Generates production music through ACE-Step's open-source models. You can create background tracks for videos, jingles with vocals and lyrics, extract stems, or repaint weak sections of existing audio. The default acemusic cloud provider uses the 4B XL Turbo model with a thinking mode that enriches sparse prompts into detailed musical descriptions. Self-hosting on Modal or RunPod is available but uses the smaller 2B model. Includes scene presets tuned for video production (corporate background, tension, call-to-action) and handles vocal gender through combined prompt and lyric tags. Best for video editors and content creators who need custom soundtrack work without licensing hassles.

skills.sh installs
1K
GitHub stars
2.5K
last updated
Aug 21, 2026

Install

$ npx -y skills add digitalsamba/claude-code-video-toolkit --skill acestep --agent claude-code

Installs into .claude/skills of the current project.

Files

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

Sponsors

Details

Repository
github.com/digitalsamba/claude-code-video-toolkit
Category
Code Review & Quality
First seen
Jun 3, 2026

More from digitalsamba/claude-code-video-toolkit

All 12
1orchestra-research avatarevaluating-llms-harnessorchestra-research/ai-research-skillsEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting 1Kskills.sh installs
2jezweb avatarus-business-englishjezweb/claude-skillsAmerican business English writing style for professional communications — direct, action-oriented, EN-US spelling (color, organize, center). Use whenever the us1Kskills.sh installs
3mindrally avataroptimized-nextjs-typescriptmindrally/skillsOptimized Next.js TypeScript best practices with modern UI/UX, focusing on performance, security, and clean architecture1Kskills.sh installs
4zubair-trabzada avatargeo-auditzubair-trabzada/geo-seo-claudeFull website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform a1Kskills.sh installs
5alirezarezvani avatartdd-guidealirezarezvani/claude-skillsTest-driven development skill for writing unit tests, generating test fixtures and mocks, analyzing coverage gaps, and guiding red-green-refactor workflows acro1Kskills.sh installs
6orchestra-research avatarnanogptorchestra-research/ai-research-skillsEducational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfec1Kskills.sh installs