say-mcp-server logo

say-mcp-server

by bmorphism

An MCP server that provides text-to-speech functionality using macOS's built-in `say` command. It allows for extensive customization of voice, rate, and other speech parameters.

View on GitHub

Last updated: N/A

What is say-mcp-server?

say-mcp-server is an MCP (Meta-Control Protocol) server that leverages the macOS say command to provide text-to-speech capabilities. It allows other applications and services to programmatically generate speech using a variety of voices and customizable parameters.

How to use say-mcp-server?

To use the server, you need to install it using npm install say-mcp-server and configure your MCP settings file to point to the server's executable. You can then use the speak tool with various arguments to control the text, voice, rate, and other aspects of the speech. The list_voices tool can be used to discover available voices on the system. The server can be integrated with other MCP servers to read search results, YouTube transcripts, or Apple Notes.

Key features of say-mcp-server

  • Text-to-speech using macOS's say command

  • Voice selection

  • Speaking rate control

  • Volume modulation

  • Emphasis and pitch adjustment

  • Background speech support

  • Integration with other MCP servers

Use cases of say-mcp-server

  • Reading search results aloud

  • Narrating YouTube video transcripts

  • Listening to Apple Notes

  • Providing audio feedback in applications

  • Creating accessible interfaces for visually impaired users

FAQ from say-mcp-server

What operating systems are supported?

macOS is required, as the server relies on the built-in say command.

What versions of Node.js are supported?

Node.js version 14.0.0 or higher is required.

How do I find the path to the server's executable?

After installing the package, the path will be in the node_modules directory. The configuration example shows /path/to/say-mcp-server/build/index.js as an example.

How do I change the speaking voice?

Use the voice parameter in the speak tool and specify the desired voice name. Use the list_voices tool to see available voices.

Can I adjust the speaking rate?

Yes, use the rate parameter in the speak tool to control the speaking rate in words per minute. The range is 1-500, with a default of 175.