Deepgram Nova-3
Speech model with SONAR embedding space
Episodes
-
#5959: What RTF Actually Tells You About Speech ModelsAccuracy gets the headlines, but speed decides what ships. How RTF, latency percentiles, and memory shape real ASR deployments. -
#1585: The End of the Digital Sandwich: How AI Learns to Speak Your LanguageExplore how new omnilingual models are collapsing the Tower of Babel, moving from rigid translation to a universal understanding of human speech. -
#1564: The Death of the Cascaded PipelineForget basic transcription. Explore how native omni-modal models are capturing the "soul" of speech with near-instant latency.