MS-Lucidia-Voice-Gateway-MCP
A Model Context Protocol (MCP) server that provides text-to-speech and speech-to-text capabilities using Windows' built-in speech services. This server leverages the native Windows Speech API (SAPI) through 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
- Simple web interface for testing
- No external API dependencies
- Uses native Windows capabilities
Prerequisites
- Windows 10/11 with Speech Recognition enabled
- Node.js 16+
- PowerShell
Installation
- Clone the repository:
- Install dependencies:
- Build the project:
Usage
Testing Interface
- Start the test server:
- Open `http://localhost:3000` in your browser
- Use the web interface to test TTS and STT capabilities
Available Tools
text_to_speech
Converts text to speech using Windows SAPI.
Parameters:
- `text` (required): The text to convert to speech
- `voice` (optional): The voice to use (e.g., "Microsoft David Desktop")
- `speed` (optional): Speech rate from 0.5 to 2.0 (default: 1.0)
Example:
speech_to_text
Records audio and converts it to text using Windows Speech Recognition.
Parameters:
- `duration` (optional): Recording duration in seconds (default: 5, max: 60)
Example:
Troubleshooting
- Make sure Windows Speech Recognition is enabled: - Open Windows Settings - Go to Time & Language > Speech - Enable Speech Recognition
- Check available voices: - Open PowerShell and run: ```powershell Add-Type -AssemblyName System.Speech (New-Object System.Speech.Synthesis.SpeechSynthesizer).GetInstalledVoices().VoiceInfo.Name ```
- Test speech recognition: - Open Speech Recognition in Windows Settings - Run through the setup wizard if not already done - Test that Windows can recognize your voice
Contributing
- Fork the repository
- Create your feature branch
- Commit your changes
- Push to the branch
- Create a new Pull Request
License
MIT