AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction, audio repainting, and continuation for video production.
SkillScore91Maintained
Automatic
◆AI Engineer pack
Last verified 9/2/2026
What it changes
Passed 21 of 23 test cases with the skill, and 4 of 23 without it.
Without skill17%
With skill91%
Checks it passed that the model alone missed
Specifies --cover-strength 0.2
Passes --cloud modal to tools/music_gen.py
Passes --variations 4 to tools/music_gen.py
and 23 more in the full report
17 fixed4 passed either way2 still failing0 broke
Pass-rate lift
+74 pp
Tokens
+134%
Agent turns
0%
Response time
-47%
Measured 9/2/2026v2 · latest is v321 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.8-flash on 10/19/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
See it in action
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 17
Prompt
We want to generate closing call-to-action audio that aligns with our brand guidelines stored in `brands/digital-samba/brand.json`. What parameter tells `tools/music_gen.py` to load those brand hints?
What was checked, without and with the skill
Checked
Without skill
With skill
Passes --brand digital-samba to tools/music_gen.py
Missed
Passed
Combines brand parameters with scene presets like cta for closing branding
Missed
Passed
case-12 · gemini-3.6-flash · 9/2/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md345 linessingle file
ACE-Step 1.5 Music Generation
Open-source music generation via tools/music_gen.py.
Cloud providers:
acemusic (default) — Official ACE-Step cloud API with XL Turbo (4B) model + 5Hz LM thinking mode. Free API key from acemusic.ai/api-key. No GPU required.
modal — Self-hosted ACE-Step 1.5 XL Turbo (4B DiT, no LM) on Modal A10G. Requires MODAL_MUSIC_GEN_ENDPOINT_URL.
runpod — Self-hosted ACE-Step 2B Turbo on RunPod. Requires RUNPOD_ACESTEP_ENDPOINT_ID.
Setup
# acemusic (recommended — free, best quality, no GPU)
echo "ACEMUSIC_API_KEY=your_key" >> .env
# Get key at https://acemusic.ai/api-key
# Self-hosted (optional fallback)
uv run tools/music_gen.py --setup # RunPod
uv run modal deploy docker/modal-music-gen/app.py # Modal
Quick Reference
# Basic generation (uses acemusic XL Turbo by default)
uv run tools/music_gen.py --prompt "Upbeat tech corporate" --duration 60 --output bg.mp3
# Generate 4 variations, pick the best
uv run tools/music_gen.py --prompt "Calm ambient piano" --duration 30 --variations 4 --output ambient.mp3
# Fast mode (disable thinking)
uv run tools/music_gen.py --no-thinking --prompt "Quick draft" --duration 30 --output draft.mp3
# With musical control
uv run tools/music_gen.py --prompt "Calm ambient piano" --duration 30 --bpm 72 --key "D Major" --output ambient.mp3
# Scene presets (video production)
uv run tools/music_gen.py --preset corporate-bg --duration 60 --output bg.mp3
uv run tools/music_gen.py --preset tension --duration 20 --output problem.mp3
uv run tools/music_gen.py --preset cta --brand digital-samba --duration 15 --output cta.mp3