What kind of audiovisual environment makes passengers experience travel well-being in high-speed railway stations?

China has the world's largest high-speed railway network. As critical hubs handling millions of trips daily, these stations profoundly shape passengers’ travel experience. Based on a survey of 377 passengers across six stations, this study employs structural equation modeling (SEM) to investigate how audiovisual environments influence waiting experience and travel well-being. The key findings are: (1) The model explains 75.2% of the variance in travel well-being; soundscape and visual perception contribute comparably, and their synergy shapes waiting experience, which in turn affects travel well-being. (2) Visual perception directly affects the waiting experience (β_wayfinding = 0.483 > β_comfort = 0.394) and travel well-being (β = 0.259). Functional layout and wayfinding systems are most influential, followed by spatial scale, lighting conditions, and landscape aesthetics. (3) Soundscape pleasantness, rather than eventfulness, is the critical factor, exerting its strongest influence on comfort (β = 0.345), followed by travel well-being (β = 0.247) and wayfinding (β = 0.224). Human sounds are the primary negative predictor, while background music and public announcements exert comparable positive effects. (4) Female passengers, frequent travelers, and passengers with longer waiting times report lower travel well-being. Interestingly, older passengers exhibit a “low wayfinding, high well-being” profile versus the young.