ESP32-S3-BOX-3 AIoT Development Kit User Guide
Espressif
Overview
The ESP32-S3-BOX-3 is a powerful, open-source AIoT development kit based on the ESP32-S3 SoC. It combines innovation with artistry, offering a compact and beautiful enclosure with rich assemblies. This next-generation tool empowers developers to easily customize and expand its functionality using Espressif's trusted software solutions like ESP-BOX, ESP-SR, ESP-Rainmaker, and ESP-Matter. It strikes a balance between form and function, ideal for prototyping new projects or building complex IoT systems.
The ESP32-S3-BOX-3 comes with pre-built firmware supporting offline voice wake-up and speech recognition in both Chinese and English. The ESP-BOX mobile app facilitates reconfigurable AI voice interaction, allowing users to create personalized commands for controlling smart devices. The firmware also includes various sensor demos and enables IR learning, transforming the device into a controller for in-house air conditioners.
Target Group
This product is designed for individuals and organizations involved in making, prototyping, and development. It caters to a wide range of users, including hobbyists, makers, engineers, educators, and professionals seeking versatile and expandable solutions for their projects.
Target Application
- Smart Home
- Smart Agriculture
- Smart City
- Energy Management
- IoT Prototyping and Education
- Industrial Internet of Things
- Smart Retail
Key Features
- An out-of-the-box entry-level edge AI + HMI application development board.
- FreeRTOS-based four-in-one voice interaction panel: offline voice recognition, network communication, screen display, peripheral control.
- Supports far-field voice interaction with 2 microphones.
- Offline voice wake-up and commands recognition with a high wake-up rate.
- Allows continuous recognition, wake-up interrupt, and over 200 customizable command words.
- Flexible and versatile home automation solutions: Matter, Home Assistant, ESP-RainMaker.
- Visual drag-and-drop GUI development: LVGL SquareLine Studio, Embedded Wizard, etc.
- Rich development framework: ESP-IDF, Arduino, PlatformIO, Circuit Python, and more.
Hardware Introduction
Contents of the Kit (ESP32-S3-BOX-3 Kit)
- ESP32-S3-BOX-3: Main unit
- ESP32-S3-BOX-3-DOCK: Stand for the main unit
- ESP32-S3-BOX-3-SENSOR: Accessory for showcasing sensor applications
- ESP32-S3-BOX-3-BRACKET: Adapter for mounting the main unit to other devices
- ESP32-S3-BOX-3-BREAD: Adapter for easy connection to a standard breadboard
- A USB-C Power Cable
- An RGB LED module and Dupont wires for testing
Contents of the Kit (ESP32-S3-BOX-3B Kit)
- ESP32-S3-BOX-3: Main unit
- ESP32-S3-BOX-3-DOCK: Stand for the main unit
- A USB-C Power Cable
- An RGB LED module and Dupont wires for testing
Variant Description
The ESP32-S3-BOX-3 offers two versions: ESP32-S3-BOX-3 (standard edition with four blue accessories) and ESP32-S3-BOX-3B (fewer accessories for starters).
ESP32-S3-BOX-3
The ESP32-S3-BOX-3 is powered by the ESP32-S3-WROOM-1 module, offering Wi-Fi + Bluetooth 5 (LE) wireless capability and AI acceleration. It features 512 KB SRAM, 16 MB Quad flash, and 16 MB Octal PSRAM. The device includes a 2.4-inch 320 x 240 SPI touch screen, two digital microphones, a speaker, a 3-axis Gyroscope, a 3-axis Accelerometer, a Type-C port for power and debugging, a high-density PCIe connector for hardware extensibility, and three functional buttons.
ESP32-S3-BOX-3-DOCK
The ESP32-S3-BOX-3-DOCK serves as a stand for the ESP32-S3-BOX-3, offering expandability through two Pmod™ compatible headers. These headers provide 16 programmable GPIOs with 3.3 V power output. It includes one USB Type-A port for connecting USB devices (like cameras or USB disks) and one USB Type-C port for 5 V power input only.
