In a nonstrenuous exercise, the heart rate (HR) shows a linear relationship with the maximum volume of oxygen consumption VO(2Max) and serves as an indicator of performance of the cardiovascular system. The HR replaces the %VO(2Max) in exercise program prescription to improve aerobic endurance. In order to achieve an optimal effect in an endurance training, the athlete needs to work out at an HR high enough to trigger the aerobic metabolism, while avoiding the very high HRs that bring along significant risks of myocardial infarction. The minimal and optimal base training programs, followed by stretching exercises to prevent injuries, are adequate programs to maximize benefits and minimize health risks for the cardiovascular system during single session training. In this paper, we have defined a functional model for an ambient intelligence system that monitors, evaluates, and trains the aerobic endurance. It is based on the Android operating system and the Gow Running smart shirt. The system has been evaluated during functional assessment stress testing of aerobic endurance in the Stress Physiology Laboratory (SPL) of the Technical University of Madrid. Furthermore, a voice system designed to guide the user through minimal and optimal base training programs has been evaluated. The results obtained fully confirm the model with a high correlation between the data collected by the system and the by SPL. There is also a high hit rate between training sessions of the users and the objective training functions defined in the training programs.