This thesis introduces an innovative application designed for the Apple Watch that aims to bridge the communication gap between hearing impaired individuals and those who can hear and speak by translating Swedish sign language into text and sound. Leveraging the growing popularity of smartwatches and their advanced sensors, the application utilizes the accelerometer, gyroscope, and rotation rate sensors from Apple's Core Motion framework. The application has been tested with eleven static hand gestures representing letters from the Swedish alphabet and seven moving hand gestures representing words from Swedish sign language. Two different machine learning models were employed: Random Forest for letter detection and an Activity Classifier model developed by Apple for word detection, both implemented using Create ML. In an experiment involving five participants who each performed the gestures and words ten times, the application achieved a letter detection accuracy rate of over 36%, with an average correct detection rate of 61.6%. For word detection, the success rate was above 88%, with an average detection accuracy of 96%.