A number of studies have examined the validity of using spectral parameters, such as median frequency ($F_{med}$) and Dimitrov spectral index of muscle fatigue ($FI_{nsm5}$) from the surface EMG signal during dynamic exercise, to assess muscle fatigue. Despite these studies, the ability to accurately predict endurance capacity using these spectral parameters during repetitive dynamic contractions is limited. The main purpose of this study was to examine the potential of using the incremental time, defined as the time when the Dimitrov spectral index increases to a certain value relative to the initial value, to predict the endurance time ($T_{end}$), which was determined when the subject became exhausted and could no longer follow the fixed contraction cycle. Ten healthy subjects performed five sets of voluntary isotonic contractions until they could only produce 10% and 20% of their maximal voluntary contraction level (MVC). The $T_{end}$ for all subjects were within the following ranges: $157{pm}62$ s at 10% MVC; $75{pm}31$ s at 20% MVC. Spectral parameters such as median frequency and Dimitrov spectral index were extracted from every contraction segment and estimated using linear regressive analysis at every contraction. The initial slope of both spectral parameters and the incremental time of the Dimitrov spectral index were compared as a predictor of endurance time. Significant correlations were found: 1) between $T_{end}$ and contraction level (p<0.05) and 2) between $T_{end}$ and the incremental time when the Dimitrov spectral index was above 130% of the increment with respect to the initial value at 20% MVC (p<0.01). In conclusion, the incremental time of the Dimitrov spectral index could be used to describe the changes in the spectral content of the sEMG signal and could be used as a good predictor of endurance time in comparison to the initial slope of the median frequency.