All structures within living cells must form at the right time and place. This includes condensates such as the nucleolus, Cajal bodies and stress granules, which form via liquid–liquid phase separation of biomolecules, particularly proteins enriched in intrinsically disordered regions (IDRs)^,. In non-living systems, the initial stages of nucleated phase separation arise when thermal fluctuations overcome an energy barrier due to surface tension. This phenomenon can be modelled by classical nucleation theory (CNT), which describes how the rate of droplet nucleation depends on the degree of supersaturation, whereas the location at which droplets appear is controlled by interfacial heterogeneities^,. However, it remains unknown whether this framework applies in living cells, owing to the multicomponent and highly complex nature of the intracellular environment, including the presence of diverse IDRs, whose specificity of biomolecular interactions is unclear^{, , –}. Here we show that despite this complexity, nucleation in living cells occurs through a physical process similar to that in inanimate materials, but the efficacy of nucleation sites can be tuned by their biomolecular features. By quantitatively characterizing the nucleation kinetics of endogenous and biomimetic condensates in living cells, we find that key features of condensate nucleation can be quantitatively understood through a CNT-like theoretical framework. Nucleation rates can be substantially enhanced by compatible biomolecular (IDR) seeds, and the kinetics of cellular processes can impact condensate nucleation rates and specificity of location. This quantitative framework sheds light on the intracellular nucleation landscape, and paves the way for engineering synthetic condensates precisely positioned in space and time.