Provides a unified interface for text-to-speech engines, including Kokoro TTS and OpenAI TTS.
This server offers a versatile text-to-speech solution built on the Model Context Protocol (MCP) framework, enabling access to multiple TTS engines, such as the high-quality local Kokoro TTS and the cloud-based OpenAI TTS, through a unified interface. It supports real-time streaming, configurable voice selection, voice customization via natural language instructions (OpenAI), speed adjustment, and playback control for stopping audio and clearing the queue, ensuring seamless integration with Claude and other LLMs.