Tracking biodiversity and its dynamics at scale is essential if we are to solve global environmental challenges. Detecting animal vocalizations in passively recorded audio data offers an automatable, inexpensive, and taxonomically broad way to monitor biodiversity. However, the labor and expertise required to label new data and fine-tune algorithms for each deployment is a major barrier. In this study, we applied a pretrained bird vocalization detection model, BirdNET, to 152,376 h of audio comprising datasets from Norway, Taiwan, Costa Rica, and Brazil. We manually listened to a subset of detections for each species in each dataset, calibrated classification thresholds, and found precisions of over 90% for 109 of 136 species. While some species were reliably detected across multiple datasets, the performance of others was dataset specific. By filtering out unreliable detections, we could extract species and community-level insight into diel (Brazil) and seasonal (Taiwan) temporal scales, as well as landscape (Costa Rica) and national (Norway) spatial scales. Our findings demonstrate that, with relatively fast but essential local calibration, a single vocalization detection model can deliver multifaceted community and species-level insight across highly diverse datasets; unlocking the scale at which acoustic monitoring can deliver immediate applied impact.