Background Effective communication skills are fundamental for health care professionals, yet conventional training methods face challenges in scalability and accessibility due to resource constraints. The emergence of artificial intelligence (AI), particularly generative AI, offers innovative ways for enhancing communication skills training by simulating realistic conversational scenarios and providing personalised, adaptive feedback. This manuscript is presented as study protocol for a cluster-randomised controlled trial that aims at evaluating the efficacy of an AI-supported higher education training protocol incorporating generative AI exercises to enhance communication competencies among psychology students. Methods In this cluster-randomised controlled trial, psychology students enrolled in communication skill seminars at a medium sized university in a medium sized German city will participate. Classes will be assigned within a parallel group design to the AI condition (AI-enhanced exercises alongside teaching-as-usual, TAU, that includes classical exercises) or the control condition (TAU only). Additional non-randomised comparison classes will comprise students with TAU only, but not be part of main analyses. The primary outcome is the change in communication skills from baseline, assessed through questions reflecting the communication techniques emphasised in the training. Secondary outcomes include communication skills, self-efficacy and self-concept, motivation, attitudes toward AI, user experience with the AI tool, student evaluations of course quality, and feasibility aspects such as uptake and usability. Data will be collected via online surveys and the university’s teaching platform. Statistical analyses will employ mixed models to evaluate the intervention’s impact. Discussion This study will provide empirical evidence on the effectiveness and feasibility of integrating AI into higher education communication skills training. Successful integration of AI-enhanced training could revolutionise educational practices by offering scalable, accessible, and personalised learning experiences. The findings may have broader implications for incorporating AI tools in various educational and professional training contexts, while addressing ethical considerations and promoting responsible use of AI in education. Trial registration This trial has been pre-registered on the Open Science Framework (OSF) under identifier ‘th6f4’.