{
  "slug": "audiogen",
  "name": "AudioGen MCP",
  "vendor": "Community (peerjakobsen)",
  "official": false,
  "category": "sound-design",
  "featured": false,
  "tagline": "Free, local sound-effect generation with Meta's AudioGen — no API key needed.",
  "description": "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.",
  "capabilities": [
    "sfx",
    "local-inference",
    "job-queue"
  ],
  "tools_sample": [
    "generate_sound_effect",
    "check_generation_status",
    "list_generated_sounds"
  ],
  "install": {
    "claude_code": null,
    "remote_url": null,
    "stdio_command": null
  },
  "auth": {
    "type": "none",
    "env_var": null,
    "key_url": "No key needed; model auto-downloads from Hugging Face Hub"
  },
  "pricing": "free",
  "links": {
    "repo": "https://github.com/peerjakobsen/audiogen-mcp",
    "docs": null,
    "site": null
  },
  "added": "2026-06-11",
  "verified": "2026-06-11",
  "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."
}