Media MCP Server

Example Use Cases

• 1

  Generate or edit high-quality images with customizable aspect ratios and resolutions.

• 2

  Create videos with native audio, dialogue, and sound effects from text prompts.

• 3

  Produce instrumental music or convert text to speech with voice and style control.

Description

media-mcp is an MCP server that enables AI agents to generate and edit multimedia content including images, videos, music, and speech by leveraging Google Gemini models. It supports high-resolution outputs, multi-speaker speech synthesis, and weighted music prompts, providing flexible and powerful media generation capabilities. The server can save generated media to disk or return base64 data, optimizing usage for production or experimentation.