Pronunciation & Voice Coach

Overview

Pronunciation & Voice Coach is a Model Context Protocol (MCP) server: Local MCP voice coach with English pronunciation, grammar, and fluency feedback. In practice that means any MCP-compatible AI assistant can call Pronunciation & Voice Coach's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package mcp-server-pronunciation (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.3.0, published under the MIT license, with source at JuhongPark/mcp-server-pronunciation on GitHub.

Pronunciation & Voice Coach is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Pronunciation & Voice Coach for JuhongPark, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "pronunciation_voice_coach": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation"
      ]
    }
  }
}