Blabber (OpenAI TTS) MCP server

Blabber-MCP is a server that integrates with the Model Context Protocol (MCP) to provide text-to-speech capabilities for Large Language Models using OpenAI's Text-to-Speech API. It allows your LLM to convert text into spoken audio with various voice options and quality settings.

Installation and Configuration

To use Blabber-MCP, you need to add its configuration to your MCP client's settings file:

1. Obtain an OpenAI API key from OpenAI's platform
2. Add the server configuration to your MCP settings file (e.g., mcp_settings.json):

{
  "mcpServers": {
    "blabber-mcp": {
      "command": "node",
      "args": ["/full/path/to/blabber-mcp/build/index.js"],
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "AUDIO_PLAYER_COMMAND": "xdg-open",
        "DEFAULT_TTS_VOICE": "nova"
      },
      "disabled": false,
      "alwaysAllow": []
    }
  }
}

Configuration Options

• OPENAI_API_KEY (required): Your OpenAI API key
• AUDIO_PLAYER_COMMAND (optional): Command to play audio files (defaults to "cvlc")
  • Options include: "cvlc", "vlc", "mpv", "ffplay", "afplay", "xdg-open"
• DEFAULT_TTS_VOICE (optional): Default voice to use (defaults to "nova")
  • Available voices: "alloy", "echo", "fable", "onyx", "nova", "shimmer"

Important: Make sure to use the full absolute path to the build/index.js file in your configuration.

Using the Text-to-Speech Tool

Once configured, you can use the text_to_speech tool with your MCP client.

Tool Parameters

• input (string, required): The text to convert to speech
• voice (string, optional): Voice to use ("alloy", "echo", "fable", "onyx", "nova", "shimmer")
• model (string, optional): Model quality ("tts-1" or "tts-1-hd")
• response_format (string, optional): Audio format ("mp3", "opus", "aac", "flac")
• play (boolean, optional): Automatically play audio after generation

Example Usage

To generate speech with the Shimmer voice and play it automatically:

<use_mcp_tool>
  <server_name>blabber-mcp</server_name>
  <tool_name>text_to_speech</tool_name>
  <arguments>
  {
    "input": "Hello from Blabber MCP!",
    "voice": "shimmer",
    "play": true
  }
  </arguments>
</use_mcp_tool>

Response Format

The tool saves audio to the output/ directory and returns a JSON response:

{
  "message": "Audio saved successfully. Playback initiated using command: cvlc",
  "filePath": "path/to/speech_1743908694848.mp3", 
  "format": "mp3",
  "voiceUsed": "shimmer"
}

Feature Overview

Blabber-MCP supports:

• High-quality text-to-speech conversion
• Multiple voice options (alloy, echo, fable, onyx, nova, shimmer)
• Standard (tts-1) and high-definition (tts-1-hd) models
• Multiple audio formats (mp3, opus, aac, flac)
• Optional automatic playback of generated audio
• Custom default voice configuration

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.