Expired60% confidenceReleaseExact time
OpenAI's latest voice model can listen and speak simultaneously, achieving nearly zero-latency two-way conversation
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
Valid until: 10/18/2026(expired)
Sources
Related Claims
UnverifiedOpenAI's new voice assistant can simulate non-verbal cues during conversation, including pauses, hesitation, self-correction, slight throat-clearing, and a tone of resignation.82% similarUnverifiedOpenAI's new model adopts an end-to-end voice architecture that directly takes audio as input and output, skipping the intermediate text conversion step.79% similarUnverifiedState-of-the-art real-time speech transcription latency is approximately 200–400 milliseconds, with mainstream industry solutions including OpenAI's Whisper, Google Speech-to-Text, and AssemblyAI.79% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/568264API
curl https://kongchang.com/api/v1/knowledge/claims/568264MCP
get_claim(id=568264)