Biological invasion is a major threat to biodiversity worldwide, and eradication is most feasible during the early phase of invasion. Recent advancements in deep learning now allow researchers to develop accurate and automated acoustic detectors with relative ease, making bioacoustic monitoring a promising method for early detection of sound-emitting species. However, its application to invasive alien species remains limited. In this study, we developed and evaluated a deep learning-based call detector for Southeast Asian treefrog (Polypedates leucomystax) and cane toad (Rhinella marina) on Iriomote Island, a Natural World Heritage Site located 30 km from established populations of these alien species on the nearby Ishigaki Island. We trained the BirdNET model with acoustic data collected on Ishigaki Island, where these species are common, as well as native frog calls from Iriomote Island. Model performance was evaluated using sounds obtained by playing back the alien species call on Iriomote Island. When detection thresholds were properly adjusted, these playback survey dates were clearly identifiable from the high number of detections, except on a night with dense choruses of the native frog Microhyla kuramotoi. Furthermore, a year-round acoustic monitoring on Ishigaki Island revealed the breeding phenolgies of both invasive species, which offers insights for scheduling monitoring efforts. Finally, we provide a workflow for creating automated acoustic detectors using the user-friendly BirdNET software.