š§Ŗ What if we could give senses to AI?
Ā
For the past few years, Iāve been experimenting with ESP32 modules, plugging them into my Alambic framework. The goal? Build a seamless voice āļø LLM āļø voice loop ā in any language ā enriched with vision and a wide array of sensors. In short, give senses to artificial intelligence.
Ā
š Good news: I finally found the right device ā for under $25!
ā
WebSocket communication with Node-RED
ā
Powerful enough for light Edge AI
ā
Compatible with dozens of sensors
ā
And yes⦠it talks! š£ļø In any language!
Ā
š„ Real-time demo available (a bit slow for now, blame the MS API latency). With a real-time model, itāll be much smoother (see the wiki).
Ā
Ā
I was really impress with ChatGPT4o be able to describe with accuracy the dragon where the image quality was very weak !
Ā
āļø The real challenge?
š Taming C++ in the real world: managing Wi-Fi power, avoiding CPU crashes, distributing tasks across cores⦠every detail matters.
š§ But there's still a major frustration: how does the Gravity connector actually work?
Ā
Thanks to DFRobot for the DFR1154, a brilliant board But⦠Iām stuck:
Ā
- Is the Gravity port UART-only, not I2C? If so, why such a limitation?- I tried connecting SEN0539 (for KWS) and DFR0997 (for camera), with no success.- There's no way to wire a button like DFR0785, which could trigger speech events.
Ā
I posted a detailed question on the DFRobot forum, but still waiting for answers.
š If you have any tip, workaround, or code snippet to make the Gravity port more useful ā Iām all ears.
Ā
Ā
