Post-Cutoff
Search For AI agents

ACE Studio & StepFunACE-Step familyCurrentMusic generationReleased 28 Jan 2026

ACE-Step 1.5 (incl. 1.5 XL)

The go-to MIT-licensed local song generator in 2026. Quick start: clone https://github.com/ace-step/ACE-Step-1.5 and follow the README (Gradio UI and API server included).

PricePrice not published

Checked29 September 2026

Where it stands

9newer music generation models since its release

The 5 newest are listed. All music generation models

Weights
Weights are public under a permissive licence (MIT).

How to call it

4 ways to use ACE-Step 1.5 (incl. 1.5 XL).

Providers, model ids, endpoints and docs for ACE-Step 1.5 (incl. 1.5 XL)
ProviderModel idEndpointDocs
Hugging Face huggingface.co
Hugging Face (XL 4B DiT) huggingface.co
GitHub github.com
Web app acemusic.ai

Pricing

Price not published.

No price source linked. Checked 29 September 2026.

Specs

Input
Text and audio
Output
Audio
Context window
Not published
Max output
Not published
Open weights
Yes
Licence
MIT
Released
28 January 2026
Status
Current
Type
Music generation

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Full songs in seconds on consumer hardware

    10 s to 10 min of music; under 2 s per song on an A100 and under 10 s on an RTX 3090; standard models run in <4 GB VRAM with offload (XL: >=12 GB, 20 GB recommended).

    Source: github.com

  • LM planner + DiT synthesizer

    A language model (0.6B/1.7B/4B ‘5Hz LM’) turns prompts into a song blueprint that a Diffusion Transformer renders; aligned with ‘intrinsic’ RL without external reward models.

    Source: arxiv.org

  • Editing and personalization toolkit

    Cover generation, repaint/editing, vocal-to-BGM, track separation, multi-track generation, BPM/key extraction and LoRA fine-tuning from ~8 songs (about 1 h on a 12 GB RTX 3090); lyrics in 50+ languages.

    Source: github.com

Notes

Checkpoints: acestep-v15-base / -sft / -turbo (plus turbo-shift variants) and, from 2026-04-02, XL (4B DiT) xl-base / xl-sft / xl-turbo; diffusers versions added Apr-Jun 2026. Release date 2026-01-28 is from secondary sources (HF repos created 2026-01-23, arXiv 2602.00744 submitted 2026-01-31). Authors claim quality beyond most commercial models (SongEval above Suno v5 per secondary coverage; not independently verified). Supports Mac, AMD, Intel and CUDA.

Sources: GitHub, HF, tech report, project page.