Blabber (OpenAI TTS)

🚀 Blabber-MCP 🗣️

A MCP server that uses the OpenAI Text-to-Speech API to provide voices for your Large Language Model (LLM)! 🔊

✨ Features

• Text-to-Speech: Convert input text into high-quality, colloquial audio.
• Voice Selection: Choose from a variety of voices provided by OpenAI (alloy, echo, fable, onyx, nova, shimmer).
• Model Selection: Use the standard model (tts-1) or the high-definition model (tts-1-hd).
• Format Options: Output audio in optional formats such as mp3, opus, aac, or flac.
• File Saving: Save the generated audio to a local file.
• Optional Playback: Automatically play the generated audio through configuration commands.
• Default Settings Configuration: Specify the default voice through configuration.

🔧 Configuration

To use this server, add its configuration to your MCP client settings file (e.g., mcp_settings.json).

1. Get an OpenAI API Key: You need to obtain an API key from OpenAI.
2. Add to MCP Settings: Add the following to the mcpServers object, replacing "YOUR_OPENAI_API_KEY" with your own key.

{
  "mcpServers": {
    "blabber-mcp": {
      "command": "node",
      "args": ["/full/path/to/blabber-mcp/build/index.js"], (Important: Use the full absolute path to `build/index.js` in the `blabber-mcp` project directory)
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "AUDIO_PLAYER_COMMAND": "xdg-open", (Optional: Specify the command to play audio (e.g., `cvlc`, `vlc`, `mpv`, `ffplay`, `afplay`, `xdg-open`; default is `cvlc`))
        "DEFAULT_TTS_VOICE": "nova" (Optional: Set the default voice (`alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`); default is `nova`)
      },
      "disabled": false,
      "alwaysAllow": []
    }
  }
}

📄 License

This project is licensed under the MIT License. For more information, see the LICENSE file.

📝 Changelog

Refer to the CHANGELOG.md file for the version update history.

❤️ Made by Pink Pixel