Soil respiration (Rs), the soil‐to‐atmosphere CO2 flux produced by microbes and plant roots, is a critical but uncertain component of the global carbon cycle. Our current understanding of the variability and dynamics is limited by the coarse spatial resolution of existing estimates. We predicted annual Rs and associated uncertainty across the world at 1‐km resolution using a quantile regression forest algorithm trained with observations from the global Soil Respiration Database spanning from 1961 to 2011. This model yielded a global annual Rs estimate of 87.9 Pg C/year with an associated global uncertainty of 18.6 (mean absolute error) and 40.4 (root mean square error) Pg C/year. The estimated annual heterotrophic respiration (Rh), derived from empirical relationships with Rs, was 49.7 Pg C/year over the same period. Predicted Rs rates and associated uncertainty varied widely across vegetation types, with the greatest predicted rates of Rs in evergreen broadleaf forests (accounting for 20.9% of global Rs). The greatest prediction uncertainties were in northern latitudes and arid to semiarid ecosystems, suggesting that these areas should be targeted in future measurement campaigns. This study provides predictions of Rs (and associated prediction uncertainty) at unprecedentedly high spatial resolution across the globe that could help constrain local‐to‐global process‐based models. Furthermore, it provides insights into the large variability of Rs and Rh across vegetation classes and identifies regions and vegetation types with poor model performance that should be prioritized for future data collection. Plain Language Summary Soils emit large amounts of carbon dioxide to the atmosphere every year via the process of soil respiration, which greatly exceeds emissions from human sources. However, rates of soil respiration are highly variable in space, which limits our ability to balance global carbon budgets and forecast climate change. We used a novel application of a machine learning approach to predict annual rates of soil respiration at high resolution (1 km) across the globe and examined spatial patterns of the associated uncertainty of these predictions. Predictions were made based on how observations of soil respiration were related to climate (annual temperature and annual and seasonal precipitation) and vegetation information. Predicted annual soil respiration and prediction uncertainty varied across ecosystem types and regions. Our predictions suggest that evergreen tropical forests dominate global annual soil respiration emissions. Dryland, wetland, and cold ecosystems had the highest associated prediction uncertainties, suggesting that future soil respiration measurements would be especially useful in these areas. The high spatial resolution of our predictions will help researchers studying the carbon cycle at local to global scales. Key Points A high spatial resolution machine learning approach was used for estimating soil respiration across the world Predictions of soil respiration varied widely across ecosystem classes, and allowed for suitable estimates of heterotrophic respiration Associated prediction uncertainty was highest in high latitudes and data scarce regions, which should be targets for future measurements