Welcome
Original Voice Soundboard is a production-ready text-to-speech library and MCP server for AI agents and developers. Install it with pip, point it at a model, and start generating speech in seconds.
What you get
Section titled “What you get”- 54+ voices with British, American, and international accents
- 19 emotions from happy to nostalgic to determined
- MCP server with 40+ tools so AI agents like Claude can speak out loud
- Three TTS engines — Kokoro (default), Chatterbox (paralinguistic tags), and F5-TTS (voice cloning)
- Natural language style control — describe how you want it to sound in plain English
- Runs locally — no cloud, no telemetry, no API keys
Handbook contents
Section titled “Handbook contents”- Getting started — install, download models, generate your first audio file
- Voices and emotions — 54+ voices, 19 emotions, presets, and natural language style
- MCP server — give your AI agent a voice with 40+ MCP tools
- Engines — Kokoro, Chatterbox, F5-TTS, and advanced topics