📋 Info
| GitHub Stars | ⭐ 7.5k Stars |
| License | Stability License |
| Language | Python |
| Version | 1.0 |
| Updated | 2026-03-20 |
📖 Overview
Stable Audio Open is an audio generation model made open source by Stability AI. It can produce high-quality audio up to 47 seconds long based solely on textual descriptions. It excels at generating drum beats, musical riffs (such as guitar, piano, and bass solos), and ambient sounds (like rain, city noises, or forest sounds). Built on a diffusion model, it delivers excellent sound quality. It is suitable for creators who need high-quality short audio clips.
✨ Features
- Text-to-high-quality audio in 47 seconds
- Expert at drum beats/instrument riffs/background sounds
- Stability AI quality
- Diffusion model — excellent sound quality
- A powerful tool for short audio clips.
Advertisement