MCP TTS Say

What is MCP TTS Say?

MCP TTS Say is a tool that converts text to speech using OpenAI's TTS SDK and plays the audio locally. It integrates with MCP servers to provide a simple text-to-speech utility for developers.

How to use MCP TTS Say?

Clone the repository, install dependencies with npm install, and set your OPENAI_API_KEY in a .env file. Run npm run dev to start in development mode, or use npm run inspect to debug with MCP Inspector.

Key features of MCP TTS Say

• Text-to-speech using OpenAI's TTS SDK
• Local audio playback
• MCP server integration
• Development mode with TypeScript

Use cases of MCP TTS Say

• Converting AI-generated text responses to spoken audio in MCP applications
• Adding voice output to local development tools
• Prototyping voice-enabled features with minimal setup

FAQ from MCP TTS Say

What are the requirements?

Node.js v18 or higher, an OpenAI API key, and a local environment capable of audio playback.

How do I set up the environment variables?

Create a .env file in the project root and add OPENAI_API_KEY=your_api_key_here.

How do I run MCP TTS Say?

Use npm run dev for development mode, npm test for testing, and npm run lint for linting.

How do I debug MCP TTS Say?

Use npm run inspect to launch MCP Inspector for debugging.

Where can I find more detailed specifications?

See spec.md for detailed specifications and todo.md for task progress.