ESP32-S3-BOX-3-SENSOR
The ESP32-S3-BOX-3-SENSOR is a versatile accessory integrating a Temp&Hum Sensor, IR Emitter and Receiver, Radar Sensor, an 18650 Rechargeable Battery slot, and a MicroSD Card slot (up to 32 GB). It enables users to create sensor networks and applications, monitor human presence, and use IR learning for controlling devices like air conditioners, fans, and TVs.
ESP32-S3-BOX-3-BRACKET
The ESP32-S3-BOX-3-BRACKET allows the ESP32-S3-BOX-3 to be mounted to other devices, enabling the transformation of non-smart devices into smart ones. Installation is straightforward with two mounting holes and a slot. Its two Pmod™ compatible headers facilitate integration of wireless connectivity, voice control, and screen control capabilities.
ESP32-S3-BOX-3-BREAD
The ESP32-S3-BOX-3-BREAD is an adapter for easy connection of the ESP32-S3-BOX-3 to a standard breadboard. It features a high-density PCIe connector and two rows of 2.54 mm pitch pins, exposing the ESP32-S3's 16 programmable GPIOs.
Getting Started
Power on Your Device
- Power on your device using the USB-C cable.
- Once powered on, the screen will display the Espressif logo boot animation.
Let's Play Around!
The initial pages of the quick guide provide an overview of the buttons' functions. Press 'Next' to proceed.
Button Functions:
- Touch to return
- Function Button: Customized by user
- Reset Button: Press to reset the device
Steps for Voice Assistant
- Say "Hi E. S. P." to wake up the device.
- Wait for "Hi ESP" to show on the screen.
- Say a command, like "turn on the light".
Default Command Words:
- "Turn on the light", "Switch off the light"
- "Turn Red", "Turn Green", "Turn Blue"
- "Sing a song", "Next Song"
- "Pause Playing"
The menu consists of six options: Sensor Monitor, Device Control, Network, Media Player, Help, and About Us. Navigate between options by swiping left or right. For example, access 'Device Control' and tap 'Light' to toggle the light on or off. You can then return to the menu and enter 'Media Player' to play music or adjust system volume.
Media Player
Press the mute button on the top of the device to disable voice wake-up and speech recognition. Press again to enable them.
Tap the red circle below the screen to go back to the previous page. This red circle is a customizable touch region for extra capabilities.
Sensor Monitor
This feature requires the ESP32-S3-BOX-3 to be mounted to the ESP32-S3-BOX-3-SENSOR dock. The ESP32-S3-BOX-3-SENSOR integrates a Temp&Hum Sensor, IR Emitter and Receiver, and a Radar Sensor. It allows for creating sensor networks and applications, monitoring human presence via a 2.4 GHz radar, and performing IR learning for controlling devices like air conditioners.
Radar Monitoring:
Enter the Sensor Monitor screen and tap the ON/OFF button to enable/disable radar monitoring. When enabled, a red body icon indicates detection; it turns gray if no person is detected within 2 minutes.
IR Learning
This module learns the ON/OFF function of a remote controller. Follow the on-screen instructions to learn the ON/OFF command four times. Successful learning allows control of the device.
To test, point the ESP32-S3-BOX-3-SENSOR at your air conditioner. If the ON/OFF logic is reversed, use the 'Reversal' button. Use 'Relearn' to clear history and start again.
Tips:
- The Sensor Monitor function is operational only when the ESP32-S3-BOX-3 is mounted to the ESP32-S3-BOX-3-SENSOR dock.
- Avoid hot-plugging the ESP32-S3-BOX-3-DOCK and switching to the ESP32-S3-BOX-3-SENSOR to prevent recognition issues. Power cycle the sensor to resolve.
- The effective control range for IR learning is between 1 to 1.5 meters.
