Magic Voice (Smart Serve Project)

Official Website: https://magicvoice.online

Magic Voice is an advanced AI voice cloning and TTS (Text-to-Speech) platform. Experience the power of AI voice technology directly on our official website.

This is a multi-component project with:

• Frontend: Vue 3.js application
• Backend: Spring Boot REST API
• LLM Service: Python Flask application

Project Structure

smart-serve/
├── frontend/                 # Vue 3 frontend
│   ├── src/
│   │   ├── components/       # Vue components
│   │   ├── views/            # Page views
│   │   ├── assets/           # Static assets
│   │   ├── router/           # Vue Router configuration
│   │   └── store/            # Pinia state management
│   ├── public/
│   ├── package.json          # Dependencies and scripts
│   └── vite.config.js        # Vite configuration
├── backend/                  # Spring Boot backend
│   ├── src/main/java/        # Java source files
│   ├── src/main/resources/   # Configuration files
│   └── pom.xml              # Maven dependencies
└── llm-python/              # Python LLM service
    ├── api/                 # Flask application
    ├── services/            # LLM service logic
    ├── models/              # ML models (if any)
    ├── utils/               # Utility functions
    ├── config/              # Configuration files
    └── requirements.txt     # Python dependencies

Getting Started

Frontend Setup

1. Navigate to the frontend directory:

cd frontend

2. Install dependencies:

npm install

3. Start the development server:

npm run dev

The frontend will be accessible at http://localhost:3000

Backend Setup

1. Navigate to the backend directory:

cd backend

2. Build the project:

mvn clean install

3. Run the application:

mvn spring-boot:run

The backend will be accessible at http://localhost:80080

LLM Service Setup

1. Navigate to the llm-python directory:

cd llm-python

2. Create a virtual environment:

python -m venv venv

3. Activate the virtual environment:

# On Windows
venv\Scripts\activate
# On macOS/Linux
source venv/bin/activate

4. Install dependencies:

pip install -r requirements.txt

5. Run the application:

python api/app.py

The LLM service will be accessible at http://localhost:5000

Configuration

Environment variables for each service:

Frontend (environment variables in .env)

• VITE_API_URL=http://localhost:8080 (Backend API URL)

Backend (application.properties)

• server.port=8080 (Port to run the server)
• spring.datasource.url=jdbc:h2:mem:testdb (Database URL)

LLM Service (.env file)

• LLM_MODEL_NAME=gpt2 (Default model name)
• API_HOST=0.0.0.0 (Host for the API)
• API_PORT=5000 (Port for the API)