Understanding whether and how environmental conditions may impact food web structure at a global scale is central to our ability to predict how food webs will respond to climate change. However, such an understanding is nascent. Using the best resolved available food webs to date, I address whether latitude, temperature, or both, explain the number of species and feeding interactions, the proportion of basal and top species, as well as the degree of omnivory, connectance and the number of trophic levels across food webs. I found that temperature is a more parsimonious predictor of food web structure than latitude. Temperature directly reduces the number of species, the proportion of basal species and the number of interactions while it indirectly increases omnivory levels, connectance and trophic level through its direct effects on the fraction and number of basal species. While direct impacts of temperature are routinely taken into account to predict how ecosystems may respond to global climate change, indirect effects have been largely overlooked. These results thus suggest that food webs may be affected by a combination of biotic and abiotic conditions, both directly and indirectly, in a changing world.