Mcp Speak

What is Mcp Speak?

Mcp Speak is a Model Context Protocol (MCP) server that provides text-to-speech capabilities using the native MacOS say command. It allows AI agents such as Claude Desktop or Gemini CLI to speak to users directly.

How to use Mcp Speak?

Install the required Python dependencies with pip install -r requirements.txt, then configure the server in your client’s settings (e.g., ~/.gemini/settings.json for Gemini CLI, ~/Library/Application Support/Claude/claude_desktop_config.json for Claude Desktop, or use claude mcp add for Claude CLI). The server exposes two tools: speak (blocking, waits for speech to finish) and speak_non_blocking (returns immediately).

Key features of Mcp Speak

• Sequential speech queue prevents overlapping audio.
• Supports both blocking and non‑blocking speech modes.
• Uses native MacOS say command for low‑latency output.
• Integrates easily with Claude Desktop, Gemini CLI, and Claude Code.

Use cases of Mcp Speak

• AI agents announcing status updates or milestones during tasks.
• Voice‑based clarifications when user input is needed.
• Reading out answers or summaries without needing a screen.
• Creating interactive, voice‑first experiences with personalized agent personas.

FAQ from Mcp Speak

Is Mcp Speak cross‑platform?

No, it is strictly for MacOS systems. It relies on the native say command.

What dependencies are required?

MacOS and Python 3 must be installed. Then run pip install -r requirements.txt to install the required Python packages.

How do I configure Mcp Speak for Claude Desktop?

Edit the file at ~/Library/Application Support/Claude/claude_desktop_config.json and add the server under mcpServers with the command python3 and the absolute path to speak_server.py.

How do I configure Mcp Speak for Gemini CLI?

Edit ~/.gemini/settings.json and add the server under mcpServers with the command python3 and the absolute path to speak_server.py.

How can I improve voice quality?

Open System Settings → Accessibility → Spoken Content, manage voices, and download a Siri or Premium voice. Set it as the default System Voice for more natural speech.