Even with the rapid advancement of technology, using a television still requires a physical remote control. Apart from occasionally losing sight of the television remote control, we also sometimes run out of batteries. The goal is to discover an effective way of controlling television and develop 3D hand gesture-based smart television control using Gated Recurrent Unit (GRU).The results of the research show that hand gesture recognition-based interface technology is capable of performing the majority of smart TV operations.It is a comfortable and delightful experience for consumers. The existing research features static image gesture recognition with predefined models for training in addition to the existing research the proposed model features sample video dataset, Custom design with Gated Recurrent Unit. The suggested model is trained using five hand gestures. The camera positioned on the TV continually records the motions. Each gesture is associated with a certain command. The proposed model has achieved an accuracy of about 94% in recognizing the gestures.