The overuse of the voice by professional voice users, such as teachers, is known to cause physiological vocal fatigue. Vocal fatigue is used to denote negative vocal adaptation that occurs as a consequence of prolonged voice use or vocal load. This study investigates how self-reported vocal fatigue is related to voice parameters (sound pressure level SPL, fundamental frequency f0, and their standard deviations) and the duration of the vocal load. Thirty-nine subjects were recorded while reading a text. Different acoustics scenarios were artificially created to increase the variability in the speech produced (3 reverberation time, 2 noise conditions, and 3 auditory feedback levels), for a total of 18 tasks per subject presented in a random order. For each scenario, the subjects answered questions addressing their perception of vocal fatigue on a visual analog scale. A model of the vocal fatigue to acoustic vocal parameters is proposed. The duration of the vocal load contributed to 55% of the variance explained by the model, followed by the interaction between the standard deviations of the SPL and f0 (24%). The results can be used to give a simple feedback during voice dosimetry measurements.