ai-music
๐ฏSkillfrom agentspace-so/runcomfy-agent-skills
|A smart music generation router for RunComfy that picks the right model based on your intent, supporting ElevenLabs (premium vocal tracks) and ACE Step (open-weights, ~27x cheaper), with inpainting and outpainting for editing existing tracks.
Overview
AI Music is a smart music generation router for the RunComfy platform, called through the runcomfy CLI. It picks the right model from the RunComfy catalog based on intent: ElevenLabs AI Music Generation for premium 44.1 kHz stereo vocal tracks ($0.0083/s), ACE Step and ACE Step 1.5 for open-weights tag-driven composition with multilingual lyrics ($0.0002-$0.0003/s, approximately 27x cheaper), plus ACE Step audio-inpaint for regenerating sections and audio-outpaint for extending tracks. The skill handles vocal songs, instrumentals, jingles, game loops, and multilingual covers.
Key Features
- Intelligent model routing - Automatically selects between ElevenLabs Music (premium vocal quality) and ACE Step (budget-friendly open-weights) based on the user's intent, quality needs, and budget.
- Full music editing suite - Beyond generation, access ACE Step audio-inpaint to regenerate a specific time range (fix a bad chorus, replace a section) and audio-outpaint to extend a track before or after its current duration.
- Wide format coverage - Generate premium vocal songs with structured lyrics, instrumental beds, game loops, podcast intros, jingles, theme music, and multilingual tracks from text prompts.
- Cost-optimized workflows - Route to ACE Step ($0.0002/s) for drafting and library building, then to ElevenLabs ($0.0083/s) for hero-quality final delivery, with the skill guiding the selection.
Who is this for?
- Content creators and marketers who need a single skill that picks the right music model for any task, from cheap background loops to premium vocal hooks
- Music producers exploring AI-generated compositions who want both generation and editing (inpaint/outpaint) capabilities in one CLI-accessible tool
- Development teams building music generation features who need intelligent model routing across multiple providers with different quality and cost tiers
Same repository
agentspace-so/runcomfy-agent-skills(30 items)
Installation
npx vibeindex add agentspace-so/runcomfy-agent-skills --skill ai-musicnpx skills add agentspace-so/runcomfy-agent-skills --skill ai-music~/.claude/skills/ai-music/SKILL.mdSKILL.md
More from this repository10
A RunComfy skill that generates images using Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family. Optimized for rapid iteration, social thumbnails, and in-image typography with configurable resolution tiers and safety tolerance.
A smart intent-routing skill for image editing on RunComfy that selects the best model based on the editing task. Routes to Nano Banana Edit for batch edits up to 20 images, GPT Image 2 for multilingual text rewrite, Flux Kontext Pro for single-shot precise edits, or Z-Image Turbo for mask-driven inpainting.
Provides Kling 3.0 video generation on RunComfy, covering all six endpoints across three quality tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video) for Kuaishou's third-generation cinematic video model with native synchronized audio.
Edit images with Google Nano Banana 2 on RunComfy, supporting batch edits of up to 20 images per call with strong identity preservation. Features localized edits using spatial language, background swaps, and configurable resolution up to 4K.
Generate text-to-video with Wan-AI's Wan 2.7 on RunComfy, featuring multi-reference conditioning and audio-driven lip-sync via custom audio tracks. Supports prompt expansion, negative prompts, and up to 1080p resolution through the RunComfy CLI.
Edit images with OpenAI GPT Image 2 on RunComfy, excelling at multilingual in-image text editing across any script (Latin, kana, CJK, Cyrillic, Arabic) and multi-reference composition with up to 10 input images. Ideal for identity-preserving edits and layout-precise repositioning.
Generate text-to-video with HappyHorse 1.0 on RunComfy, currently ranked #1 on Artificial Analysis Video Arena. Supports native 1080p with in-pass synchronized audio, multi-shot character consistency, and 6-language prompt support via the RunComfy CLI.
Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy, supporting multi-modal references including up to 9 images, 3 videos, and 3 audio tracks. Features native lip-synced audio generation and is ideal for brand-consistent multi-language narratives.
A RunComfy skill for generating images with Black Forest Labs' Flux 2 Klein, the distilled low-latency variant of Flux 2. Supports 9B and 4B model variants with sub-second inference for real-time art direction, rapid concepting, and multi-reference brand styling.
The foundation skill for the RunComfy platform, providing a single CLI to install, authenticate, and invoke hundreds of model endpoints including image generation, video, face-swap, lip-sync, and LoRA training.