AivisSpeech

This Model Context Protocol (MCP) server facilitates seamless integration with the AivisSpeech text-to-speech engine, enabling AI assistants and various applications to convert text into high-quality, natural-sounding Japanese speech. It supports multiple voice characters, offers customizable parameters like speed, pitch, and volume, and provides cross-platform audio playback. The server also includes features for real-time engine status monitoring and smart error handling, simplifying the process of adding sophisticated speech capabilities to your projects.