The 'automatic letter-sound integration hypothesis' (Blomert, ) proposes that dyslexia results from a failure to fully integrate letters and speech sounds into automated audio-visual objects. We tested this hypothesis in a sample of English-speaking children with dyslexic difficulties (N = 13) and samples of chronological-age-matched (CA; N = 17) and reading-age-matched controls (RA; N = 17) aged 7-13 years. Each child took part in two priming experiments in which speech sounds were preceded by congruent visual letters (congruent condition) or Greek letters (baseline). In a behavioural experiment, responses to speech sounds in the two conditions were compared using reaction times. These data revealed faster reaction times in the congruent condition in all three groups. In a second electrophysiological experiment, responses to speech sounds in the two conditions were compared using event-related potentials (ERPs). These data revealed a significant effect of congruency on (1) the P1 ERP over left frontal electrodes in the CA group and over fronto-central electrodes in the dyslexic group and (2) the P2 ERP in the dyslexic and RA control groups. These findings suggest that our sample of English-speaking children with dyslexic difficulties demonstrate a degree of letter-sound integration that is appropriate for their reading level, which challenges the letter-sound integration hypothesis.