Voice AI has gotten very good over the past few years, but it still suffers from a bit of an uncanny valley problem.
Why listen
It goes beyond the title with direct discussion of know, think, it's, including: Humans are remarkably sensitive to the subtle things that make a conversation feel natural or not.
Key takeaways
01A little too much latency, an interruption handled awkwardly, the wrong tone or emotional response, and suddenly the illusion breaks
02Our conversation explores what it takes to build these systems, from the models and inference infrastructure needed to make voice work in real time, to emotional intelligence, and
03And so I think what this is converging to is that you'll be talking to an AV agent that looks and feels like a human
Best for
research-minded practitioners comparing model behavior