Abstract The Nancy Grace Roman Space Telescope (Roman) is NASA’s next astrophysics flagship mission, expected to launch in late 2026. As one of Roman’s core community science surveys, the Galactic Bulge Time Domain Survey (GBTDS) will collect photometric and astrometric data for over 100 million stars in the Galactic bulge in order to search for microlensing planets. To assess the potential with which Roman can detect exoplanets via transit, we developed and conducted pixel-level simulations of transiting planets in the GBTDS. From these simulations, we predict that Roman will find between ∼60,000 and ∼200,000 transiting planets—over an order of magnitude more planets than are currently known. While the majority of these planets will be giants (R _p > 4R _⊕) on close-in orbits (a < 0.3 au), the yield also includes between ∼7000 and ∼12,000 small planets (R _p < 4R _⊕). The yield for small planets depends sensitively on the observing cadence and season duration, with variations on the order of ∼10%–20% for modest changes in either parameter, but is generally insensitive to the trade between surveyed area and cadence given constant slew/settle times. These predictions depend sensitively on the Milky Way’s metallicity distribution function, highlighting an opportunity to significantly advance our understanding of exoplanet demographics, in particular across stellar populations and Galactic environments.