Skip to main content
skill CX Codex

ai-music-generation — Claude Code skill: what it does, install

The ai-music-generation skill lets an agent create music and songs through belt and inference.sh. Use it for background tracks, podcast jingles, game scores, and other audio.

no license 248 installs ★ 31 updated 2026-08-31

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add 101-skills/superpowers --skill ai-music-generation -a claude-code
Open on GitHub

What ai-music-generation does

The skill gives an agent a way to run music-generation apps from the belt CLI. It supports text-to-music, instrumental tracks, songs with vocals, lyric-based generation, and soundtrack work through ElevenLabs Music, Diffrythm, and Tencent Song Generation.

ElevenLabs Music supports tracks up to 10 min and includes a commercial license. Diffrythm focuses on song generation, while Tencent Song Generation handles complete vocal songs. Prompts can describe genre, mood, instruments, and song structure.

The belt CLI must be installed and authenticated with belt login before generation commands will run. The skill grants Bash(belt *), so the agent needs permission to execute belt commands.

What it helps with

  • create background music for a video
  • generate a vocal song from lyrics
  • make a podcast intro jingle
  • prepare a soundtrack for a game
  • turn a text brief into an instrumental track

Example prompts for the agent

  • Create a calm lo-fi background track for this video using belt.
  • Generate a vocal song about summer love and put the inputs in input.json.
  • Make an epic orchestral game soundtrack with Diffrythm.

How to install ai-music-generation

1Skills CLI (Vercel)

npx skills add 101-skills/superpowers --skill ai-music-generation -a claude-code

2Manually: put the files in place

~/.claude/skills/ai-music-generation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ai-music-generation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ai-music-generation

How do I install ai-music-generation in Claude Code?

Run npx skills add 101-skills/superpowers --skill ai-music-generation -a claude-code, then check ~/.claude/skills/ai-music-generation/SKILL.md.

What does ai-music-generation do?

It lets an agent run ElevenLabs Music, Diffrythm, and Tencent Song Generation through belt for music, vocal songs, instrumental tracks, and soundtracks.

What is required for ai-music-generation to work?

Install the belt CLI and authenticate with belt login. Tencent Song Generation is the option for vocal songs, while Diffrythm can create instrumental tracks.

Similar skills

All skills for AI and ML →

From the same set81

The whole set →
prompt-engineering prompt-engineering — a skill that lays out prompt structure for text models, image generators and video models, with examples you can run through the belt CLI. CX Codex +1 251installs explainer-video-guide The explainer-video-guide skill maps an explainer video from script to assembly, with guidance for pacing, scene design, voiceover, and generated visuals. CX Codex +1 249installs logo-design-guide logo-design-guide guides AI agents through logo concept generation and prompt styling via the belt CLI, covering rules from favicon sizes to vectors. CX Codex +1 249installs ai-social-media-content ai-social-media-content produces multi-platform social media posts, videos, voiceovers, and captions via the belt command-line utility. CX Codex +1 248installs agent-ui agent-ui is a Claude Code skill that adds a ready-made AI agent interface to React and Next.js, with chat, user approvals, and browser tool calls. CX Codex +1 247installs ai-automation-workflows ai-automation-workflows — a skill that writes automated AI workflows out of belt calls: batches, chained models, cron runs, retries with a fallback model. CX Codex +1 246installs image-upscaling The image-upscaling skill for Claude Code enlarges and enhances images through inference.sh using belt, for print or high-resolution displays. CX Codex +1 246installs text-to-speech text-to-speech gives the agent ready belt commands for speech synthesis: Kokoro, ElevenLabs, Inworld TTS-2 with emotion steering, and a few more models. CX Codex +1 246installs

Project sponsors

Companies that keep this analytics open