ACE-Step 1.5
Shares rank 5 of 8 AI music generators by recommenders
Open-source music model, cheap to run locally and fine-tunable on your own songs. Caveat: critics say its musicality trails commercial services.
Open-source music model, cheap to run locally and fine-tunable on your own songs. Caveat: critics say its musicality trails commercial services.
8 people gave an opinion
- recommend it
- 6
- criticize it
- 2
- approval share
- 75%
Recommended in 4 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- 3 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Open source and cheap to run
“the results were actually good with it being opensource and for how cheap the model is to run”
Comment from 7 Apr 2026 in “Ace-Step-1.5 playground- SOTA open source music model” “only 1.5b params so very easy to run locally”
Comment from 17 Feb 2026 in “Claude Sonnet 4.6” Runs locally and can be fine-tuned
“run locally, own it, fine-tune with your songs”
Comment from 3 Feb 2026 in “SHOW HN:AceStep1.5an on-device music model that beats Suno on common eval metric” “only 1.5b params so very easy to run locally”
Comment from 17 Feb 2026 in “Claude Sonnet 4.6” Good for music creation pipelines
“All great for creation pipelines.”
Comment from 21 May 2026 in “Ask HN: Is the next big thing locally running coding agents?” “very good music generation model”
Comment from 19 Feb 2026 in “Step 3.5 Flash: Fast Enough to Think. Reliable Enough to Act”
What people warn about
Each mark is one comment
Quality around Stable Diffusion 1.0 level
“Currently its quality is at about the Stable Diffusion 1.0 level”
Comment from 22 Dec 2025 in “Backing up Spotify”
Other AI music generators people recommend
The four most recommended other AI music generators, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Suno | 107 | 80 | 57% | 12 | 1 yr6 owners | — |
| ElevenLabs Music | 10 | 10 | 50% | 1 | — | — |
| Google Flow Music | 9 | 26 | 26% | 1 | — | — |
| Lyria | 8 | 5 | 62% | 5 | — | — |
| ACE-Step 1.5This page | 6 | 2 | 75% | 4 | — | — |
What people said
All 9 comments that mention it, newest first. Each links to the original comment.
“All great for creation pipelines.”
“the results were actually good with it being opensource and for how cheap the model is to run”
“very good music generation model”
“only 1.5b params so very easy to run locally”
“I found ACE-Studio 1.5's cover ability to be incredibly lackluster.”
“the musicality of this system is much lower than what we have commercially”
“Once you start thinking in tags + structure, results get much more predictable.”
“run locally, own it, fine-tune with your songs”
“Currently its quality is at about the Stable Diffusion 1.0 level”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.