OpenAI TTS MCP server

This MCP server enables high-quality text-to-speech generation through the OpenAI TTS API, allowing integration with Claude Desktop and other MCP-compatible clients as well as direct command-line usage.

Installation

Installing from Repository

# Clone the repository
git clone https://github.com/nakamurau1/tts-mcp.git
cd tts-mcp

# Install dependencies
npm install

# Optional: Install globally
npm install -g .

Using with npx (No Installation Required)

# Start the MCP server directly
npx tts-mcp tts-mcp-server --voice nova --model tts-1-hd

# Use the CLI tool directly
npx tts-mcp -t "Hello, world" -o hello.mp3

MCP Server

Starting the Server

# Start with default settings
npm run server

# Start with custom settings
npm run server -- --voice nova --model tts-1-hd

# Or directly with API key
node bin/tts-mcp-server.js --voice echo --api-key your-openai-api-key

Server Options

Options:
  -V, --version       Display version information
  -m, --model <model> TTS model to use (default: "gpt-4o-mini-tts")
  -v, --voice <voice> Voice character (default: "alloy")
  -f, --format <format> Audio format (default: "mp3")
  --api-key <key>     OpenAI API key (can also be set via environment variable)
  -h, --help          Display help information

Integrating with Claude Desktop

1. Open the Claude Desktop configuration file (typically at ~/Library/Application Support/Claude/claude_desktop_config.json)
2. Add the following configuration:

{
  "mcpServers": {
    "tts-mcp": {
      "command": "node",
      "args": ["full/path/to/bin/tts-mcp-server.js", "--voice", "nova", "--api-key", "your-openai-api-key"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key"
      }
    }
  }
}

Alternatively, use npx for easier setup:

{
  "mcpServers": {
    "tts-mcp": {
      "command": "npx",
      "args": ["-p", "tts-mcp", "tts-mcp-server", "--voice", "nova", "--model", "gpt-4o-mini-tts"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key"
      }
    }
  }
}

You can provide the API key in two ways:

• Direct method: Include it in the args array using the --api-key parameter
• Environment variable method: Set it in the env object as shown above

Security Note: Make sure to secure your configuration file when including API keys.

3. Restart Claude Desktop
4. When you ask Claude to "read this text aloud" or similar requests, the text will be converted to speech

Command-Line Tool

Basic Usage

# Convert text directly
tts-mcp -t "Hello, world" -o hello.mp3

# Convert from a text file
tts-mcp -f speech.txt -o speech.mp3

# Specify custom voice
tts-mcp -t "Welcome to the future" -o welcome.mp3 -v nova

CLI Options

Options:
  -V, --version           Display version information
  -t, --text <text>       Text to convert
  -f, --file <path>       Path to input text file
  -o, --output <path>     Path to output audio file (required)
  -m, --model <n>         Model to use (default: "gpt-4o-mini-tts")
  -v, --voice <n>         Voice character (default: "alloy")
  -s, --speed <number>    Speech speed (0.25-4.0) (default: 1)
  --format <format>       Output format (default: "mp3")
  -i, --instructions <text> Additional instructions for speech generation
  --api-key <key>         OpenAI API key (can also be set via environment variable)
  -h, --help              Display help information

Supported Features

Voice Characters

• alloy (default)
• ash
• coral
• echo
• fable
• onyx
• nova
• sage
• shimmer

TTS Models

• tts-1
• tts-1-hd
• gpt-4o-mini-tts (default)

Output Formats

• mp3 (default)
• opus
• aac
• flac
• wav
• pcm

Environment Configuration

You can configure the tool using system environment variables:

OPENAI_API_KEY=your-api-key-here

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.