Devlog #3 - My assistant talks now (Really)

In this devlog, I bring my AI assistant to life by making it listen and talk in real-time. Using wake word detection, real-time audio streaming, and Whisper AI, my custom-built system can now process audio input and respond intelligently. 🛠️ What’s inside: Real-time audio streaming via MQTT Wake word detection with Vosk Audio chunking and buffering Transcription using Whisper gRPC pipeline between Go and Python services I’m building this assistant from scratch to eventually handle routines, reminders, and smart interactions — with full control over the stack. Want to see more contents like this? 📖 🤓 Follow me on: Medium: https://medium.com/@fdn-sharp X: https://x.com/farhad_nowzari LinkedIn: https://www.linkedin.com/in/farhad-nowzari-94060699/ Github: https://github.com/farhadnowzari Have fun coding ❤️