OpenAI 发布语音到语音模型 gpt-realtime-2。开发者 @kwindla 将其用作 Gradient Bang 游戏船舶 AI 的大脑，并给出未剪辑的语音到语音响应和工具调用录像，展示模型在包含复杂系统指令与频繁工具调用的智能体中的交互表现。他提到子代理任务由 gpt-5.2 medium 执行，并剪掉了子代理开始执行任务后的片段。
OpenAI shipped a new speech-to-speech model today: gpt-realtime-2
This is the first speech-to-speech model good enough to use in my voice agents that do "real work."
Or real play, for that matter. Here's gpt-realtime-2 as the brain of the ship AI in Gradient Bang.
The voice-to-voice response and tool calling times here are unedited, so you can see exactly what the interaction with the model is like in an agent with a very complex system instruction and frequent tool calls.
(I did clip out the subagent task execution segments, after gpt-realtime-2 starts a subagent via a tool call. Subagents in this config used gpt-5.2 "medium" effort.)
Video
来源：@kwindla · x.com