Model · Stability AI · Audio-Gen
Stable Audio 3.0
Stability AI's open-weight audio model. Generates music tracks, sound effects, and audio loops from text prompts — the open alternative to Suno/Udio. (Small/medium tiers open-weighted; large is API-only.)
- Modality
- Audio-Gen
- License
- Stability AI Community License (Open weights)
- Released
- May 20, 2026
- Last verified
- June 8, 2026
- Runs locally
- Yes
Strengths
- Open weights — runs offline on capable hardware
- Good sound-effect generation, not just music
- Community License allows free commercial use under thresholds
Weaknesses
- Vocal generation weaker than Suno/Udio
- Community License has revenue thresholds for commercial use
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | Stability Community License |
| Stable Audio Studio | product | Web UI |
Official sources
- Model card model
Change log
- — Updated from Stable Audio 2.5 to Stable Audio 3.0 (released 2026-05-20). Prior release date (2024-04-03) belonged to the 2.0 line.
- — Initial entry.
Esc