Provides tools to generate high-quality sound effects from text descriptions using Meta's AudioGen model, supporting both single and batch audio generation.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AudioGen MCP Servergenerate a realistic sound effect of a wine glass breaking on a tile floor"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AudioGen MCP Server
An MCP server that generates sound effects from text descriptions using Meta's AudioGen model. Designed for Apple Silicon Macs.
Prerequisites
macOS with Apple Silicon (M1/M2/M3/M4)
Python 3.9-3.11 (3.12+ not yet supported by audiocraft)
ffmpeg:
brew install ffmpeg~4GB disk space for model weights
~8GB RAM recommended
Installation
Due to audiocraft's complex dependencies (xformers doesn't build on Apple Silicon), installation requires a specific order:
The first run will download the AudioGen model (~2GB).
Configure Claude Code
Or add to ~/.config/claude/claude_desktop_config.json:
Available Tools
Tool | Description |
| Start a background generation job, returns job_id |
| Poll job status by job_id until completed |
| List all jobs and their current status |
| List previously generated audio files |
| Check if model is loaded and device info |
How It Works
Generation runs in the background to avoid timeouts:
Call
generate_sound_effectwith your prompt → returnsjob_idPoll
check_generation_statuswith thejob_idevery 10-15 secondsWhen status is
completed, the result includesfile_path
Example Prompts
Once configured, ask Claude Code to generate sounds:
"Generate an explosion sound effect"
"Create a dark ambient tension drone, 10 seconds"
"Make a retro 8-bit power-up sound, 2 seconds long"
"Generate footsteps on gravel, 5 seconds"
Prompt Tips
For best results, be specific:
Include style, mood, and context for better results.
Performance
~18 seconds to generate 1 second of audio on Apple Silicon
5 seconds of audio ≈ 90 seconds generation time
10 seconds of audio ≈ 180 seconds generation time
First generation takes longer (model loading ~5s)
Uses Metal Performance Shaders (MPS) for GPU acceleration
Output
Generated files save to ~/audiogen_outputs/ by default as WAV or OGG files.
Troubleshooting
Installation fails with xformers error
This is expected on Apple Silicon. The server mocks xformers at runtime since it's only needed for CUDA. If audiocraft installation fails, try:
Model download fails
Ensure stable internet and sufficient disk space. The model downloads from HuggingFace Hub.
Slow generation
Check device with get_model_status tool. CPU fallback is 10-20x slower than MPS.
MPS not available
Requires macOS 12.3+ and PyTorch 2.0+.
License
MIT License - see LICENSE file.
Acknowledgments
Meta AudioCraft - The underlying AI model
MCP - Model Context Protocol specification