Overview
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
saycommand - 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.
