MCP TTS Server

Name: MCP TTS Server
Author: kristofferv98

@kristofferv98

リポジトリ

MCP TTS Server について

MCP Server wrapper for TTS engines (Kokoro TTS and OpenAI TTS)

#text-to-speech #tts #mcp-server

基本情報

カテゴリ

その他

ライセンス

View license

ランタイム

python

トランスポート

stdio

公開者

kristofferv98

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "MCP_tts_server": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP TTS Server?

MCP TTS Server is a Text-to-Speech server built on the Model Context Protocol (MCP) framework. It provides a unified interface to multiple TTS engines—Kokoro TTS (local) and OpenAI TTS (cloud)—for use with Claude Desktop and other MCP-compatible hosts.

How to use MCP TTS Server?

Install prerequisites (Python ≥3.10, uv), clone the repository, create a virtual environment, and install dependencies. Configure an OpenAI API key in a .env file if using the OpenAI engine. Integrate with Claude Desktop via fastmcp install or by adding the server to claude_desktop_config.json. The server exposes the tts tool to convert text to speech with engine, voice, speed, and instructions parameters.

Key features of MCP TTS Server

Supports Kokoro (local) and OpenAI (cloud) TTS engines
Real-time streaming audio playback
MCP protocol integration with Claude and other LLMs
Configurable voice selection for both engines
Voice customization via natural language instructions (OpenAI)
Playback control: stop and clear the audio queue

Use cases of MCP TTS Server

Enabling Claude to speak responses using a local or cloud TTS engine
Generating speech offline with Kokoro without external API calls
Using OpenAI’s high-quality voices with customizable instructions for character or emotion
Stopping ongoing speech and clearing queued requests on demand

FAQ from MCP TTS Server

What TTS engines does the server support?

The server supports Kokoro TTS (local) and OpenAI TTS (cloud) through a single unified interface.

Do I need an API key to use OpenAI TTS?

Yes, an OpenAI API key is required and must be set in a .env file. Kokoro TTS works entirely locally with no API key.

How do I integrate this server with Claude Desktop?

You can register the server using fastmcp install ./tts_mcp.py --name tts, or manually add the server configuration to Claude Desktop’s claude_desktop_config.json.