End-to-end documentation to set up your own local & fully private LLM server on Debian. Equipped with chat, web search, RAG, model management, MCP servers, image generation, and TTS.

Text-to-speech CLI tool that uses the Kokoro model for inference. Runs extremely fast locally with or without a GPU. Render smooth speech faster than real-time on most machines. Use Kokoro from CLI or the FastAPI webserver via HTTP requests or directly in the browser. Supports audio playback from the CLI, web interface, or download in many formats.