Simple Voicevox
Offers VOICEVOX text-to-speech functionality through the Model Context Protocol.
概要
This project provides a straightforward server implementation that allows the VOICEVOX speech synthesis engine to be utilized as an MCP (Model Context Protocol) tool. It enables MCP clients, such as Claude Code, to easily access text-to-speech capabilities, converting text inputs into natural-sounding Japanese audio. Users can specify the text to be spoken, choose from various speaker IDs available in VOICEVOX, and adjust the speech speed, making it a versatile tool for integrating voice output into automated workflows and applications.
主な機能
- VOICEVOX text-to-speech integration via MCP
- Configurable speech parameters (text, speaker ID, speed scale)
- Cross-platform audio playback support (macOS, Linux, Windows)
- Easy installation via npm package or source
- Direct access to VOICEVOX engine's speaker ID information
- 13 GitHub stars
ユースケース
- Integrating voice synthesis capabilities into MCP client applications like Claude Code
- Automating voice narration for various content generation or interactive systems
- Enabling AI agents or automated systems to generate spoken responses or information