BBTalkie: A Hands-Free Mini Walkie-Talkie Based on ESP32
A portable ESP32-based walkie-talkie that uses an embedded neural network for voice activity detection and keyword spotting, enabling push-to-talk-free operation.
Sensors and I/Ovoice activity detectionkeyword spottingembedded neural networkaudio I/Oportable radioESP32 family
Official path: https://oshwhub.com/corebb/bbtalkie
01 Overview
BBTalkie is a compact ESP32-based walkie-talkie designed for hands-free use.
An embedded neural network performs voice activity detection (VAD) and keyword spotting (KWS); transmission is triggered automatically when speech or a wake word is detected.
The hardware is open source: PCB, firmware, CAD drawings, and development tools are all provided in the repository.
02 Hardware
MCU: ESP32 family (exact variant per schematic).
Audio: onboard microphone input and speaker driver for voice capture and playback.
RF: uses ESP32 Wi-Fi or Bluetooth for wireless voice streaming (protocol and band per firmware).
Power: Li-ion battery with charging management (voltage and charger IC per schematic).
Interfaces: programming/debug header (UART or USB) for flashing and debugging.
03 Software flow
Firmware is built on ESP-IDF or Arduino, handling audio capture, neural network inference, and wireless transmission.
The neural network model performs VAD and KWS; it is quantized for deployment on ESP32.
The open-source repository includes full code, PCB design files, CAD drawings, and auxiliary tools and references used during development.