# ACE-Step

> Audio AI Model by ACE-Step — available on Layer

Fast open-source music generation with lyrics alignment, remixing, and audio editing.

ACE-Step is an open-source 3.5B-parameter music generation foundation model co-developed by ACE Studio and StepFun. It synthesizes up to 4 minutes of music in just 20 seconds on an A100 GPU — 15x faster than LLM-based baselines — while achieving superior musical coherence and lyric alignment across melody, harmony, and rhythm. The model supports text-to-music, audio-to-audio remixing, lyric editing, audio inpainting, and audio outpainting. Licensed under Apache 2.0.

## Specifications

| Property | Value |
|----------|-------|
| Provider | ACE-Step |
| Category | Audio |
| Price | 0.02 / second per second |

---

[Try ACE-Step](https://next.app.layer.ai/me/session/new?baseModelId=ACE_STEP) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)