video1.0<iframe src="https://www.loom.com/embed/967da808d8e846beafd3d98ed1632afa" frameborder="0" width="1920" height="1440" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>14401920Loomhttps://www.loom.com14401920https://cdn.loom.com/sessions/thumbnails/967da808d8e846beafd3d98ed1632afa-f0f19bfe86363fd7.gif318.742In part two, I built the ears of our WhatsApp automation system using the Speech Recognition library. I used SR Recognizer to open the microphone, adjust for ambient noise for one second, capture audio, and convert speech to text by sending it to Google servers, then print the lowercase text on screen. I also handled errors when the audio cannot be understood or when the Google request fails. I ran the code with examples like asking for Raja to get a message. No viewer action was specifically requested.