Aivis Speech MCP

Aivis Speech MCP is a server implementation of the Model Context Protocol (MCP) designed to provide speech synthesis capabilities via integration with the AivisSpeech Engine. It enables applications, such as AI assistants, to generate and play speech audio from text input using the MCP protocol.

• Source Code: GitHub Repository
• Category: Media Processing MCP Servers
• Tags: text-to-speech, audio, media-processing, open-source
• License: MIT

Features

• Implements the Model Context Protocol (MCP) for media and speech integration.
• Provides an interface for text-to-speech synthesis via AivisSpeech Engine.
• Offers MCP-compliant API endpoints to facilitate integration with AI assistants and other applications.
• Customizable environment via .env configuration file.
• Supports both development (with hot reload) and production modes.
• Build and test scripts included for streamlined development and deployment.
• Modular architecture for easy maintenance and extension.
• Open-source and welcoming to community contributions.

Installation & Usage

• Requires setting up environment variables in a .env file.
• Configuration for the MCP interface is handled in a .cursor/mcp.json file.
• Can be run in development mode (with hot reload) or production mode after building.
• Testing supported via provided scripts.

Pricing

• Open Source: Free to use under the MIT License.