1.85″ 360×360 ESP32-S3 QSPI AI Development Kit

EchoEar plus 1.85 Inch 360×360 ESP32-S3 QSPI Interface Round Touch Display AI Development Kit with Dual Microphone Array for Voice Interaction and Edge AI Applications

EchoEar plus is a compact AI development kit designed for voice-enabled embedded systems. Powered by the ESP32-S3, it integrates a 1.85 inch 360×360 round IPS touchscreen via QSPI interface, enabling responsive UI and efficient data communication.

Equipped with a dual microphone array, the module supports offline voice wake-up and sound source localization, making it ideal for always-on voice interaction devices. With support for advanced AI ecosystems such as OpenAI, Gemini, and Xiaozhi AI, it enables full-duplex voice communication, multimodal interaction, and intelligent agent control.

Designed for rapid prototyping and scalable deployment, EchoEar plus is suitable for smart speakers, AI toys, and smart control panels. Its compact design, integrated audio system, and battery support make it a complete edge AI solution for developers building next-generation human-machine interfaces.

• Product Features

  AI Processing Core – ESP32-S3 provides powerful AI computing capabilities optimized for voice interaction and edge deployment;
  Round Touch Display – 1.85 inch 360×360 IPS QSPI interface delivers smooth UI and compact visual interaction experience;
  Voice Interaction – Dual microphone array supports offline voice wakeup sound source localization and noise filtering capabilities;
  Multimodal AI – Supports integration with OpenAI Gemini and Xiaozhi AI for advanced intelligent agent interaction features;
  Full Duplex Audio – Enables real time bidirectional voice communication for natural and seamless user interaction experience;
  Compact Integration – Integrated display microphone speaker and battery for complete AI device prototyping platform;
  Edge AI Ready – Designed for local processing reducing latency and improving privacy preservation in AI applications;
  Developer Friendly – Supports ESP-IDF and Arduino for rapid development and flexible application customization;
  Application Versatility – Ideal for smart speakers AI toys central control systems and interactive IoT devices.

• Application Scenarios

  Smart speakers with AI voice interaction and display interface
  Interactive toys powered by voice recognition and AI responses
  Smart home hubs with multimodal control and voice assistant
  Wearable AI devices with compact display and voice input
  Edge AI terminals for voice-based automation and control
  Educational AI kits for learning voice and embedded development

• Competitive Advantages

  ESP32-S3 powered AI kit with strong edge computing capability
  Dual microphone array enabling accurate voice recognition and localization
  Supports offline wake-up and full-duplex voice interaction
  Compatible with OpenAI, Gemini, and Xiaozhi AI ecosystems
  Integrated display, speaker, and battery for standalone operation
  Compact design with enhanced aesthetics and improved user experience

• Specifications

  Model	EchoEar Plus
  OS	RTOS
  CPU	ESP32-S3 240Mhz
  Ram	8MB
  Flash	16MB
  Wireless	2.4GHz Wi-Fi, BLE 5, BLE Mesh
  Interface	USB
  Display Type	IPS TFT
  Screen Size	1.85 Inch
  Resolution	360*360
  Brightness	300 cd/㎡
  Touch Screen	Capacitive
  Outline Demension	TBD
  Operating Voltage	5V
  Operating Current	200mA
  Operating Temp	-20~70℃