MCP ServerSTDIOOfficialv0.1.0

Jxoesneon Gemini Audio MCP Server

Generate high-performance audio, music, and voice content using Google's Gemini 2.5 and Lyria 3 models. Built for developers who need to integrate AI-powered audio synthesis into applications via MCP.

io.github.jxoesneon/gemini-audio-mcp

Hosted URL

Local install

Transport

STDIO

Auth

1 required env var

What the Jxoesneon Gemini Audio MCP server does

How models use it and what it is built for.

Generate high-performance audio, music, and voice content using Google's Gemini 2.5 and Lyria 3 models. Built for developers who need to integrate AI-powered audio synthesis into applications via MCP.

Connect to Jxoesneon Gemini Audio

Local install — runs as a subprocess.

docker run ghcr.io/jxoesneon/gemini-audio-mcp:0.1.0

Environment variables

Configuration this server reads at startup.

  • GEMINI_API_KEYRequiredSecret

    Your Google AI Studio API Key

Resources

Where to find authoritative docs and source for Jxoesneon Gemini Audio.

Example prompts for Jxoesneon Gemini Audio

Paste any of these into Agent Studio after connecting Jxoesneon Gemini Audio.

  • Generate a 30-second ambient background music track for a meditation app
  • Create a natural-sounding voice narration for this product description text
  • Synthesize a upbeat electronic music loop with drums and synth
  • What audio models and generation parameters does this server support?

Jxoesneon Gemini Audio MCP server — FAQ

Common questions about connecting and running Jxoesneon Gemini Audio.

  • What audio formats and quality levels does this server output?

    The server leverages Gemini 2.5 and Lyria 3 for audio generation. Refer to the official Gemini API documentation for supported output formats, sample rates, and quality tiers available through these models.

  • How do I authenticate and set up the Gemini Audio MCP server?

    Set the GEMINI_API_KEY environment variable with your Google AI Studio API key, then run the Docker image: `docker run ghcr.io/jxoesneon/gemini-audio-mcp:0.1.0`. The server communicates via stdio transport.

  • Is there a cost to use this MCP server?

    Usage is billed through Google's Gemini API. Check Google AI Studio pricing for Gemini 2.5 and Lyria 3 audio generation rates.

  • Can I use this server for real-time voice generation or only batch audio synthesis?

    The registry describes this as a high-performance server but does not specify latency guarantees or real-time capabilities. Test with your use case or consult the project repository for performance benchmarks.

  • What are the alternatives to this audio MCP server?

    Other audio generation options include ElevenLabs (voice synthesis), Stability AI (music generation), and direct Gemini API calls. This server is optimized for MCP integration with Gemini 2.5 and Lyria 3 specifically.

Skip the local setup — run MCP in your browser

MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.

Open Agent Studio

Related servers

More on MCP Playground