Daisys AI Text-to-Speech

Daisys MCP Server provides a bridge to the Daisys AI text-to-speech API, enabling AI assistants to generate high-quality voice audio from text. Developed by Jasper Jumelet, it supports both HTTP and WebSocket protocols for audio generation, with the WebSocket implementation offering real-time streaming capabilities. The server includes tools for voice management (creating, listing, and removing voices), model discovery, and audio file handling with configurable output paths. Built with Python and the Daisys SDK, it features comprehensive authentication handling through environment variables and supports various audio formats. This implementation is particularly valuable for applications requiring natural-sounding voice synthesis with control over voice characteristics like gender, pace, pitch, and expression.