Hello everyone! I wanted to share an exciting project I’ve been working on over the past couple of months. It’s a custom PCB design for the Google Home Mini that incorporates ESP32-based wake word detection and Bluetooth A2DP audio streaming. This has been a fascinating journey, and I’m thrilled to see it finally come together!
The key features of this project include local wake word detection handled entirely by the ESP32, eliminating the need for cloud connectivity. When a voice command is detected, it’s streamed via Bluetooth, ensuring seamless interaction. To conserve power, the system enters sleep mode when no voice interaction is detected, functioning as a Bluetooth A2DP speaker for music or media playback while idle.
My goal with this project was to create a low-power, flexible voice interface that’s ideal for offline or privacy-focused smart environments. It’s been incredibly rewarding to see it work as intended, especially the power management aspect which significantly extends battery life.
Currently, I’m waiting for native support in OpenHAB for ESP32 audio streaming and voice detection, which will allow for full integration of this DIY voice assistant. This would enable it to trigger rules, control items, and more within the OpenHAB ecosystem.
If anyone is exploring similar ideas, has tips, or knows of workarounds, I’d love to connect and exchange thoughts! Let’s collaborate to push the boundaries of what’s possible with ESP32 and voice interfaces. Happy tinkering! 