# AI Music Generation — model skill for AI music

> **For AI agents:** find the right skill in one call — `curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"` returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the use-case page.

Generate songs and instrumentals with ElevenLabs Music, DiffRhythm or Tencent Song Generation.

- **Type:** [Model](https://skills.varg.ai/models.md) · [AI music](https://skills.varg.ai/browse/skills/ai-music.md)
- **Slug:** `inference-sh-ai-music-generation`
- **Status:** live
- **Publisher:** inference.sh (vendor, verified)
- **License:** MIT
- **Source:** https://github.com/inference-sh/skills/tree/main/tools/audio/ai-music-generation
- **Works in:** Claude Code, Codex, Cursor, Gemini CLI
- **Requires:** inference.sh account, belt CLI (`belt login`)
- **Cost:** Billed by inference.sh
- **Adoption:** 6 installs, 781 GitHub stars (skills.sh, 2026-10-26)

## What it does

Music and song generation through inference.sh's `belt` CLI. It offers ElevenLabs Music (up to 10 minutes, commercial license), DiffRhythm for fast song generation and Tencent Song Generation.

## Use when

- A song with vocals
- Background music for a video

## Install

- Claude Code: `npx skills add inference-sh/skills --skill ai-music-generation -a claude-code`
- Codex: `npx skills add inference-sh/skills --skill ai-music-generation -a codex`
- Cursor: `npx skills add inference-sh/skills --skill ai-music-generation -a cursor`
- Gemini CLI: `npx skills add inference-sh/skills --skill ai-music-generation -a gemini-cli`

**Models it drives:** eleven_music, diffrhythm, tencent-song-generation

## Example output

https://skills.varg.ai/previews/inference-sh-ai-music-generation.mp3 — DiffRhythm (the skill's quick-start model, infsh/diffrythm) English rock demo from its official project page: a full song with vocals on LLM-written lyrics, styled from a reference clip; cut from where the vocals come in (credit: ASLP Lab, NWPU (DiffRhythm demo), https://aslp-lab.github.io/DiffRhythm.github.io/)

## More AI music skills

- [ElevenLabs Music](https://skills.varg.ai/skills/elevenlabs-music.md): Compose songs, instrumentals, jingles and background tracks from a prompt or a section-by-section plan.
- [ElevenLabs Music (inference.sh)](https://skills.varg.ai/skills/inference-sh-elevenlabs-music.md): Compose royalty-free tracks up to 10 minutes from a text prompt with ElevenLabs Music, via inference.sh.

## Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt