The Gemini Audio MCP server brings enterprise-grade generative audio directly to your AI assistant. Built in high-performance Rust, it leverages Google's state-of-the-art models to provide a unified bridge for environmental sound design, expressive narration, and professional music production. ✨ Key Capabilities * 🎙️ Infinite Soundscapes: Generate complex, immersive environmental audio using the Gemini 2.0 Multimodal Live API. * 🎵 Music & SFX: Create high-fidelity rhythmic loops, full songs, and discrete foley cues via Google's Lyria 3 Pro and Clip models. * 🗣️ Expressive Voice: Convert text to speech with natural voice direction and emotional nuances. * 🎲 Seamless Looping: Features a proprietary 100ms micro-crossfade algorithm to ensure click-free, non-repeating background audio. * 🎭 Cinematic Transitions: Smoothly blend and crossfade between two distinct audio prompts for dynamic environment changes. * 🎛️ Universal Encoding: Direct Stdin-to-FFmpeg piping allows for zero-latency transcoding into 10+ formats (MP3, OGG, FLAC, OPUS, WAV, etc.). 🎮 Use Cases * Game Developers (UE5, Godot, Blender): Instantly generate procedural soundscapes and NPC dialogue lines during development. * Content Creators: Automate foley and background texture generation for video projects. * Productivity: Enhance your AI workspace with high-quality narration and focus-oriented ambient audio. --- 🛠️ Requirements * FFmpeg: Must be installed on the system path for audio transcoding. * API Key: A valid Google AI Studio (Gemini) API Key.

An open-source AI agent that brings the power of Gemini directly into your terminal.

Gemini CLI Tips and Tricks

Performs automated multi-step web research using Google Search API and Gemini models to generate diverse search queries, conduct parallel searches, and synthesize comprehensive answers with proper source citations through configurable research depth levels.

Skills for the Gemini API, SDK and model/agent interactions

Analyze images and videos with Gemini to get fast, reliable visual insights. Handle content from URLs and YouTube links. Summarize scenes, identify objects, and extract key details for reports or automation. This is remote version, check local branch in github to use local tools.

:octocat: GitHub Emoji for C#, dotnet and beyond

Prompt library with recursive gem composition, REST + MCP access. Built with FastAPI, FastMCP, Next.js, and Supabase.

Leverage the power of Gemini API for intelligent model selection and advanced file handling. Optimize your AI operations with seamless integration and efficient processing across various file types. Enhance your productivity by utilizing the right tools for your specific tasks effortlessly.

Genderize MCP — gender prediction from first name (genderize.io, free, no auth)

Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview preparation, and coding preparation.

Five lessons, learn how to really apply AI to your .NET Applications

The Generative AI Toolkit is a lightweight library for building, testing and evaluating AI agents in Python, using any of the LLMs supported by the Amazon Bedrock Converse API.

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.

MCP Server for GenLobe SaaS API - Provides AI assistants with comprehensive API documentation for building frontend applications

Industrial intelligence for AI agents. Conviction scores and diligence for 10,000+ industrials.

Geo MCP — geographic utilities from free public APIs

US address intelligence: 120M+ addresses, verify, suggest, reverse geocode, coverage stats.

Turn GPS coordinates into place name, category, and live opening hours via OpenStreetMap.

DEPRECATED: This package is no longer maintained. Use https://github.com/MCPmed/GEOmcp instead.

MCP-Server für deutsche Behörden-Daten — Autobahn, Wetter, Warnungen, Energie, Statistik, Gesetze, Politik und mehr

Search live credit card merchant offers across Amex, Chase, Citi, PayPal, Rakuten, Capital One.

Search and book tours and travel experiences in 40+ countries via MCP.

MCP server that bridges Figma plugin data to AI tools without hitting API rate limits

MCP server with GitHub repository and workflow tools