Offline Voice Assistant
Connecting the RGB LED Module
Connect the RGB LED module to your device using Dupont wires, linking the R, G, B, and GND pins to the female header connector on the ESP32-S3-BOX-3-DOCK's Pmod™ interface. Refer to the pin definitions table.
Using Voice Commands
- Say "Hi E. S. P." (pronounced in alphabet) at any screen to wake up the device. The screen will display the wake word. If not displayed, try again.
- Utter a command within 6 seconds after the beep (e.g., "Turn on the light"). The command will show on screen, and the LED will turn on. You will hear "OK". If no commands are given within 6 seconds, the voice control screen exits.
You can use voice commands to enjoy music. Say "Sing a song" to launch the music player. Commands are available to pause or skip songs.
Tips:
- If the LED light does not turn on, check module pin insertion.
- If the BOX does not recognize a command within the timeframe, a "Timeout" message appears, and the screen exits.
Default Commands: turn on the light, turn off the light, turn red, turn green, turn blue, sing a song, next song, pause playing.
Continuous Speech Recognition
The device supports continuous speech recognition after waking up, enhancing the interactive experience.
How to use:
- Say "Hi, E. S. P" to wake up the device.
- Speak your command. Upon recognition, you will hear "OK", and the device remains ready for more commands.
- If no command is identified, the device waits. If no commands are given within 6 seconds, the voice control screen exits, and you need to wake it up again.
Attention:
- If commands are repeatedly unrecognized, allow the device to time out and wake it up again.
- Do not move the device after saying the wake-up word to ensure proper recognition.
- Voice commands of 3-5 words are recommended for optimal results.
- Commands cannot be recognized while the device is playing a beep.
Voice Command Customization
The ESP32-S3-BOX-3 features Espressif's proprietary AI Speech Recognition System for custom commands via the ESP BOX APP.
- Connect to the ESP BOX mobile app:
- Enter 'Network', tap 'To install APP'. Scan the QR Code or search "ESP BOX" in the App Store or Google Play to install the app.
- Register an account if you are a new user.
- Sign in with your ESP BOX account, turn on Bluetooth on your phone. Tap '+' and scan the QR code on your device to set up the network.
- After adding the device, follow the on-screen prompts for configuration, registration, and setup. Ensure the device is near your Wi-Fi router.
- Customize Voice Commands:
- Select the ESP-BOX device icon to access the screen. Toggle the button to turn the light on or off. You may need to develop Fan and Switch functionalities.
- Tap 'Light', then the 'Configure' tab to view default pin information and commands. Red, Green, and Blue pins can be changed.
- In the 'Configure' tab, customize commands for turning the light on/off and changing its color. For example, set "Good Morning" as the command to turn on the light. Click 'Save'.
- In the 'Control' tab, adjust the color, brightness, and saturation of the light.
- Test your new command by saying "Hi E. S. P." and then your custom command (e.g., "Good Morning") within 6 seconds. The command will show on the screen, and the module light will turn on.
For effective command performance:
- Command Length: 2-8 words. Maintain consistent length for command sequences.
- Avoid Repetition: Do not use shorter commands within longer ones (e.g., "turn on" and "turn on the light").
Development Guide for mobile APP
The ESP-BOX APP is built on the Nova Home APP architecture. For commercial access or inquiries, contact sales@espressif.com. For developers, Espressif offers the ESP RainMaker solution with development documentation and API guides. Access them via:
- ESP RainMaker Get Started
- RainMaker App APIs Definitions
- ESP RainMaker Programming Guide
Switch Voice Model Language
Access the 'About Us' page. Press the 'Boot' button to enter the factory mode language setting. Select 'English' or 'Chinese' and confirm. The device will reset and restart automatically.
