Expired50% confidenceFactExact time
OpenAI's new model adopts an end-to-end voice architecture that directly takes audio as input and output, skipping the intermediate text conversion step.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
Valid until: 10/18/2026(expired)
Sources
Related Claims
UnverifiedOpenAI推出了名为Voice Engine的语音克隆技术81% similarUnverifiedOpenAI's latest voice model can listen and speak simultaneously, achieving nearly zero-latency two-way conversation79% similarUnverifiedEnd-to-end native architectures directly process audio input and output audio without relying on intermediate conversion steps, preserving richer acoustic features.78% similarVerifiedEnd-to-end voice models take audio directly as input and output, performing understanding and generation at the audio token level while preserving acoustic features such as intonation, speaking rate, sighs, and laughter.78% similarUnverifiedThe new end-to-end voice model is trained directly at the audio level, without first converting speech to text, and can directly capture acoustic features and emotions.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/567868API
curl https://kongchang.com/api/v1/knowledge/claims/567868MCP
get_claim(id=567868)