Text-to-Speech MCP Server

What is Text-to-Speech MCP Server?

A Model Context Protocol (MCP) server, written in TypeScript, that provides text-to-speech conversion. It allows AI assistants and other MCP clients to convert text into MP3 audio files through a standardized interface.

How to use Text-to-Speech MCP Server?

Install globally via npm install -g mcp-koko-tts, set the TTS_OUTPUT_DIR environment variable (default ~/.mcp_tts), and start the required Kokoro-FastAPI Docker container (GPU or CPU). Then configure the MCP client (e.g., Cherry Studio) with the server’s build path.

Key features of Text-to-Speech MCP Server

• Convert any text to speech audio
• Save the resulting audio as MP3 files
• Simple integration with any MCP-compatible client

Use cases of Text-to-Speech MCP Server

• Convert AI assistant responses into spoken audio
• Generate voiceovers from text for applications
• Provide accessibility for visually impaired users
• Integrate with MCP clients like Cherry Studio

FAQ from Text-to-Speech MCP Server

What runtime dependencies does the server require?

It requires a running Kokoro-FastAPI Docker container (GPU or CPU configuration) and the TTS_OUTPUT_DIR environment variable set.

How do I install the server?

Install it globally via npm: npm install -g mcp-koko-tts.

Where are the audio output files stored?

Files are saved to the directory specified by the TTS_OUTPUT_DIR environment variable, which defaults to ~/.mcp_tts.

Does the server support GPU acceleration?

Yes, when using the GPU Docker image it requires an NVIDIA GPU with CUDA 12.8 support, achieving ~35x–100x realtime speed.

What audio format does the server output?

All generated speech audio files are in MP3 format.