Aivisspeech

🚀 AivisSpeech MCP Server

AivisSpeech MCP Server is an implementation of the Model Context Protocol (MCP) for speech synthesis. It works in conjunction with the AivisSpeech engine to provide speech synthesis interfaces. Through the MCP protocol, applications such as AI assistants can easily utilize the speech synthesis capabilities of AivisSpeech.

🚀 Quick Start

AivisSpeech MCP Server offers the following features:

• API endpoints compliant with the MCP protocol
• High-quality speech synthesis (powered by the AivisSpeech engine)
• TypeScript type safety design
• Simple setup and a highly scalable architecture

✨ Features

Prerequisites

• Node.js 18.x or higher
• npm 9.x or higher
• AivisSpeech engine (to be installed separately)

📦 Installation

# Clone the repository
git clone https://github.com/kentaro/aivis-speech-mcp.git
cd aivis-speech-mcp

# Install dependencies
npm install

# Build the project
npm run build

# Set up environment variables
cp .env.sample .env
# Edit the .env file and configure the necessary settings

# Configure Cursor MCP
cp .cursor/mcp.json.sample .cursor/mcp.json
# Replace "/path/to/aivis-speech-mcp/dist/index.js" in the mcp.json file
# with the actual project path
# Example: "C:/Users/username/path/to/aivis-speech-mcp/dist/index.js"

Environment Configuration

Configure the following settings in the .env file:

# AivisSpeech API Configuration
AIVIS_SPEECH_API_URL=http://localhost:10086  # Example address, modify according to actual situation
AIVIS_SPEECH_API_KEY=your_api_key_here      # Replace with the actual API key

# Other configurations (if any)
SAMPLE_TEXT=hello                            # Example text

💻 Usage Examples

Basic Usage Steps:

1. Install dependencies: Run npm install to install the required modules.
2. Configure the environment: Edit the .env file and fill in the correct API address and key.
3. Build the project: Run npm run build to build the project.
4. Start the service: Run npm start to start the server.

Example Commands:

# Install dependencies
npm install

# Build the project
npm run build

# Start the server
npm start

📚 Documentation

Architecture

• Frontend: Responsible for receiving user requests and displaying results.
• Backend: Handles business logic and communicates with the AivisSpeech engine.
• Engine: Provides speech synthesis services.

API Specifications

Request Format:

{
  "text": "hello world",
  "speaker_id": "1",
  "format": "wav"
}

Response Format:

{
  "audio_url": "http://example.com/audio.wav",
  "duration": 3.5
}

MCP Protocol Integration

Achieve seamless integration with AI assistants through the MCP protocol. The specific steps are as follows:

1. Register the service: Register the speech synthesis service at the MCP center.
2. Configure parameters: Set relevant parameters (such as pitch, speed, etc.).
3. Handle requests: Receive and process synthesis requests from the MCP.

Troubleshooting

Common Issues and Solutions:

• Unable to connect to the AivisSpeech engine:

  • Check if the AIVIS_SPEECH_API_URL in the .env file is correct.
  • Ensure that the engine is running and the network is accessible.

• Speech not playing:

  • Check the system audio settings and ensure that the correct audio device is selected.
  • Ensure that the path and permissions of the generated audio file are correct.

• Invalid speaker_id:

  • Confirm that the speaker_id exists in the AivisSpeech engine.
  • Refer to the engine documentation for the list of available speaker IDs.

🤝 Contribution

We welcome you to submit issues or feature requests through the GitHub Issue Tracker. Pull Requests are also welcome!

📄 License

MIT

🙏 Acknowledgments

• AivisSpeech engine team
• Model Context Protocol developers