About the Study: Can automated analysis of 1 to 2 minutes of connected speech yield interpretable profiles that distinguish primary progressive aphasia (PPA) variants and reflect neuroanatomical and neuropathologic substrates? In this cross-sectional study of 214 participants, Lasso multinomial modeling generated variant-specific speech profile scores that differentiated nonfluent PPA, logopenic PPA, and semantic PPA with high overall performance and showed expected atrophy associations. In an autopsy-confirmed subset, speech profiles also discriminated common neuropathologic classes. Results suggest that brief automated speech profiling may enable scalable, interpretable support for PPA differential diagnosis and monitoring.