AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction for video production.
SkillScore100Maintained
Automatic
◆Marketing & Content pack
Last verified 8/17/2026
What it changes
Passed 22 of 22 test cases with the skill, and 10 of 22 without it.
Without skill45%
With skill100%
Checks it passed that the model alone missed
Invokes python tools/music_gen.py.
Specifies the parameter --cover-strength.
Uses python tools/music_gen.py --preset cta.
and 13 more in the full report
12 fixed10 passed either way0 still failing0 broke
Pass-rate lift
+55 pp
Tokens
+94%
Agent turns
0%
Response time
-70%
Model gemini-3.6-flashMeasured 8/17/2026v122 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
We need a short 15-second high-energy call-to-action track for a brand named digital-samba. Provide the terminal command using our music generator script with the appropriate scene preset and brand tag, producing cta.mp3.
What was checked, without and with the skill
Checked
Without skill
With skill
Uses python tools/music_gen.py --preset cta.
Missed
Passed
Includes --brand digital-samba, --duration 15, and --output cta.mp3.
Passed
Passed
case-08 · gemini-3.6-flash · 8/17/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md259 linessingle file
ACE-Step 1.5 Music Generation
Open-source music generation (MIT license) via tools/music_gen.py. Runs on RunPod serverless.
Requires RUNPOD_API_KEY and RUNPOD_ACESTEP_ENDPOINT_ID in .env (run --setup to create endpoint).