Pronunciation & Voice Coach MCP Server

An MCP (Model Context Protocol) server that lets you talk to your MCP assistant by voice while getting English pronunciation, grammar, and fluency feedback in the same turn. Use it for casual voice chat with light coaching, or switch to drill mode when you want to practice a specific sentence. Its 15 documented tools cover voice, capture, practice.

People connecting media tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-05-24 · ★ 2 · #119 OF 155 MAINTAINED MEDIA · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Pronunciation & Voice Coach

before you install - you'll need

Set MCP_PRONUNCIATION_MODEL, HF_HUB_CACHE, MCP_PRONUNCIATION_PRELOAD, MCP_PRONUNCIATION_AUDIO_RETENTION, MCP_PRONUNCIATION_INPUT_DEVICE, MCP_PRONUNCIATION_VAD_SENSITIVITY, MCP_PRONUNCIATION_SILENCE_DURATION before connecting.

Claude Code

claude mcp add juhongpark-mcp-server-pronunciation -- uvx mcp-server-pronunciation

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "juhongpark-mcp-server-pronunciation": {
      "command": "uvx",
      "args": [
        "mcp-server-pronunciation"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package mcp-server-pronunciation - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.JuhongPark is GitHub-verified and matches the repo owner

03 · What Pronunciation & Voice Coach can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can open the MCP Apps voice panel when the client supports embedded UI, start recording in the background and return a session id immediately, check whether a background capture is recording, analyzing, done, cancelled, or failed, and read the most recent background voice capture result.

Capability map

Tools grouped from the project's README - what Pronunciation & Voice Coach lets an agent do.

Converse

1 tool - e.g. Primary. Record + transcribe + quick feedback + assistant guidance for natural voice-chat-with-coaching.

converse

Practice

1 tool - e.g. Drill mode: record user reading a specific reference sentence, return detailed assessment.

practice

Quick

1 tool - e.g. Pick a random sentence (by phoneme focus + difficulty) and drill it.

quick_practice

Retry

1 tool - e.g. Re-record the last sentence and compare the new attempt against the previous one.

retry

Open

1 tool - e.g. Open the MCP Apps voice panel when the client supports embedded UI.

open_voice_panel

Analyze

1 tool - e.g. Analyze WAV audio uploaded by the voice panel and store it as the latest voice capture.

analyze_uploaded_audio

run & execute

1 tool - e.g. Start recording in the background and return a session id immediately.

start_voice_capture

Voice

1 tool - e.g. Check whether a background capture is recording, analyzing, done, cancelled, or failed.

voice_capture_status

Latest releases

v0.3.0 · 2026-05-03

v0.3.0 Stable Release · This is the first stable package release for mcp-server-pronunciation. · Pronunciation feedback remains a coaching signal, not a standardized-test, · clinical, employment, or high-stakes…

04 · Who maintains Pronunciation & Voice Coach

Pronunciation & Voice Coach is maintained by juhongpark. It's the only MCP server we track from this author; the repo dates to Apr 2026.

05 · Facts

repository: github.com/juhongpark/mcp-server-pronunciation
category: media - ranked #119 of 155 actively-maintained media servers as of 2026-08-25.
registry: io.github.JuhongPark/pronunciation (active, first published 2026-05-03 · 3 versions)
packages: pypi:mcp-server-pronunciation

06 · Pronunciation & Voice Coach FAQ

Is Pronunciation & Voice Coach still maintained?

Yes - as of 2026-08-25, its last commit was 2026-05-24. We re-verify nightly.

What can Pronunciation & Voice Coach do?

How do I install Pronunciation & Voice Coach?

Run `uvx mcp-server-pronunciation`. The README documents 7 environment variables (MCP_PRONUNCIATION_MODEL, HF_HUB_CACHE, MCP_PRONUNCIATION_PRELOAD…) to set first. Set MCP_PRONUNCIATION_MODEL, HF_HUB_CACHE, MCP_PRONUNCIATION_PRELOAD, MCP_PRONUNCIATION_AUDIO_RETENTION, MCP_PRONUNCIATION_INPUT_DEVICE, MCP_PRONUNCIATION_VAD_SENSITIVITY, MCP_PRONUNCIATION_SILENCE_DURATION before connecting. You can also paste the ready-made client config above.

Does Pronunciation & Voice Coach run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Pronunciation & Voice Coach

Alternatives to Pronunciation & Voice Coach

Maintained media servers if Pronunciation & Voice Coach isn't the fit.

More media MCP servers · Gongio MCP · Audio Analyzer · Apple Voice Memo MCP · Whisper MCP · Pdf MCP

More Python MCP servers · Wikimoth · DrissionPage MCP · Juniper Routing Director MCP Server · ChemDraw MCP (unofficial) · Entroly · see all