# kentaro
## 基本信息
- Slug: `kentaro-aivis-speech-mcp`
- Source: modelscope
- Publisher: @kentaro/aivis-speech-mcp
- Categories: speech-processing / autonomous-agents
- Hosted: No
- License: Unknown
- Source URL: https://www.modelscope.cn/mcp/servers/@kentaro/aivis-speech-mcp
## 简介
暂无描述。
## MCP Server 详情

# AivisSpeech MCP Server

This is the implementation of the Model Context Protocol (MCP) server for AivisSpeech. This server works in conjunction with the AivisSpeech Engine to provide an interface for speech synthesis. Through the MCP protocol, applications such as AI assistants can easily utilize AivisSpeech's speech synthesis capabilities.

## Overview

The AivisSpeech MCP Server provides the following features:

- API endpoints compliant with the MCP protocol
- High-quality speech synthesis through integration with the AivisSpeech Engine
- Type-safe design using TypeScript
- Simple setup and a highly scalable architecture

## Prerequisites

- Node.js 18.x or higher
- npm 9.x or higher
- AivisSpeech Engine (needs to be installed separately)

## Installation

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

# Install dependencies
npm install

# Build
npm run build

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

# Cursor MCP configuration
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 path to your project
# 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:10101  # AivisSpeech Engine API endpoint

# Speaker Configuration
AIVIS_SPEECH_SPEAKER_ID=888753760  # Default speaker ID


## Cursor MCP Configuration

Configure the following settings in the `.cursor/mcp.json` file:

json
{
  "mcpServers": {
    "AivisSpeech-MCP": {
      "command": "node",
      "args": ["/path/to/aivis-speech-mcp/dist/index.js"]
    }
  }
}


Replace `/path/to/aivis-speech-mcp/dist/index.js` with the actual path to your project.
For Windows, escape backslashes or use forward slashes.
Example: `"C:/Users/username/path/to/aivis-speech-mcp/dist/index.js"`

## Usage

### Development Mode

During development, you can start the server with hot-reload functionality using the following command:

bash
npm run dev


### Build

To build for production, run the following command:

bash
npm run build


### Production Mode

After building, start the server in production mode using the following command:

bash
npm start


### Testing

To run tests, use the following command:

bash
npm test


## Architecture

The AivisSpeech MCP Server consists of the following components:

- **MCP Service**: Provides a server compliant with the Model Context Protocol and handles requests from clients.
- **AivisSpeech Service**: Communicates with the AivisSpeech Engine API to perform speech synthesis.

## API Specification

The server provides API endpoints that comply with the MCP protocol. The main functionalities include:

- Speech synthesis (generating speech from text)
- Retrieving speaker information
- Setting voice styles

For detailed API specifications, refer to the [AivisSpeech Engine API Specifications](https://aivis-project.github.io/AivisSpeech-Engine/api/).

## Integration with MCP Protocol

This server implements the Model Context Protocol (MCP), allowing seamless integration with applications such as AI assistants. For more details on the MCP protocol, refer to the [MCP Official Documentation](https://modelcontextprotocol.github.io/).## Troubleshooting

Common issues and solutions:

- **Cannot connect to AivisSpeech Engine**: Please check if `AIVIS_SPEECH_API_URL` in the `.env` file is correctly set.
- **Audio does not play**: Check your system's audio settings and ensure that the appropriate audio device is selected.
- **Speaker ID not found**: Verify that the AivisSpeech Engine is running properly and check for available speaker IDs.

## Contributions

Please use the GitHub Issue tracker for bug reports or feature requests. Pull requests are also welcome.

## License

[MIT](LICENSE)

## Acknowledgments

- [AivisSpeech Engine](https://github.com/aivis-project/AivisSpeech-Engine) team
- Developers of the [Model Context Protocol](https://modelcontextprotocol.github.io/)