MCP_tts_server

MCP_tts_server

3.3

If you are the rightful owner of MCP_tts_server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The MCP TTS Server is a versatile Text-to-Speech server built on the Model Context Protocol framework, providing access to multiple TTS engines through a unified interface.

The MCP TTS Server is designed to offer a seamless Text-to-Speech experience by integrating multiple TTS engines into a single, unified server. It supports both local and cloud-based TTS engines, namely Kokoro TTS and OpenAI TTS, allowing users to choose the best option for their needs. The server is capable of real-time streaming audio playback, making it ideal for applications requiring immediate audio feedback. It also supports voice customization through natural language instructions, particularly with the OpenAI TTS engine, providing a personalized audio experience. The server is built with the Model Context Protocol, ensuring smooth integration with other MCP-supported platforms like Claude Desktop. Additionally, it offers configurable voice selection, speed adjustment, and playback control, making it a comprehensive solution for TTS needs.

Features

  • Multiple TTS engines in one unified server
  • Real-time streaming audio playback
  • Configurable voice selection and speed adjustment
  • Support for voice customization via natural language instructions
  • Playback control for stopping audio and clearing the queue

Tools

  1. tts

    Convert text to speech using the preferred engine and streams the speech to the user.

  2. tts_stop_playback_and_clear_queue

    Stops the currently playing audio and clears all pending TTS requests from the queue.

  3. tts_examples

    Provides research-based examples of effective voice instructions for OpenAI TTS.

  4. get_tts_instructions

    Fetches TTS instructions by calling get_voice_info.