# ACE-Step v1.5: what's new, verdict & setup

Canonical: https://theagenticweekly.com/tools/ace-step · Released: 2026-01-28 · Last verified: 2026-10-25 · Evidence: Reported (not run by us) · Vendor: ACE-Step · Official site: https://github.com/ace-step/ACE-Step

> Open-source (Apache-2.0) music generation foundation model you can run yourself.

## Verdict

**The pick if you want open weights and local control; expect a manual setup and no recent updates.**

Good for:
- Tinkerers who want to run music generation locally
- Developers who want to fine-tune with LoRA
- People who need Apache-2.0 licensing

Skip if:
- You want a polished app with no setup
- You need active weekly releases

Status: Reported. Written from official release notes and docs; we have not run this release ourselves.

Pricing: Not verified. We have not verified pricing for this tool; see the official site.

## Best for

- [Best AI tool for music](https://theagenticweekly.com/best/music) (#3): Open-source music model with local setup, ComfyUI support and LoRA training.

## What's new

ACE-Step v1.5 was released on Jan 28, 2026 per the README. The repository's last push we saw was in February 2026, so treat it as a stable open option rather than a fast-moving one.

- 2026-01-28: README announces ACE-Step v1.5 as the latest and most advanced model.
- The model targets many styles and 19 languages, with ComfyUI nodes and LoRA training instructions listed in the README.
- The README notes a memory optimization that reduced maximum VRAM to 8GB for consumer devices.

## How to set it up: Run ACE-Step locally

Steps come from the vendor's own pages or docs. We have not run them ourselves.

1. **Clone the repo.** The README starts by cloning the repository.

```
git clone https://github.com/ace-step/ACE-Step.git
cd ACE-Step
```
2. **Create an environment and install.** Use a virtual environment and an editable install. Install the PyTorch build that matches your GPU first, as the README describes.

```
python -m venv venv
source venv/bin/activate
pip install -e .
```
3. **Launch the UI.** Start the Gradio UI. The README recommends extra flags on lower-VRAM GPUs.

```
acestep --port 7865
```

## Pros and cons

Pros:
- Apache-2.0 open source
- Runs locally; README says as little as 8GB VRAM with optimizations
- ComfyUI nodes and LoRA training available

Cons:
- No GitHub releases found; last push Feb 2026
- Setup needs a GPU and technical comfort
- We did not listen-test it

## Alternatives

- [Suno](https://theagenticweekly.com/tools/suno): AI music creation: text, audio, images or video in, finished songs out.
- [ElevenLabs](https://theagenticweekly.com/tools/elevenlabs): Voice, speech, music and voice-agent platform with a detailed API changelog.

## FAQ

### What is ACE-Step?

An open-source foundation model for music generation, with v1.5 announced on 2026-01-28 in the README.

### How much VRAM does ACE-Step need?

The README says a memory optimization reduced maximum VRAM to 8GB.

### Is ACE-Step actively updated?

Our check found the repository last pushed in February 2026 and no recent releases.

## What we have not verified

- Audio quality compared with Suno (not tested)
- Whether newer versions exist outside the repo
- Hardware needs for v1.5 specifically

## Sources

- [ACE-Step README](https://github.com/ace-step/ACE-Step) (fetched 2026-10-25)
- [ACE-Step repository metadata (GitHub API)](https://api.github.com/repos/ace-step/ACE-Step) (fetched 2026-10-25)

## How to cite

Agentic Weekly, "ACE-Step v1.5: what's new, verdict & setup", last updated 2026-10-25, https://theagenticweekly.com/tools/ace-step

Keep the Reported or Tested label when you quote the verdict.