Voiceroid Daemon Mcp is an MCP server that connects Claude Desktop and other Model Context Protocol clients to VOICEROID2 via the voiceroid_daemon service. Software developers, digital content creators, and Japanese language enthusiasts use it to trigger speech synthesis directly through conversational AI prompts. The server enables an AI agent to verify daemon network connectivity, convert standard Japanese text into phonetic kana representations, and generate spoken audio output with customized voice settings. Users can configure sound parameters such as volume, playback speed, pitch, and emphasis, allowing precise adjustment over how synthetic speech sounds. Operating across macOS, Windows, and Linux, the server plays speech audio locally through the host system using native media tools such as afplay, PowerShell SoundPlayer, or aplay. By bridging large language models to local VOICEROID2 installations, it facilitates real-time spoken responses, accessibility reading tools, and automated media production workflows without requiring manual clipboard copying or switching between multiple applications.
Category: Design, Media & Creative
Tags: audio, synthesis, text to speech, voiceroid
bash git clone https://github.com/mohemohe/voiceroid_daemon-mcp.git cd voiceroid_daemon-mcp npm install 3. Optionally create a .env file to set VOICEROID_DAEMON_URL and credentials if authentication is required. 4. Add the server to your Claude Desktop configuration file (claude_desktop_config.json): json { "mcpServers": { "voiceroid-daemon": { "command": "npx", "args": ["tsx", "/path/to/voiceroid_daemon-mcp/src/index.ts"], "env": { "VOICEROID_DAEMON_URL": "http://127.0.0.1:8080" } } } } 5. Restart Claude Desktop to activate the tools.Part of MCP Servers
Voiceroid Daemon Mcp exposes tools to test connections to a running voiceroid_daemon instance, convert Japanese text into phonetic kana readings, and synthesize speech audio. It also supports adjusting voice parameters like pitch, volume, speed, and emphasis, and plays the resulting audio using native OS media utilities.
Clone the GitHub repository, install dependencies using npm install, and ensure voiceroid_daemon and VOICEROID2 are running locally. Then, register the server in your Claude Desktop configuration file by pointing npx tsx to the index.ts file along with the daemon URL environment variable.
It is designed to work with Claude Desktop on macOS and Windows, as well as any other Model Context Protocol client capable of launching a local Node.js process over stdio.
Yes, Voiceroid Daemon Mcp is open-source software released under the MIT license. You can inspect its source code and contribute via its official GitHub repository.
On Linux, the server requires aplay, which is typically installed as part of the alsa-utils package. On macOS, it uses the built-in afplay tool, while Windows relies on PowerShell's Media.SoundPlayer.