Ever wanted to dabble in face and/or speech recognition? Espressif’s ESP-EYE is a miniature ESP32-based development board that combines a digital microphone, ESP32 (of course) with 8 MB PSRAM and 4 MB flash, and a 2 megapixel camera. There’s a few buttons and LEDs as well for basic control and configuration.
Unlike some boards, this codebase does not require internet connectivity — you don’t have to send video or audio data to ‘the cloud’ — it’s all processed on-chip! The built in demo shows off what it can do:
- Plug into a computer USB port and open up a serial port connection at 115,200 baud to the new serial port
- Once the red LED is lit, activate the board with the watchword «Hi Lehshin» (in documents they spell it lexin, the x is pronounced as a shh sound)
- The red LED will blink — then connect to the new Wi-Fi access point created
- Open up a web browser to http://192.168.4.1/face_stream
- Point the camera at faces to show off the recognition boxes! Video is about 2 frames per second, not super fast.
Once you get the demo going, check out the source code and ESP development platform to customize your very own DIY voice/speech recognition project.
- WiSoC ESP32 dual core Tensilica LX6 processor with WiFi and Bluetooth
- Memory: 8MB PSRAM
- Storage: 4MB Flash
- Camera: 2MP OV2640 Camera
- Audio: MEMS Microphone
- USB: 1 microUSB port for power and programming over serial
- Misc: Reset, boot and function buttons, 2x LEDs
- Dimensions: 41 x 21 mm
For product support and replacement parts for Espressif Systems products visit the forum page or contact Espressif System directly https://www.espressif.com/