OpenAI 开放 GPT-Live-1 全双工语音 API
原标题：OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time
AI 摘要
OpenAI 将 GPT-Live-1 语音模型以 API 形式开放给开发者，该模型支持全双工（同时听说），已在 ChatGPT 内部运行。开发者可将其与不同后端模型搭配，按任务匹配推理深度、速度与成本，定价为每分钟 0.05 美元。Yelp 已用其处理电话预订并报告通话处理改善。OpenAI 基准显示该模型在全双工交互、轮次延迟、工具调用准确率等指标上明显优于前代 GPT-Realtime-2.1。
正文节选
OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time OpenAI is making GPT-Live-1 available to developers as an API. The speech model can listen and talk at the same time, a feature known as "full-duplex," and is already running inside ChatGPT. Developers can pair it with different backend models depending on the task, matching reasoning depth, speed, and cost to each use case. At $0.05 per minute, it's not cheap. Yelp is using the model for phone-based reserva