Vv Mcp

Vv Mcp is an MCP server that provides text-to-speech synthesis using a local VOICEVOX engine. It connects Model Context Protocol clients like Claude Desktop and Claude Code directly to a running VOICEVOX instance on the user's computer. The server is designed for developers, Japanese language learners, and accessibility users who want Claude to vocalize answers, status notifications, and reading tasks using natural Japanese character voices. Vv Mcp enables tools to synthesize speech asynchronously, query available character voices, track audio playback queues, and assign distinct speaker identities across separate Claude sessions. It also coordinates between concurrent Claude processes to prevent multiple instances from speaking over each other with the same voice by automatically picking available speaker IDs. It runs cross-platform across macOS, Linux, and Windows, leveraging system audio players like afplay, PipeWire, PulseAudio, or PowerShell.

Category: Other & General Purpose

Tags: boilerplate, starter, template

Visit Vv Mcp

How to install and configure Vv Mcp

1. Ensure Node.js 18 or higher is installed and a local VOICEVOX instance is running at http://localhost:50021. 2. Install the server globally via npm: npm install -g @arrow2nd/vv-mcp or run directly using npx. 3. Open your Claude Desktop configuration file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, ~/.config/Claude/claude_desktop_config.json on Linux, or %APPDATA%\Claude\claude_desktop_config.json on Windows). 4. Add vv-mcp to the mcpServers object: json { "mcpServers": { "vv-mcp": { "command": "npx", "args": ["-y", "@arrow2nd/vv-mcp"], "env": { "VOICEVOX_URL": "http://localhost:50021", "DEFAULT_VOICE_ID": "47", "DEFAULT_SPEED": "1.0" } } } } 5. Restart Claude Desktop or Claude Code to access the voice tools.

What you can do with Vv Mcp

• Reading Claude responses aloud using Japanese speech synthesis engines like VOICEVOX during coding or reading workflows. * Querying available character voice models and styles to dynamically switch narrators during interactive AI conversations. * Vocalizing build completion or background task notifications automatically through Claude Code terminal sessions. * Managing playback queues to verify pending audio clips or clear stuck syntheses during heavy output operations. * Allocating distinct character voices automatically to separate concurrent Claude sessions to prevent vocal identity collisions.

Key facts

• https://github.com/arrow2nd/vv-mcp
• Other & General Purpose
• boilerplate, starter, template

Part of MCP Servers

What is Vv Mcp?

Vv Mcp is a Model Context Protocol server that bridges AI clients such as Claude Desktop and Claude Code with a local VOICEVOX speech synthesis engine to read text aloud.

Which MCP clients work with Vv Mcp?

It is designed to work with Claude Desktop and Claude Code, running across macOS, Linux, and Windows systems with standard audio utilities configured.

What are the prerequisites for running Vv Mcp?

You need Node.js 18 or higher and an active local VOICEVOX instance running at the specified URL. Audio playback uses afplay on macOS, pw-play or paplay on Linux, and PowerShell on Windows.

What can Vv Mcp do?

It allows AI assistants to convert text into speech, retrieve lists of available voices, manage audio queues, and assign dedicated voices to independent Claude sessions without voice overlap.

Is Vv Mcp open source?

Yes, Vv Mcp is open source and licensed under the MIT License on GitHub.