Welcome to the Gemini Audio MCP Wiki! 🎵

Gemini Audio MCP is a high-performance server designed to bridge the gap between AI assistants and professional-grade audio generation. Whether you're a game developer looking for procedural soundscapes or a power user building the ultimate productivity tool, this wiki will help you get the most out of the system.

🚀 Navigation

🎙️ Prompt Engineering Guide

Learn how to craft the perfect prompts for soundscapes, voices, and music. Understand the nuances of the Gemini 2.0 Live API and Lyria 3 models.

🛠️ Troubleshooting & FFmpeg Setup

Detailed installation guides for all operating systems and solutions to common "FFmpeg not found" errors.

🎛️ Audio Formats Reference

A deep dive into the 10+ supported formats (MP3, OGG, FLAC, OPUS, etc.) and how to optimize for quality vs. file size.

🐳 Docker & Deployment

Advanced configuration for running Gemini Audio MCP in containers or on cloud infrastructure.

---

🏗️ Technical Foundation

If you are looking for the internal system design, please refer to the Architecture Document in the main repository.

🤝 Community & Support

• Issues: Report bugs or request features on the GitHub Issues page.
• Glama: Check our status and scores on Glama.ai.