Verified70% confidenceFactTime unknown
GPT-4o released by OpenAI in 2024 achieved low-latency real-time voice conversation, with end-to-end latency reduced to under 320 milliseconds.
4
Sources
70%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOpenAI推出GPT Real-Time 2.1及其Mini版实时语音模型，通过API开放，借助新缓存机制可让P95延迟至少降低25%80% similarVerifiedOpenAI released the GPT-4o voice mode in 2024.78% similarUnverifiedgpt-transcribe is a next-generation transcription model released by OpenAI in 2025, offering improvements over the older Whisper series in multilingual recognition accuracy and low-latency scenarios.71% similarVerifiedMultimodal models such as GPT-4o already support native processing of real-time audio.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/8117API
curl https://kongchang.com/api/v1/knowledge/claims/8117MCP
get_claim(id=8117)