The integration of gesture recognition and voice assistance technologies into human-computer interaction (HCI) has garnered significant attention in recent years, fostering innovative applications across various domains. This literature review synthesizes findings from several research papers, highlighting advancements in static and dynamic gesture recognition using Convolutional Neural Networks (CNN) and other machine learning techniques. Notably, several studies demonstrate the efficacy of gesture-based controls in enhancing user experience, particularly in smart environments and automated systems. The proposed systems exhibit high accuracy rates, with some achieving over 88% in gesture recognition, emphasizing the robustness of deep learning approaches. Furthermore, the evolution of gesture recognition interfaces to include voice-controlled assistants showcases a dual-modality approach that enhances accessibility and user interaction. These systems, which utilize Natural Language Processing (NLP) and voice recognition technologies, allow users to perform tasks intuitively, bridging the gap between physical and virtual interactions. The integration of gesture and voice commands has significant implications for diverse applications, including smart classrooms, home automation, and assistive technologies for individuals with disabilities. Overall, this review elucidates the potential of gesture and voice-based systems to revolutionize interaction paradigms, offering a promising direction for future research and development in user interface design and assistive applications.