README.md

---
title: ace-step-jam
emoji: 🎧
colorFrom: indigo
colorTo: blue
sdk: gradio
sdk_version: 6.12.0
app_file: app.py
pinned: false
license: mit
short_description: Describe any song — AI writes & produces it
models:
  - ACE-Step/Ace-Step1.5
  - ACE-Step/acestep-v15-xl-turbo
  - Tongyi-MAI/Z-Image-Turbo
---

# ace-step-jam

Describe any song in plain English — an LLM writes the tags and lyrics, then [ACE-Step v1.5](https://github.com/ace-step/ACE-Step) generates the audio.

**Model**: [`ACE-Step/acestep-v15-xl-turbo`](https://huggingface.co/ACE-Step/acestep-v15-xl-turbo) — 8-step turbo distillation, ~2 seconds per minute of audio on GPU.

## Usage

1. Describe the song you want (genre, mood, story — anything)
2. Hit **Generate** — the AI composes lyrics, picks tags, and produces audio
3. Click the waveform to seek, download the WAV, or share to the community feed