In their Covert Repair Hypothesis, Postma and Kolk (1993) suggest that people who stutter make greater numbers of phonological encoding errors, which are detected during the monitoring of inner speech and repaired, with stuttering-like disfluencies as a consequence. Here, we report an experiment that documents the frequency with which such errors are made. Thirty-two people who stutter (PWS) and thirty-two normally fluent controls, matched for age, gender and education, recited tonguetwisters and self-reported any errors they perceived themselves to have made. In 50% of trials the tonguetwisters were recited silently and errors reported were those detected in inner speech. Compared to controls, PWS produced significantly more word-onset and word-order errors. Crucially, this difference was found in inner as well as in overt speech. Comparison of experimenter ratings and participants' own self-ratings of their overt speech revealed similar levels of accuracy across the two groups, ruling out a suggestion that PWS were simply more sensitive to the errors they made. However, the frequency of participants' inner-speech errors was not correlated to their SSI4 scores, nor to two other measures of stuttering severity. Our findings support Postma and Kolk's contention that, when speech rate is held constant, PWS make, and therefore detect, more errors of phonological encoding. They do not, however, support the hypothesis that stuttering-like disfluencies in everyday speech stem from covert repairs of errors of phonological encoding. Learning outcomes: Readers will learn about three current psycholinguistic theories of stuttering, and how speech-errors elicited during tonguetwister recitation can be used to explore the controversies that exist surrounding: (a) Whether or not people who stutter are more prone to making language production errors; and (b) The extent to which stuttering-like disfluencies stem from covert repairs of language-production errors. (Contains 3 figures and 4 tables.)