext-to-audioenarxiv:2605.17991base_model:stabilityai/stable-audio-3-medium-basebase_model:finetune:stabilityai/stable-audio-3-medium-baselicense:other

Publisher

cocktailpeanutView publisher statistics →

Derived from stabilityai/stable-audio-3-medium-base (reported by the source; parent not yet tracked).

Similar models

Models similar to stable-audio-3-medium
ModelDL 30D
stable-audio-3-mediumstabilityai61.1K
stable-audio-3-medium-basestabilityai8,675
acestep-v15-baseACE-Step3,983
acestep-v15-sftACE-Step3,230
acestep-v15-turbo-shift3ACE-Step514
MiniMax-Music3MiniMaxAI7,307
cocktailpeanut/stable-audio-3-medium — Downloads, Growth & Stats | OpenModelStats