mcp-tts-voicevox and rvc-mcp
These are complementary tools: VOICEVOX provides pre-trained voice synthesis for text-to-speech output, while RVC enables custom voice cloning and vocal separation for training personalized voice models that could feed into synthesis pipelines.
About mcp-tts-voicevox
kajidog/mcp-tts-voicevox
VOICEVOX MCP Server (MCP Apps対応)
This project helps anyone using an AI assistant like Claude or ChatGPT make their AI speak aloud and even have multi-character conversations. You provide the text you want spoken, and it outputs interactive audio players directly within your chat interface, letting you control playback, switch speakers, and fine-tune pronunciation on the fly. It's designed for anyone who wants to add a dynamic, audible dimension to their AI assistant interactions.
About rvc-mcp
ExpertVagabond/rvc-mcp
MCP server for RVC WebUI — voice training, inference, model management, vocal separation via Gradio API (12 tools)
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work