---
title: audio-studio
emoji: 🎵
colorFrom: purple
colorTo: blue
sdk: gradio
sdk_version: 6.15.1
app_file: app.py
short_description: Local music generation studio wrapping ACE-Step 1.5
python_version: "3.12"
---

# audio-studio

Local music generation studio wrapping **ACE-Step 1.5**. Text-to-music, reference-audio melody borrowing, and reference-audio cover generation, with configurable artist/album/track/genre texture hints.

## Features

- Text-to-music generation
- Melody borrowing from reference audio
- Cover mode (full sound/texture conditioning)
- Configurable texture hints (artist, album, track, genre)
- Two backends: `mlx-serve` (default) and `ace-step`

## Quick Start

```bash
git clone https://github.com/sm3222/audio-studio.git
cd audio-studio
uv sync
mlx-serve serve --port 8082 --model-dir ~/.mlx-serve/models
uv run audio-studio "a calm piano piece" --output out.wav
```

## Links

- [GitHub Repository](https://github.com/sm3222/audio-studio)
- [ACE-Step 1.5 Paper](https://arxiv.org/abs/2503.02057)