Ms Lucidia Voice Gateway MCP

🚀 MS-Lucidia-Voice-Gateway-MCP

A Model Context Protocol (MCP) server that leverages the built-in Windows voice services to provide Text-to-Speech (TTS) and Speech-to-Text (STT) capabilities. This server calls the local Windows Speech API (SAPI) via PowerShell commands, eliminating the need for external APIs or services.

✨ Features

• Text-to-Speech (TTS) using Windows SAPI voices.
• Speech-to-Text (STT) using Windows Speech Recognition (SR).
• A simple web interface for testing.
• No external API dependencies.
• Utilizes local Windows features.

📋 Prerequisites

• Windows 10/11 with Speech Recognition enabled.
• Node.js 16+.
• PowerShell.

📦 Installation

1. Clone the repository:

git clone https://github.com/ExpressionsBot/MS-Lucidia-Voice-Gateway-MCP.git
cd MS-Lucidia-Voice-Gateway-MCP

2. Install the dependencies:

npm install

3. Build the project:

npm run build

💻 Usage Examples

Basic Usage

Test Interface

1. Start the test server:

npm run test

2. Open http://localhost:3000 in your browser.
3. Use the web interface to test the TTS and STT features.

Advanced Usage

text_to_speech

Converts text to speech using Windows SAPI voices.

Parameters:

• text (required): The text to be converted.
• voice (optional): The voice to be used (e.g., "Microsoft David Desktop").
• speed (optional): The speech speed, ranging from 0.5 to 2.0 (default: 1.0).

Example:

fetch('http://localhost:3000/tts', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    text: "Hello, this is a test",
    voice: "Microsoft David Desktop",
    speed: 1.0
  })
});

speech_to_text

Records audio and converts it to text using Windows Speech Recognition.

Parameters:

• duration (optional): The recording duration in seconds (default: 5, maximum: 60).

Example:

fetch('http://localhost:3000/stt', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    duration: 5
  })
}).then(response => response.json())
  .then(data => console.log(data.text));

🔧 Troubleshooting

1. Ensure that Windows Speech Recognition is enabled:
   • Open Windows Settings.
   • Navigate to Time & Language > Speech.
   • Enable Speech Recognition.
2. Check the available voices:
   • Open PowerShell and run:

   Add-Type -AssemblyName System.Speech
   (New-Object System.Speech.Synthesis.SpeechSynthesizer).GetInstalledVoices().VoiceInfo.Name
   

3. Test Speech Recognition:
   • Open Speech Recognition in Windows Settings.
   • Complete the installation wizard if not already done.
   • Test if Windows can recognize your speech.

🤝 Contribution

1. Fork the repository.
2. Create a feature branch.
3. Commit your changes.
4. Push to the branch.
5. Create a new Pull Request.

📄 License

MIT