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新版语音助手能够在对话中模拟停顿、迟疑、自我修正、轻微清嗓子和无奈语气等非语言信号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)