What is Gemini TTS and its primary function?

Gemini TTS is an MCP (Model Context Protocol) server that integrates Google's high-fidelity Gemini 2.5 Text-to-Speech models, enabling AI assistants to generate natural-sounding and expressive speech.

What unique voice control features does Gemini TTS offer?

It provides natural language control for guiding voice style (e.g., 'Say cheerfully', 'Whisper softly') and offers access to over 30 distinct prebuilt voices like Aoede, Zephyr, and Puck.

How do I install Gemini TTS?

You can install it as a Gemini CLI extension using `gemini extensions install https://github.com/notsointresting/gemini-tts-mcp` or manually via npm. It requires a Google Gemini API Key and Node.js 18+.

Can I save the audio generated by Gemini TTS?

Yes, you can optionally save the generated speech directly to a local `.wav` file. Additionally, the tool returns raw audio data in Base64 format for flexible integration into your applications.

Gemini TTS

Name: Gemini TTS
Author: notsointresting

bynotsointresting

•

Ciencia de Datos y ML

Herramientas para Desarrolladores

Integrates high-fidelity Text-to-Speech capabilities into AI assistants using Google's Gemini 2.5 TTS models.

The Gemini TTS server provides advanced Text-to-Speech functionality to your AI assistants via the Model Context Protocol (MCP). Leveraging Google's Gemini 2.5 Flash and Pro TTS preview models, it generates natural-sounding speech with over 30 premium voices and offers fine-grained control over voice style using natural language commands. It supports direct audio file saving and outputs raw Base64 audio for flexible client-side handling, enhancing interactive AI experiences.

Características Principales

01High-Fidelity Audio generation using Gemini 2.5 Flash/Pro models

02Natural language control for guiding voice style (e.g., 'Say cheerfully')

03Access to 30+ prebuilt voices (e.g., Aoede, Zephyr, Puck)

04Option to save generated audio directly to a local .wav file

05Returns raw audio data in Base64 for flexible integration

060 GitHub stars

Casos de Uso

01Integrating advanced text-to-speech capabilities into Claude Desktop or other MCP-compatible clients

02Generating and saving spoken audio files from text input for various applications

03Adding high-quality voice output to AI assistants integrated with Gemini CLI