Espressif ESP32-S3-BOX-3B AIoT Kit w/ 2.4-Inch Touchscreen
The Espressif ESP32-S3-BOX-3B is a fully open-source AIoT evaluation kit built around the ESP32-S3 SoC, featuring a 2.4-inch capacitive touchscreen, dual microphones, and a speaker for developing edge AI and HMI applications with Wi-Fi, Bluetooth LE 5.0, and offline voice recognition.
Features
- Powered by the ESP32-S3 dual-core Xtensa LX7 processor (240 MHz) with AI acceleration, 16MB flash, and 8MB PSRAM for demanding edge computing tasks.
- Integrated 2.4-inch (320×240) SPI capacitive touchscreen and ES8311 audio codec with dual digital mics & speaker for rich human-machine interface (HMI) development.
- Comprehensive offline voice assistant framework supports far-field interaction, continuous recognition, wake-word interruption, and over 200 customizable command words.
- Out-of-the-box compatibility with ESP-IDF, Arduino, PlatformIO, and CircuitPython for rapid prototyping of AIoT, smart home, and industrial automation projects.
- Includes expansion dock with high-density PCIe connector and dual Pmod ports for hardware extensibility and peripheral integration.
Out of stock
The ESP32-S3-BOX-3B is a next-generation, production-ready AIoT development platform from Espressif. It integrates the feature-rich ESP32-S3 SoC, which provides dual-core 240 MHz processing, 2.4 GHz Wi-Fi 802.11b/g/n, and Bluetooth 5 LE with mesh support, all enhanced with vector and FFT computing acceleration for neural network and acoustic algorithms. The kit is designed as a complete voice-and-touch interactive panel, enabling developers to build sophisticated edge AI applications with local processing, eliminating cloud dependency for core voice commands.
Beyond its core compute and wireless connectivity, the board includes a suite of onboard peripherals: a 2.4-inch ILI9342C-driven LCD with 10-point capacitive touch, an ES7210 ADC for dual digital MEMS microphones, and an ES8311 audio codec paired with an NS4150 power amplifier for high-quality audio playback. This hardware ensemble, combined with Espressif’s ESP-SR (Speech Recognition) framework, facilitates advanced features like far-field voice pickup, offline wake-word detection, and customizable command recognition. The included dock provides a stable base and exposes expansion interfaces, including a PCIe connector and standard Pmod ports, for adding sensors, actuators, or communication modules.
Additional Information
| Weight | 0.343 kg |
|---|---|
| Dimensions | 18 × 11 × 8 cm |













