Speech perception in noisy environments is boosted when a listener can see the speaker's mouth and integrate the auditory and visual speech information. Autistic children have a diminished capacity to integrate sensory information across modalities, which contributes to core symptoms of autism, such as impairments in social communication. We investigated the abilities of autistic and typically‐developing (TD) children to integrate auditory and visual speech stimuli in various signal‐to‐noise ratios (SNR). Measurements of both whole‐word and phoneme recognition were recorded. At the level of whole‐word recognition, autistic children exhibited reduced performance in both the auditory and audiovisual modalities. Importantly, autistic children showed reduced behavioral benefit from multisensory integration with whole‐word recognition, specifically at low SNRs. At the level of phoneme recognition, autistic children exhibited reduced performance relative to their TD peers in auditory, visual, and audiovisual modalities. However, and in contrast to their performance at the level of whole‐word recognition, both autistic and TD children showed benefits from multisensory integration for phoneme recognition. In accordance with the principle of inverse effectiveness, both groups exhibited greater benefit at low SNRs relative to high SNRs. Thus, while autistic children showed typical multisensory benefits during phoneme recognition, these benefits did not translate to typical multisensory benefit of whole‐word recognition in noisy environments. We hypothesize that sensory impairments in autistic children raise the SNR threshold needed to extract meaningful information from a given sensory input, resulting in subsequent failure to exhibit behavioral benefits from additional sensory information at the level of whole‐word recognition. Autism Res 2017. © 2017 International Society for Autism Research, Wiley Periodicals, Inc. Autism Res 2017, 10: 1280–1290. © 2017 International Society for Autism Research, Wiley Periodicals, Inc.