Gemini TTS MCP Server

Example Use Cases

• 1

  Generate high-fidelity, natural-sounding speech from text using advanced TTS models.

• 2

  Flexible voice style control through natural language instructions.

• 3

  Multiple voice options and local audio file saving capabilities.

Description

This MCP server enables AI assistants to generate natural-sounding speech with over 30 prebuilt voices using Google's Gemini 2.5 Flash and Pro TTS preview models. It supports natural language control for voice style and can output audio as raw base64 data or save directly to local .wav files. The server requires a Gemini API key and integrates easily with Gemini CLI or standalone setups.