ESP32-S3 AI Voice Development Board w/ 0.96-Inch OLED & Dual Mics

You can program the board using the Arduino IDE with the ESP32 board package installed, Espressif's official ESP-IDF framework for advanced features, or MicroPython for scripting. Connect via the USB-C port, select the correct COM port and board target (e.g., ESP32-S3 Dev Module), and upload your code. The board supports standard serial communication for debugging.

The board is designed to work with Espressif's AI frameworks like WakeNet for offline wake-word detection and MultiNet for speech command recognition. You need to integrate these models into your ESP-IDF project, configure the PDM microphone channels, and flash the firmware. The dual microphones provide the necessary audio data for accurate, noise-resistant voice processing locally on the chip.

Yes, the board supports battery operation via its 3.3V input pin. Typical operating current depends on Wi-Fi/Bluetooth activity and CPU load, ranging from 50mA during active wireless communication to below 10mA in deep sleep mode. For prolonged battery life, utilize the ESP32-S3's ultra-low-power coprocessor and deep sleep features, waking via timer or external interrupt.

Connect a 4-8 ohm speaker directly to the onboard amplifier's output terminals. The integrated 2.5W Class-D amplifier is controlled via the I2S audio interface of the ESP32-S3. Use the ESP-IDF Audio Development Kit (ADF) or Arduino libraries to generate tones, play audio files, or synthesize speech, sending the digital audio stream to the I2S peripheral which drives the amplifier.