🦀 Full-stack AI agent powered by Rust

Open Source voice AI agent toolkit for students and builders

Build, customize and host your own voice AI agent

EchoKit is a fun voice AI agent that can chat with you out of the box. But more importantly, it is also a complete toolkit that enables YOU (and your kids / students) to build cutting edge AI agent systems.

EchoKit in Action

See how people are using EchoKit to build amazing voice AI experiences

What is EchoKit?

AI learning with EchoKit is fun! Voice chat with interesting characters and get first-hand experience with real-time AI. You can also customize every aspect of the hardware and software stack, and run the whole AI agent system in your own home!

EchoKit DIY

Get the hardware components (assemble like Lego), AI agent server software, docs and learning materials in a single package.

$49 - Details

EchoKit Cube

The EchoKit Cube is a pre-assembled voice AI device. You will also get the complete AI agent server software, docs and learning materials.

$49 - Details

Fun voice

Not ready for the $49 device? Chat with fun AI characters for FREE from your browser! Experiment with and learn voice AI.

Playground

Teachers

If you are interested in building an AI lab for your school, you can purchase EchoKit and related course materials in bulk!

Get in touch

Why you'll love the EchoKit

Cheaper, better, and private realtime voice AI agent in your own house.

🎭Fun voice AI characters

Speak with entertaining and engaging AI personalities right out of the box. No more boring, robotic responses.

🆓Use private AI models for free

Setup and run your own AI models on your computers without any monthly fees or usage limits. Complete freedom.

📚Private and proprietary knowledge

Ground your voice AI agent with your own documents, notes, and knowledge. Create a digital twin!

🗣️Speak in any voice

Make the AI agent speak in anyone's voice and style. Bring your favorite people from distance or past into your own house!

🎯Voice commands & actions

Control your environment and send commands across the Internet through natural voice interactions.

🎓Learn by building

Build an end-to-end AI project and understand every component. Future-proof your job skills.

Everything you need in one package

Complete full-stack open-source solution from hardware firmware to AI agents to MCP to AI models

🏗️Full stack open-source

Complete solution from embedded firmware to AI inference server. Run everything privately on your own hardware or use our hosted service - you decide.

🧠Works with any AI model

Compatible with all major LLMs, voice-to-text, and TTS models. Choose your preferred AI models or switch between them seamlessly.

🎵Voice Cloning

Create personalized voice experiences with advanced voice cloning technology. Make your AI sound exactly how you want.

🔍Agentic Search

Ground your LLMs with personal knowledge bases for accurate and updated responses that are aligned with your values.

🔧MCP Support

Extensible action system with MCP-based tool calls. Enhance your AI's abilities with custom tools and integrations.

☁️Flexible deployment

Use hosted services for convenience or run your own server for complete control. Unlike Big Tech, we give you the choice.

🦀Rust Performance

Built entirely in Rust for maximum safety, performance, and reliability. Memory-safe code with blazing-fast execution.

🧑‍🏫Designed for learning

Full documentation and tutorials that teach you how to build and customize your own AI system on your own computers. You will learn AI from inside out.

Built on Open Source Foundation

Community-driven development. Learn how it works, fork it for your own needs, and contribute back!

🚀EchoKit Server

Rust AI

WebSocket-based AI agent server with VAD, voice recognition and synthesis, LLM integration, and MCP support. The coordinator of your voice agent system.

Source code on GitHub

📦EchoKit Device

Rust, ESP32, RISC-V Embedded

Hardware firmware written in embedded Rust for the EchoKit device. Handles audio I/O, buttons, display, WiFi, Bluetooth and device management.

Source code on GitHub

🎙️Silero VAD Server

Rust, VAD, Silero ML

Voice Activity Detection service using SOTA VAD models. Efficiently detects when the user is speaking for optimal interaction.

Source code on GitHub

🗣️GSV TTS

Rust, GPT-SoVITS, torch TTS

High-quality and streaming Text-to-Speech service with voice cloning capabilities. Generate natural-sounding speech in any voice you want.

Source code on GitHub

Get started in 3 simple steps

From unboxing to chatting with your AI in minutes

1

Power Up & Connect

Simply power up your EchoKit device and connect it to your WiFi network. No complex setup required.

2

Start Chatting!

Begin talking to your AI assistant immediately. It works out of the box with powerful default models.

3

Customize Your AI

Set up your own AI server, add custom knowledge, clone voices, and build advanced capabilities.

Your trusted partner

EchoKit is used by students and teachers in colleges, high schools and middle schools all over the world.

Texas State University
Tsinghua University
Wah Yan One Family Foundation
Rust Global
GOSIM
Liberal Arts and Science Academy of Austin
RustChinaConf