Hardware Overview
ESP32-S3-BOX-3 Orthographic View
Diagram showing the top, bottom, front, back, and side views of the ESP32-S3-BOX-3, labeling components like Mute LED, Mute Button, Power LED, Microphones, Expansion Connector, Boot Mode Button, USB 5V Input Serial/JTAG, Reset Button, Speaker, and the 2.4' LCD Display & Capacitive Touch Panel.
Technical Specification
ESP32-S3
| Category | Details |
|---|---|
| Microcontroller | CPU: Dual-Core Xtensa® 32bit LX7 up to 240 MHz |
| Memory | SRAM: 512 KB, ROM: 384 KB |
| PSRAM | Octal SPI, 16 MB, PSRAM Speed: 120 MHz (Experimental Feature) |
| External Flash | Quad SPI, 16 MB |
| AI Feature | AI Algorithm: Neural Network, Acoustic algorithm, etc. Computing Acceleration: Vector, Complex number, FFT, etc. |
| Wireless | Wi-Fi: 2.4 GHz, IEEE 802.11b/g/n, Bluetooth® LE: Bluetooth® 5 LE and Bluetooth® mesh |
| Display | Display Type: 2.4-inch LCD, Display Resolution: 240 x 320 pixels, Display Interface: SPI, Interface Speed: 40 MHz, Touch Type: Capacitive, Touch Points: 10, Driver IC: IL19342C, Touch IC: GT911 |
| Audio Input | Microphone Type: Dual Mic, ADC Model: ES7210, Mute: Supported |
| Audio Output | Speaker Model: 8 Ohm 1 W, PA Model: NS4150, Codec Model: ES8311 |
| Sensor | Sensor Type: 3-axis Gyroscope, 3-axis Accelerometer, Sensor Model: ICM-42607-P |
| Interface | Type: USB Type-C, Usage: Power, USB download/JTAG debug, general USB device functions. Type: Goldfinger, Usage: I/O Expansion |
| User Interface | Onboard Buttons: Reset, Boot, Mute, Onboard LEDs: Power LED, Mute LED |
| OS/SDK | Original OS: FreeRTOS, SDK: ESP-IDF |
| Outline | Dimensions: 61 x 66 x 16.6 mm, Weight: 292 g |
| Power | USB-C Power: 5 V - 2.0 A Input, Battery: N/A |
ESP32-S3-BOX-3-DOCK Technical Specification
| Type | Number | Details | Usage |
|---|---|---|---|
| 12-pin Female Header | 2 | 8 I/O (Pmod™ Compatible), 3.3 V Power Output | GPIO, I2C, SPI, UART, RMT, LEDC, etc. |
| USB Type-A | 1 | 5 V Power Output, USB Host | Connect to diverse USB devices such as USB camera, USB disk, and other HID devices |
| USB Type-C | 1 | 5 V Power Input | 5 V power input only |
| PCIe Connector | 1 | 36 Pin, 1.00 mm (.0394") pitch, Accepts .062" (1.60 mm) card | Vertical mounting goldfinger |
Digilent Pmod™ Interface Specification
ESP32-S3-BOX-3-DOCK Pinout Diagram
Diagram showing the pinout of the ESP32-S3-BOX-3-DOCK, indicating 3V3, GND, GPIO pins, USB, and PWM/JTAG/Serial/Power Rail designations.
