Waveshare ESP32-S3-AUDIO-Board
ESP32-S3 AI smart speaker development board with dual-microphone array, ES8311 audio codec, 7 surround RGB LEDs, RTC, camera and LCD expansion interfaces, and LiPo battery support for voice assistant and audio projects.
$15.99
Tap any value to browse matching devices
Specifications
Components
Espressif ESP32-S3R8 Xtensa LX7 dual-core @ 240MHz with 512KB SRAM, 8MB PSRAM, WiFi and BLE 5.0
Everest Semiconductor ES8311 24-bit mono audio codec with DAC/ADC and I2S interface for speaker output and microphone input
Everest Semiconductor ES7210 four-channel audio ADC for dual-microphone array with noise reduction
Texas Instruments TCA9555PWR 16-bit I2C GPIO expander with interrupt output
NXP PCF85063 real-time clock with integrated crystal, alarm function, and battery backup
MPS MP1605GTF-Z synchronous buck converter providing 3.3V at up to 2A output
7x WS2812 addressable RGB LEDs in surround configuration for voice assistant visual feedback
Bus Interfaces
GPIO Map
Overview
The Waveshare ESP32-S3-AUDIO-Board is an AI smart speaker development platform built around the ESP32-S3R8 module with 8MB PSRAM and 16MB flash. It integrates a complete audio pipeline featuring a dual-microphone array with ES7210 quad-channel ADC for noise reduction and echo cancellation, an ES8311 audio codec for playback, and a speaker output header.
Seven surround WS2812 RGB LEDs provide visual feedback for voice wake-word detection and status indication, similar to commercial smart speakers. The board includes a PCF85063 RTC for time-aware applications and a TCA9555PWR 16-channel GPIO expander for additional I/O.
Expansion is handled through an 18-pin SPI LCD FPC connector (supporting 1.47 to 3.5 inch Waveshare displays) and a 24-pin DVP camera interface compatible with OV2640/OV5640 sensors. The MX1.25 battery connector and built-in charging circuit enable portable operation, while the MP1605GTF-Z DC-DC converter provides efficient 3.3V power at up to 2A.
Use Cases
6AI Voice Assistant
AI-powered voice assistant device with microphone array, speaker output, and cloud or local speech recognition for voice commands and conversation.
Voice Assistant
Offline and cloud-connected voice assistant, wake-word detection, and speech recognition projects.
Music Player
Embedded audio player with speaker output, controls, and display for playing audio files or streaming.
Internet Radio
WiFi-connected streaming radio player receiving online audio streams via internet.
Smart Home Dashboard
Wall-mounted or tabletop display showing Home Assistant dashboards, sensor readings, and smart home controls.
Computer Vision
Image recognition, object detection, and ML inference using embedded cameras and AI-capable processors.
Resources
Where to Buy
Explore more of the directory — popular use cases, firmware, and specs to browse next.
