Cultural ecosystem services (CESs) represent a critical link between ecosystems and human well-being and constitute a core foundation for regional sustainable development. The balance between CES supply and demand directly affects the coordination efficiency between ecological conservation and socio-economic development, making it a key prerequisite for ecosystem management, conservation planning, and policy formulation. This study focuses on the circum-Taihu region and integrates multi-source data to assess public perceived demand and spatial supply capacity of CESs. Supply–demand matching relationships are examined across three dimensions, namely, scenic beauty, cultural heritage, and recreation, through the construction of a region-specific CES quantitative indicator system. The impacts of multiple environmental factors on CES supply–demand dynamics are further explored to provide scientific support for coordinated ecological, cultural, and economic sustainability at the regional scale. The findings demonstrate the following: (1) the proposed methodology effectively quantifies CES perception and supply capacity in the circum-Taihu region. Scenic beauty exhibits the highest perception levels, whereas cultural heritage and recreation show lower perception. Cultural heritage displays the strongest supply capacity, whereas scenic beauty and recreation exhibit weaker supply. (2) Significant spatial imbalances exist between CES perception levels and supply capacity across the circum-Taihu region. Areas exhibiting mismatches constitute the largest proportion for cultural heritage CESs, followed by scenic beauty, with recreation displaying the smallest amounts of imbalance. (3) Environmental drivers exert differentiated effects on CES supply–demand relationships. Slope, road network density, and elevation have significant positive effects, whereas the normalized difference vegetation index (NDVI), distance to water bodies, and distance to roads exhibit significant negative effects. Distance to roads imposes the strongest inhibitory influence on CES perception, whereas elevation emerges as the most influential driver of public perceived CES levels.