mcp-tts-voicevox and voicepeak-mcp
These are competitors—both provide MCP server interfaces for Japanese text-to-speech synthesis, with VOICEVOX being open-source and VOICEPEAK being a commercial alternative, allowing users to choose based on cost and feature preferences.
About mcp-tts-voicevox
kajidog/mcp-tts-voicevox
VOICEVOX MCP Server (MCP Apps対応)
Implements MCP Apps integration to render an interactive audio player directly in Claude Desktop and ChatGPT, enabling client-side playback with track editing, speaker switching, and WAV export—eliminating server audio device requirements. Supports multi-speaker dialogue with segment-level control over speed, volume, intonation, and accent phrases, plus a user dictionary manager. Connects to a local VOICEVOX Engine instance via stdio transport for Claude Desktop or HTTP for remote access.
About voicepeak-mcp
k2wanko/voicepeak-mcp
MCP server for VOICEPEAK text-to-speech synthesis
Implements the Model Context Protocol (MCP) to expose VOICEPEAK's synthesis capabilities—including voice generation with configurable narrators, emotions, speed, and pitch parameters—through a set of tools callable by Claude Desktop. Provides platform-specific features like pronunciation dictionary management on macOS/Linux, while Windows users leverage VOICEPEAK's native dictionary interface. Installs via npx/bunx and integrates directly into Claude Desktop configuration.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work