Hand gesture recognition plays a significant role in bridging the gap between humans and machines, enabling intuitive interaction in various domains. This paper presents a model focused on developing a custom hand gesture recognition using a Python LSTM (Long Short-Term Memory) deep learning model augmented with a dense layer. The aim of this model is to accurately recognize and classify a set of custom hand gestures in real-time. The system achieves high accuracy in real-time gesture recognition, showcasing its potential applications in human-computer interaction, virtual reality, sign language translation, and other domains. This paper’s findings contribute to the advancement of gesture recognition technology and provide a foundation for further research and development in this field.