Event ·Official first-hand

OpenAI 发布 GPT-Live-1.1 语音模型 API 版本

OpenAI 通过开发者账号宣布 GPT-Live-1.1 上线 API。该语音模型在跨语言场景下的口音更自然、更一致,解决了此前语音输出在不同语言间切换时口音突变的常见问题。新版本还引入了 standby 待机选项,用于降低空闲时段的调用成本,并进一步提升了任务完成的可靠性。对于在 API 上搭建实时语音交互的开发者而言,成本结构与口音稳定性是直接影响产品体验的两项关键改动。

Current read

做语音应用的朋友可以看看:OpenAI 这次更新的 GPT-Live-1.1 口音更稳了,还加了 standby 待机模式省空闲成本,做实时对话产品的可以直接在 API 里换上试试。

11 sources68° AI heatLast updated 2026/11/19 20:00:32

Evidence

11 sources
Primary source@OpenAIDevs
View source
Related source 1TestingCatalog
View source
Related source 2Databricks
View source
Related source 4OpenRouter
View source
Related source 5Artificial Analysis
View source
Related source 6Sam Altman
View source
Related source 7The Rundown AI
View source
Related source 8Microsoft AI
View source
Related source 9Guillermo Rauch
View source
Related source 10marktechpost
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.