- Step 1: Clone the repository from GitHub.
- Step 2: Install dependencies using `npm install`.
- Step 3: Configure environment variables in `.env` (e.g., API URLs and speaker IDs).
- Step 4: Run the server locally with `npm start` or build with `npm run build` for production.
- Step 5: Connect your application to the server endpoint at `http://localhost:10100/sse`.
- Step 6: Use MCP commands to manage voice models, generate speech, and configure speakers.