Understanding how species coexist is one of the main goals in ecology. While many have documented how species coexist in nature, there is much interspecific and spatial heterogeneity in which resources are partitioned and in the contributing environmental factors. Overall, we lack a general understanding of how stable coexistence is maintained for particular groups of organisms. Thus, we studied how climate relates to temporal acoustic partitioning in two frog species, Pseudacris sierra and Anaxyrus boreas at Jasper Ridge Biological Preserve - 'Ootchamin 'Ooyakma in Woodside, USA. We predicted that P. sierra prefers cooler temperatures, greater humidity, less wind, and less ultraviolet radiation relative to A. boreas. We collected climatic data and a total 1,380 hours of audio from 3PM to 1AM from January to June of 2022. We then trained a convolutional neural network model to identify our study species with 97.63% testing accuracy and manually estimated the model’s precision and true positive and false negative rates which showed adequate statistical properties. Next, we used a zero-inflated generalized linear mixed model to determine the climatic factors influencing overall and relative amphibian activity at Jasper Ridge. We found warmer temperatures and less wind were associated with overall calling activity, while only UV index affected the relative call abundance of P. sierra and A. boreas. P. sierra was unaffected by UV index while A. boreas calling activity showed a positive relationship with UV index. These results indicate sunlight and diel activity (diurnality and nocturnality) are the primary drivers of temporal acoustic partitioning in this system. We also describe how interspecific male-male competition and wind may result in signal interference which indirectly reduces sexual conflict by limiting access to conspecific females, increasing female fitness in a frequency-dependent fashion, thus promoting coexistence. Finally, we discuss the importance of noise and light pollution in relation to species coexistence in urban environments and describe several ways to improve signal-to-noise ratios for machine learning applications. [link to publication: https://doi.org/doi:10.32942/X2NK71 ]