This study examines how the cognitive and perceptual loads introduced by a word prediction feature impact learning and performance. Two groups of able-bodied subjects transcribed text using two row–column scanning systems for 10 consecutive trials each. The two systems differed only in that one system had a word prediction feature. Subject groups differed in their order of system use. The results show that, under the conditions of this study, the word prediction system was not substantially more difficult to learn, but it did not yield a statistically significant improvement in text generation rate. This suggests that the cost of using this word prediction system balanced the benefit of the keystroke savings achieved by these subjects. The relationship between keystroke savings, cost in item selection rate, and improvement in text generation rate is explored in order to provide insight into this outcome.