Ai Music
Let the agent pick RunComfy’s ElevenLabs or ACE Step music stack from plain-language intent—vocals, cheap beds, multilingual lyrics, or inpaint/outpaint edits—and run the right `runcomfy` command.
Overview
AI Music is an agent skill most often used in Build (also Grow content, Launch distribution) that routes RunComfy CLI music requests to ElevenLabs or ACE Step based on vocal quality, cost, language, and edit intent.
Install
npx skills add https://github.com/agentspace-so/runcomfy-agent-skills --skill ai-musicWhat is this skill?
- Smart router across ElevenLabs AI Music (premium 44.1 kHz vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.
- ACE Step inpaint and outpaint for repairing choruses or lengthening short drafts
- Intent-based model selection: premium vocal hook vs cheap background library vs multilingual pop vs edit passes
- Single `runcomfy` CLI surface with documented prompting patterns per routed model
- Broad triggers: generate music, jingle, soundtrack, extend music, fix this song, inpaint music
- Routes ElevenLabs at $0.0083/s and ACE Step at $0.0002–0.0003/s
- ~27× cheaper ACE path than ElevenLabs Music (per skill copy)
- ElevenLabs output up to 5 min at 44.1 kHz stereo; ACE up to 4 min per call
Adoption & trust: 142k installs on skills.sh; 15 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know you want AI music but not which RunComfy model or prompt shape fits vocals, instrumentals, fixes, or budget.
Who is it for?
Builders who want one music entry point in the agent and trust automated routing between premium ElevenLabs vocals and low-cost ACE Step generation.
Skip if: Workflows that must always use a single fixed model and price tier without router logic—install ace-step or call ElevenLabs directly with a pinned endpoint instead.
When should I use this skill?
User asks to generate music, make a song, AI music, background music, instrumental, soundtrack, jingle, theme music, royalty-free music, compose, music with lyrics, extend music, fix this song, inpaint music, or any expl
What do I get? / Deliverables
The agent selects the documented model, runs `runcomfy` with the right pattern, and returns audio aligned to premium vocal, cheap bed, multilingual lyric, or inpaint/outpaint goals.
- Routed music audio file from ElevenLabs or ACE Step generation
- Edited track segments from ACE inpaint/outpaint when requested
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
The skill’s core job is catalog routing through one CLI integration, which lands on Build → Integrations as the primary shelf even though music supports later launch and growth content. It ships model-specific prompting patterns plus minimal `runcomfy run` invokes—agent tooling against an external API—not a standalone PM or SEO workflow.
Where it fits
Wire a game loop or app UI sound bed by routing to ACE Step when cost per second matters more than vocal polish.
Produce a short vocal hook for a launch trailer by routing to ElevenLabs when the user asks for a sung premium track.
Refresh a newsletter or course intro jingle and outpaint a 30 s draft into a two-minute royalty-free cut.
Drop a cheap tagged instrumental under a clickable prototype demo before committing to licensed stock music.
How it compares
A catalog router skill with embedded prompting recipes, not a local DAW plugin or a self-hosted weights runner.
Common Questions / FAQ
Who is ai-music for?
Solo and indie builders using coding agents who want RunComfy music generation and edits without manually choosing between ElevenLabs and ACE Step every time.
When should I use ai-music?
Use it while building integrations for app or game audio, when preparing launch trailers or ad jingles, or during grow/content work on royalty-free beds—any time the ask is generate music, make a song, background music, extend music, or fix/inpaint a track.
Is ai-music safe to install?
It enables networked Bash `runcomfy` calls that consume paid generation seconds; check the Security Audits panel on this page and cap spend before unattended agent runs.
Workflow Chain
Then invoke: ace step
SKILL.md
READMESKILL.md - Ai Music
# AI Music Generate AI music on RunComfy through one CLI — vocal songs, instrumentals, jingles, game loops, multilingual covers. This skill picks the right model from the RunComfy catalog based on the user's actual intent and ships the documented prompting patterns + the exact `runcomfy run` invoke for each. [runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=ai-music) · [Audio models](https://www.runcomfy.com/models?utm_source=skills.sh&utm_medium=skill&utm_campaign=ai-music) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=ai-music) ## Install this skill ```bash npx skills add agentspace-so/runcomfy-agent-skills --skill ai-music -g ``` ## Powered by the RunComfy CLI **Step 1 — install** (one of, see the `runcomfy-cli` skill for details): ```bash npm i -g @runcomfy/cli # global install npx -y @runcomfy/cli --version # zero-install ``` **Step 2 — sign in** (or set `RUNCOMFY_TOKEN` env var in CI / containers): ```bash runcomfy login ``` **Step 3 — generate music**: ```bash runcomfy run <vendor>/<model>/<endpoint> \ --input '{"prompt": "...", ...}' \ --output-dir ./out ``` CLI deep dive: [`runcomfy-cli`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/runcomfy-cli) skill. --- ## Pick the right model for the user's intent ### Text-to-music (generate from scratch) — newest first **ACE Step 1.5** — `acestep-ai/ace-step-1.5/text-to-audio` > Latest ACE Step generation. **50+ language vocal support**, refined structured-lyric handling, $0.0003/s. Open-weights (Apache 2.0). > Pick for: multilingual launches, vocal songs in non-English, hero-quality ACE output. > Avoid for: maximally polished commercial vocal hooks (try ElevenLabs Music) or cost-sensitive batches (try base ACE Step). **ElevenLabs AI Music Generation** — `elevenlabs/elevenlabs/music-generation` > Premium 44.1 kHz stereo, 5 s–5 min, section-level control (Intro/Verse/Chorus/Bridge), multilingual vocals, commercial-friendly. $0.0083/s (~27× ACE Step). > Pick for: hero brand campaigns, polished vocal hooks, premium commercial cuts, ad music. > Avoid for: high-volume drafts / background music libraries — cost dominates. **ACE Step (base)** — `acestep-ai/ace-step/text-to-audio` *(default for cost-sensitive work)* > Original ACE Step. Tag-driven composition, optional lyrics, 5–240 s stereo. **$0.0002/s** — cheapest CLI-reachable music model on RunComfy. > Pick for: background music libraries, jingles, game loops, drafts, cost-sensitive iteration. > Avoid for: premium vocal hooks — use **ElevenLabs Music** or **ACE Step 1.5**. ### Edit existing audio — ACE Step only (ElevenLabs has no edit endpoints) **ACE Step audio-inpaint** — `acestep-ai