Expired50% confidenceFactExact time
OpenAI's new voice assistant can simulate non-verbal cues during conversation, including pauses, hesitation, self-correction, slight throat-clearing, and a tone of resignation.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/22/2026
First Seen
Valid until: 10/20/2026(expired)
Sources
Related Claims
UnverifiedOpenAI's latest voice model can listen and speak simultaneously, achieving nearly zero-latency two-way conversation82% similarUnverifiedMost previous voice assistants used a half-duplex mode, which was essentially a walkie-talkie-style turn-taking interaction that required waiting for the user to finish speaking before responding.77% similarUnverifiedThe new voice model supports users interrupting the AI at any time, with the model instantly stopping and redirecting to a new topic, enabling low-latency interaction.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/587851API
curl https://kongchang.com/api/v1/knowledge/claims/587851MCP
get_claim(id=587851)