say-mcp-server

What is say-mcp-server?

say-mcp-server is an MCP (Model Context Protocol) server that provides text-to-speech functionality using macOS's built-in say command. It allows AI assistants and other MCP clients to speak text aloud with extensive customization options.

How to use say-mcp-server?

Install via npm (npm install say-mcp-server) and add the server to your MCP settings configuration. Use the speak tool to convert text to speech, and the list_voices tool to see all available macOS voices.

Key features of say-mcp-server

• Text-to-speech via macOS built-in say command
• Customizable voice, rate, and volume
• Support for voice modulation, pitch, and emphasis
• Background speech mode for concurrent interactions
• List all available system voices

Use cases of say-mcp-server

• Read search results aloud from other MCP tools
• Narrate YouTube video transcripts
• Speak Apple Notes content
• Provide audio feedback in automated workflows

FAQ from say-mcp-server

What does say-mcp-server do?

It provides text-to-speech capabilities on macOS by calling the system's say command through an MCP interface.

What are the system requirements?

macOS (the server uses the built-in say command) and Node.js version 14.0.0 or higher.

How do I configure say-mcp-server?

Add it to your MCP settings file with the command node and the path to the server's build/index.js.

Can I use background speech?

Yes, set the background parameter to true to run speech in the background and continue other MCP interactions.

How do I list available voices?

Use the list_voices tool—it returns all text-to-speech voices installed on your system.