Google Chat:---
+86-0755-88291180
sales@spotpear.com
dragon_manager@163.com
tech-support@spotpear.com
zhoujie@spotpear.com
WhatsApp:13246739196
WhatsApp:13424403025
$20.9
The ESP32-S3 AIoT camera development board integrates audio input/output modules, supports external displays, and enables image acquisition and recognition as well as AI voice interaction.



This product is an AI development board based on the ESP32-S3, integrating a camera interface (DVP), SPI/QSPI display interface, and audio acquisition and playback functions. It balances low cost, high performance, and low power consumption, meeting the diverse development needs of smart terminals. It supports integration with online AI large-scale model platforms such as Xiaozhi, Doubao, and DeepSeek, enabling human-computer interaction functions such as voice dialogue and question-and-answer recognition. It also provides an Edge Impulse object detection example, supporting real-time and multi-object recognition, suitable for rapid development of AI voice interaction, edge vision detection, HMI applications with screens, and smart cameras.
| model | Maximum resolution | Output interface | Output format | Lens Size | focal length | aperture | Field of view |
|---|---|---|---|---|---|---|---|
| OV5640 | 2592×1944 | DVP | RGB565 YUV/YCbCr422 | 1/4inch | 4.1mm | 2.8 | D:68° H:55° V:42° |
| OV3660 | 2048×1536 | DVP | 8/10-bit Raw RGB data JPEG compression YUV/YCbCr422 RGB565 | - | 3.2mm | 2.4 | D:68° |
| GC2145 | 1616×1232 | DVP | RGB565 YCbCr422 8bit Raw RGB data | 1/5inch | 2.38mm | 2.4 | D:68° H:60° V:46.8° |
| GC0308 | 648×488 | DVP | Grayscale YCbCr422 RGB565 | 1/6.5inch | 2.5mm | 2.4 | D:58° H:46° V:35° |


Supports multiple high-definition cameras, enabling image acquisition and AI visual recognition. Integrates dual microphones, audio amplifier, and echo cancellation, supporting access to AI online large-scale model platforms such as Xiaozhi/DeepSeek for ASR (Automatic Speech Recognition) and dialogue interaction. Leveraging the powerful computing capabilities of the ESP32-S3, it achieves dual intelligent control via vision and voice, suitable for scenarios such as intelligent monitoring, voice assistants, and IoT automation.

The default onboard antenna can be switched to an external antenna via a desoldering resistor.
Output power 3W 4Ω
The GH1.25 2-pin connector can be used to connect a 3.7V lithium battery and supports charging and discharging.

