EchoKit

EchoKit is the full-stack, open-source voice AI agent toolkit: Rust-powered orchestration from embedded ESP32 firmware to LLM inference.

EchoKit delivers an end-to-end voice AI platform, providing the complete stack for builders and students. The system orchestrates multiple AI models—VAD, ASR, LLM, and TTS—via a high-performance Rust server and a WebSocket interface. It includes open-source firmware for ESP32-S3 hardware, allowing for private, self-hosted deployment and full customization. Key features include GPT-SoVITS voice cloning and Model Context Protocol (MCP) support for extensible tool integration, such as the 'US civics test prep' agent example. This design ensures flexibility: use hosted services or run everything locally for complete control.

https://echokit.dev