ESP32-S3-BOX-3-SENSOR Technical Specification
| Type | Number | Details | Usage |
|---|---|---|---|
| Radar Sensor (MS58-3909S68U4) | 1 | Frequency band: 5.8 GHz; Ultimate Power Consumption: 40 uA; Sensing Range: Around 2 meters | Human presence detection |
| Infrared Sensor | 2 | A pair of IR emitter (IRM-H638T) and receiver (IR67-21C/TR8) tubes around 4 meters | Infrared control applications |
| Temp&Hum Sensor (AHT30) | 1 | Temp Range: -40 + 120 °C/± 0.5 °C; Hum Range: 0~100% RH/± 3% RH (25 °C) | Temperature and humidity monitoring |
| External Storage | 1 | MicroSD card slot (Maximum 32GB) | Expand storage capabilities |
| Battery | 1 | 18650 Rechargeable battery slot | Sustainable and portable power supply |
| Switch | 1 | 2-speed toggle switch | Control of battery charging and discharging to protect the 18650 battery |
| Indicator LED | 1 | Charging indicator LED | Red: Charging; Green: Fully charged |
| USB Type-C | 1 | 5 V Power Input, USB Device | Power, USB download/JTAG debug, general USB device functions |
| PCIe Connector | 1 | 36 Pin, 1.00 mm (.0394") pitch, Accepts .062" (1.60 mm) card | Vertical mounting goldfinger |
Tips:
- When charging the 18650 battery, toggle to 'ON' and plug the ESP32-S3-BOX-3 into the ESP32-S3-BOX-3-SENSOR.
- Avoid hot-plugging the ESP32-S3-BOX-3-DOCK and switching to the ESP32-S3-BOX-3-SENSOR during firmware experience to prevent recognition issues. Power cycle the sensor to resolve.
ESP32-S3-BOX-3-BRACKET Technical Specification
| Type | Number | Details | Usage |
|---|---|---|---|
| 12-pin Female Header | 2 | 8 I/O (Pmod™ Compatible), 3.3 V Power Output | GPIO, I2C, SPI, UART, RMT, LEDC, etc. |
| USB Type-C | 1 | 5 V Power Input, USB Device | Power, USB download/JTAG debug, general USB device functions |
| PCIe Connector | 1 | 36 Pin, 1.00 mm (.0394") pitch, Accepts .062" (1.60 mm) card | Vertical mounting goldfinger |
| Bolt | 2 | M3 Bolt, Nut, and Washer | Mount materials and fasten components together |
ESP32-S3-BOX-3-BREAD Technical Specification
| Type | Number | Details | Usage |
|---|---|---|---|
| 12-pin Male Header | 2 | 8 I/O, 3.3 V Power Output, 5 V Power Input | GPIO, I2C, SPI, UART, RMT, LEDC, etc. |
| USB Type-C | 1 | 5 V Power Input, USB Device | Power, USB download/JTAG debug, general USB device functions |
| PCIe Connector | 1 | 36 Pin, 1.00 mm (.0394") pitch, Accepts .062" (1.60 mm) card | Vertical mounting goldfinger |
Diagram showing the pinout of the ESP32-S3-BOX-3-BREAD, indicating power, ground, GPIO, USB, and serial connections.
FCC Regulations
This device complies with Part 15 of the FCC Rules. Operation is subject to two conditions: (1) it may not cause harmful interference, and (2) it must accept any interference received, including interference that may cause undesired operation. The device has been tested and found to comply with limits for a Class B digital device, providing reasonable protection against harmful interference in residential installations. This equipment generates, uses, and can radiate radio frequency energy, and improper installation or use may cause harmful interference to radio communications. There is no guarantee that interference will not occur in a particular installation. If interference occurs, users are encouraged to try correcting it by:
- Reorienting or relocating the receiving antenna.
- Increasing the separation between the equipment and receiver.
- Connecting the equipment to an outlet on a different circuit than the receiver.
- Consulting a dealer or experienced radio/TV technician.
FCC Note Caution: Changes or modifications not expressly approved by the party responsible for compliance could void the user's authority to operate the equipment.
RF Exposure Information
This device meets government requirements for exposure to radio waves. It is designed and manufactured not to exceed emission limits for radio frequency (RF) energy set by the Federal Communications Commission (FCC). This device complies with FCC radiation exposure limits for an uncontrolled environment. To avoid exceeding these limits, human proximity to the antenna should not be less than 20 cm during normal operation.
This guide provides a basic introduction to using the latest firmware on the BOX series of development boards. Users can now start writing programs and embark on their IoT journey!
