Production voice agents hear words but miss how they're said.

arXiv 2606.26083 tested four leading real-time voice systems, including OpenAI's realtime stack, and found they transcribe lexical content well but largely ignore tone, emphasis, and emotion. The same week, SpeechEQ introduced an "emotional intelligence quotient" benchmark scoring exactly that paralinguistic competence. Two papers, one message: the agent hears but doesn't listen. If you're shipping voice, this is a concrete reliability gap that demos hide. A support agent that can't tell the difference between a calm customer and a furious one is going to make the furious one angrier.