# multimodal-audiocraft

Equips Claude Code with workflows for text-to-music and sound generation using Meta's AudioCraft tools. Helpful when building audio synthesis pipelines.

- skill · `type=skill` · Claude Code · 52 installs
- Author: Orchestra Research
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/multimodal-audiocraft
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/multimodal-audiocraft

## What it does

This skill gives Claude Code workflows for generating music and audio effects. It covers MusicGen and AudioGen. The templates handle text prompts alongside melody conditioning with reference audio. Under the hood, it details T5 embeddings and EnCodec decoding.

Running the code requires `torch>=2.0.0` and `audiocraft`. Large model checkpoints will require a capable GPU. It also includes standard bounds for duration and guidance scales.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --skill ai-research/multimodal-audiocraft
```

2. **Skills CLI (Vercel)**
```bash
npx skills add davila7/claude-code-templates --skill multimodal-audiocraft -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/multimodal-audiocraft/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/multimodal-audiocraft/

### Codex

**Manually: put the files in place**
- File: `.agents/skills/multimodal-audiocraft/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

**Manually: put the files in place**
- File: `.cursor/skills/multimodal-audiocraft/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install davila7/claude-code-templates multimodal-audiocraft
```

2. **Manually: put the files in place**
- File: `.github/skills/multimodal-audiocraft/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/ai-research/multimodal-audiocraft
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/multimodal-audiocraft/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/multimodal-audiocraft

## When to use it
- write Python code for text-to-music generation with MusicGen
- synthesize background sound effects using AudioGen
- condition song generation on an input melody track
- configure sampling parameters like temperature and guidance scale

## Example prompts
- Generate a 30-second electronic track prompt using MusicGen
- Write a script to synthesize barking dog sounds with AudioGen
- Show how to pass melody.wav into musicgen-melody with torchaudio

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 350300 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 804 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md