# Stable Audio 2.5

> Audio AI Model by Stability AI — available on Layer

Enterprise-grade audio generation with multi-part compositions and audio inpainting.

Stable Audio 2.5 from Stability AI is the first audio model built for enterprise sound production at scale. It generates tracks up to three minutes long in under two seconds on a GPU, using the Adversarial Relativistic-Contrastive (ARC) method. The model produces multi-part compositions with intro, development, and outro sections, and supports audio inpainting for seamless contextual extensions. Trained on fully licensed audio content with copyright detection built in, it is suitable for commercial brand audio, game soundtracks, and production music.

## Specifications

| Property | Value |
|----------|-------|
| Provider | Stability AI |
| Category | Audio |
| Price | 5.6 / generation per generation |

## Capabilities

- Sound Effects

---

[Try Stable Audio 2.5](https://next.app.layer.ai/me/session/new?baseModelId=STABLE_AUDIO_25) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)