Gemini Audio

MCP to uploads audio to gemini for analysis

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "unscene-gemini-audio-upload": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/gemini-audio-upload",
        "run",
        "gemini_audio/mcp_server.py"
      ],
      "env": {
        "GOOGLE_API_KEY": "your_api_key_here"
      }
    }
  }
}

You deploy and run a Microservice that analyzes audio files using Gemini models. This MCP server lets you upload audio with optional JSON context and system instructions, then receive detailed, model-guided analyses through MCP clients like Claude Desktop or a VS Code MCP extension.

How to use

You interact with the server through an MCP client by invoking the analyze_audio tool. Provide the path to your audio file, an optional prompt to guide the analysis, and optional context data either as a JSON file or a JSON string. You can also supply system instructions to steer how Gemini behaves during analysis. The server is designed to work with MCP clients, so you can incorporate it into your existing MCP workflows and dashboards.

How to install

Prerequisites: ensure you have Python 3.10 or higher installed on your system.

Clone the project and navigate into the project directory.
Install the required runtime tools. The server expects to be run with the MCP runtime tool. You will use the runtime to start the server and expose the analyze_audio tool to MCP clients.
Create a configuration file at the project root to provide your Gemini API key.

Additional sections

Configuration and running details are included below to help you get started quickly.

Tools exposed by the server

analyze_audio: An MCP tool that analyzes an audio file using Gemini. It accepts an absolute audio path, an optional prompt to guide the analysis, optional JSON context through a file or string, optional system instruction content, and optional model selection. It returns a structured analysis based on your inputs.

Available tools

analyze_audio

MCP tool to analyze an audio file using Gemini. Accepts audio_path, prompt, json_path, json_context, instruction_file, and model to tailor the analysis.