acestep-captioner
ACE-Step Captioner is the annotation model used by ACE-Step v1.5 for training data labeling.
text → audio · made by ACE-Step
Sold by
Nobody in the catalogue publishes a price for this yet.
About
acestep-captioner — an audio model from ACE-Step.
It takes text and returns audio. It was published in January 2026. The catalogue files it under speak. Its weights are published under MIT, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- ACE-Step
- Register
- model
- Takes
- text
- Returns
- audio
- Published
- January 2026
- Parameters
- 11 billion · read from its own weights
- Licence
- mit
Known as 1 name
ACE-Step/acestep-captioner