# AudioGen MCP

> Free, local sound-effect generation with Meta's AudioGen — no API key needed.

- **Category:** Sound Design & SFX
- **Vendor:** Community (peerjakobsen) (community)
- **Pricing:** free
- **Verified:** 2026-06-11

## What it does

Community MCP server that runs Meta's AudioGen (AudioCraft) locally to generate sound effects from text descriptions, with async job tracking. Attractive for filmmakers who want unlimited, offline, no-cost SFX drafts without sending prompts to a cloud API; the model (~2GB) downloads from Hugging Face on first run.

## Connect

- Follow the vendor's instructions: see links below

**Auth:** none — No key needed; model auto-downloads from Hugging Face Hub

## Capabilities

`sfx` · `local-inference` · `job-queue`

## Sample tools

`generate_sound_effect` · `check_generation_status` · `list_generated_sounds`

## Field notes

Very early stage (v0.1.0, Jan 2026), Apple Silicon only, manual Python 3.11 venv setup required. For higher-quality cloud SFX, prefer ElevenLabs text_to_sound_effects or CassetteAI SFX via the fal MCP.

## Links

- Repo: https://github.com/peerjakobsen/audiogen-mcp

---

Structured data: https://mcp.film/api/mcps/audiogen.json · Directory: https://mcp.film
