在AI技术日新月异的今天，OpenAI再次引领潮流，于近日凌晨正式推出了专为开发人员设计的语音转语音模型——GPT-RealTime。与此同时，OpenAI还对其API功能进行了全面升级，新增了远程MCP服务器支持、图像输入功能以及SIP电话呼叫支持。 据OpenAI官方介绍，GPT-RealTime ...

Earlier this month OpenAI rolled out its new Realtime Voice API, an exciting advancement for developers aiming to bring interactivity and responsiveness to their applications. If you’re curious about ...

Agora's Conversational AI Engine offers key enhancements to the Realtime API for more natural communication and interaction. This milestone builds on Agora's partnership with OpenAI, as the Realtime ...

Integration of OpenAI with Twilio’s Communications APIs Will Enable Over 300,000 Customers and more than 10 Million Developers to Create Compelling Voice Experiences SAN FRANCISCO--(BUSINESS ...

在模型方面，全新的实时模型gpt-realtime-1.5及其配套音频模型已正式发布。它们的核心目标是提高语音指令的可靠性。根据OpenAI的内部测试数据，新模型在数字和字母的转录准确率方面提高了约10%，逻辑音频任务的准确率提高了5%，指令执行的准确率也提高了7%，有效解决了AI在听取关键短语或执行复杂语音指令时出现偏差的问题。

OpenAI 指出，这一改进对于需要频繁调用大量工具的复杂 AI 代理尤为关键，能够将其运行速度直接提升 20% 到40% 。这两项更新不仅让 AI 的“听力”更敏锐，更让其“行动”效率迈向了全新的台阶。

If you are interested in building your very own AI voice agent using the new OpenAI Real-Time API. You might be interested in a new guide by Bart Slodyczka which takes you through the essential stages ...

Agora Launches Conversational AI SDK, Integrated with OpenAI's Realtime API to Power the Evolution of Natural, Voice-Driven AI Experiences "Real-time conversational AI is the next step in helping ...

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...

eSpeaks’ Corey Noles talks with Rob Israch, President of Tipalti, about what it means to lead with Global-First Finance and how companies can build scalable, compliant operations in an increasingly ...

OpenAI is rolling out a new suite of APIs and tools designed to help developers and enterprises build AI-powered agents more efficiently. These are delivered atop some of the very same technology ...

Application developers who access OpenAI through its long-running API will now have access to the company’s latest full o1 model, rather than the months-old o1-preview. The upgrade is one of a number ...