OpenAI 新出的实时语音模型，延迟砍了至少25%，mini版推理更强还保持原价，做语音agent正合适。
OpenAI 在 API 中新增了 GPT-Realtime-2.1 和 GPT-Realtime-2.1-mini 两个实时模型。GPT-Realtime-2.1-mini 是专为语音设计的迷你推理模型，定价与此前的 gpt-realtime-mini 相同。通过改进缓存，p95 延迟降低了至少 25%。开发者可通过 WebRTC 协议连接使用。
OpenAI Releases GPT-Realtime-2.1 and GPT-Realtime-2.1-mini for Low-Latency Voice Agents in the API
OpenAI added two Realtime models to its API. GPT-Realtime-2.1-mini is a mini reasoning model for voice, priced like the earlier gpt-realtime-mini. OpenAI also cut p95 latency by at least 25% through improved caching. Here is what changed, how pricing compares, and how to connect over WebRTC. The post OpenAI Releases GPT-Realtime-2.1 and GPT-Realtime-2.1-mini for Low-Latency Voice Agents in the API appeared first on MarkTechPost .