# EchoKit Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/echokit
> Markdown URL: https://aitinkerers.org/technologies/echokit.md
> Technology record last updated: 2026-03-07T13:44:32Z
> Generated: 2026-09-20T21:48:44Z

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.

- Official technology site: https://echokit.dev
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Fully Customizable Voice AI with multi-modal open source LLMs and esp32 (clone your own voice too with simple tools)](https://tokyo.aitinkerers.org/talks/rsvp__c55AmItHW0)

A step‑by‑step guide to building a fully local voice AI using fully open source EchoKit, swapping ASR/TTS models, integrating open‑source LLMs, and deploying on ESP‑32. Walkthrough of how I run the open source EchoKit (https://github.com/second-state/echokit_server) voice AI stack to connect any LLM with speech-to-text, text-to-speech, and custom prompts—all running locally or in the cloud. I’ll start with a minimal working setup, then show how to swap in different ASR/TTS models (Whisper, VITS), integrate LLMs (GPT5, Kimi K2, DeepSeek), and add domain-specific knowledge bases. We’ll explore the full data flow, from audio capture to streamed responses, plus edge deployment with the open source runtime WasmEdge for low-latency inference.

- Event context: AI Tinkerers Tokyo Kickoff – October 10, 2025 — 2025-10-10 — Tokyo
- Public talk page: https://tokyo.aitinkerers.org/talks/rsvp__c55AmItHW0

## Related Technologies

- [ESP32-S3](https://aitinkerers.org/technologies/esp32-s3) ([Markdown](https://aitinkerers.org/technologies/esp32-s3.md)) — 2 public demos
- [esp-idf-hal](https://aitinkerers.org/technologies/esp-idf-hal) ([Markdown](https://aitinkerers.org/technologies/esp-idf-hal.md)) — 1 public demo
- [LlamaEdge](https://aitinkerers.org/technologies/llamaedge) ([Markdown](https://aitinkerers.org/technologies/llamaedge.md)) — 1 public demo