This paper explores the development of a sign language to text app, which can translate sign language gestures into written text. The app leverages machine learning and computer vision technology to identify and analyse hand movements and gestures made by users, and accurately transcribes them into text in real-time. The app has the potential to revolutionise communication for deaf and hard-of-hearing individuals, as well as bridge the communication gap between hearing and non-hearing individuals. The essay further discusses the challenges faced during the development process, including the complexity of sign language and the need for accuracy in transcription, and proposes potential solutions to overcome these challenges. Additionally, the essay highlights the ethical considerations surrounding the app’s development, such as ensuring user privacy and accessibility. Overall, the sign language to text app has the potential to transform communication accessibility for the deaf and hard-of-hearing community and has far-reaching implications for accessibility and inclusivity in society. Utilising a TensorFlow architecture, the model employs a Convolutional Neural Network (CNN) for effective feature extraction from hand gestures. Trained on a number of sign language gestures, the CNN contributed to the model’s high accuracy, achieving exceptional precision and recall metrics during real-time recognition. The gesture recognition model achieved outstanding precision (0.95), recall (1.0), and F1 score (0.974), ensuring accurate sign language translation. Confidence levels consistently surpassed 97%, with the confusion matrix demonstrating a 91% reliability in gesture identification.