“when I was speaking um it wasn't there was no visual feedback um uh making it clear that my voice is actually recognized by the microphone um and then similarly when the uh voice was answering um there was no sort of like visual indication um that that's what's happening” — Raphael Shad
“important I guess to kind of pair multimodal cues um so not just rely on voice um in these type of scenarios where you do have a screen uh on the phone that would be a different scenario” — Raphael Shad
Voice AI interfaces are achieving human-like interaction quality, enabling natural conversations with software. However, challenges remain around latency, interruption handling, and multimodal feedback.