Model · ACE Studio and StepFun · Audio-Gen
ACE-Step 1.5
An open music model that writes full songs, with vocals, from 10 seconds to 10 minutes long, in 50+ languages, and can make covers or re-generate parts of a track. MIT-licensed, and its makers say the output is cleared for commercial use.
- Modality
- Audio-Gen
- License
- MIT (Open)
- Parameter size
- 2B DiT (base); 4B DiT (XL)
- Released
- January 23, 2026
- Last verified
- October 28, 2026
- Runs locally
- Yes
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 16 GB (32 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 4 GB (24 GB recommended) of video memory.
- No graphics card
- Not practical. Too slow without a graphics card or Apple Silicon.
Runs natively on Apple Silicon Macs through the project's own MLX start script, and a ready-made Mac package is offered.
Numbers are for: Base 2B model; the larger XL (4B) model needs about 20 GB of graphics memory. Based on the maker’s own figures; where the maker gives only a graphics-card figure, the Mac memory is our estimate.
Strengths
- MIT licence, and the model card says generated music can be used commercially (trained on licensed tracks)
- Full songs from 10 seconds up to 10 minutes
- Lyrics in 50+ languages
- Editing: cover generation, repainting a section, and vocal-to-backing-track conversion
- Base model runs on a graphics card with under 4 GB of memory
- Fast: under 10 seconds per full song on an RTX 3090
- Train a LoRA of your own style from a handful of songs (about an hour on a 12 GB card)
Weaknesses
- The higher-quality XL (4B) models need 12 GB of graphics memory with offloading, or 20 GB without
- Its makers rate quality between Suno v4.5 and Suno v5 — not the top of the closed market
- Style similarity can still create copyright risk; the README asks users to check originality
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | MIT; XL variants in separate repos |
| GitHub | local | Gradio app and API; Mac, AMD, Intel and CUDA |
| acemusic.ai | product | Web app from the same team |
Official sources
- Model card model
- GitHub github
- Technical report paper
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: the model card and README (Mac figures are estimated from model size).
- — Initial entry. Added 2026-10-28 from the popularity sweep: 14.1k GitHub stars. Release date is the Hugging Face repo date (2026-01-23); the lab publishes none for v1.5 (the technical report followed on 2026-01-31). The XL (4B) series was released 2026-04-02 per the README news. The README says the project is co-led by ACE Studio and StepFun.
Esc