- Step1: Clone the repository from GitHub
- Step2: Install dependencies using bun or npm
- Step3: Configure environment variables (VOICE, RATE, VOLUME, PITCH, SAVE_AUDIO)
- Step4: Start the server with `bun run start`
- Step5: Integrate with MCP-compatible clients like Cline or other AI tools
- Step6: Send text input through the `speech_text_aloud` tool to generate speech