Stable Audio 3.0 Medium
Open weights Active Audio gen
stable-audio-3-medium
2B open-weight music model generating tracks over six minutes with inpainting support.
Released
May 20, 2026
Context window
Not disclosed
Max output
Not disclosed
Parameters
2B
Input price
Not disclosed
Output price
Not disclosed
Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.
Pricing
No first-party API. This is an open-weights release you can run yourself.
Specifications
- Developer
- Stability AI
- Model type
- Audio gen
- Architecture
- Not disclosed
- Parameters
- 2B
- Input
- Text Audio
- Output
- Audio
- Knowledge cutoff
- Not disclosed
- License
- Stability AI Community License
- API access
- No first-party API