gpt-realtime

About this tag
The gpt-realtime tag covers discussions about OpenAI's real-time speech-to-speech model, now generally available on Azure AI Foundry via the Real-time API. Topics include low-latency conversational agents, multimodal voice interactions, and voice-first prompt engineering techniques distinct from text-only models. Content also touches on the broader OpenAI-Microsoft relationship, including API access and restructuring negotiations. The tag is relevant for developers and enterprises building speech-to-speech experiences with Microsoft's Azure AI platform.
  1. GPT-Realtime on Azure AI Foundry: End-to-End S2S Speech with Multimodal Voice

    Microsoft has pushed a major real‑time audio milestone into the Azure stack: gpt‑realtime, a speech‑to‑speech (S2S) model optimized for low‑latency, natural‑sounding conversational agents, is now generally available on Azure AI Foundry and accessible through the Real‑time API for developers and...
  2. Voice-First Real-Time Prompting with GPT-Realtime

    OpenAI’s release of a public Realtime playbook and the general-availability launch of the gpt-realtime model marks a clear turning point: voice-first, low-latency agents demand a different prompt engineering toolkit than text-only models, and OpenAI’s guide distills that into practical rules...
  3. OpenAI–Microsoft Restructuring Delayed Over API, IP and AGI Clause Talks

    OpenAI’s highly anticipated corporate restructuring has been pushed off the immediate calendar as last‑ditch negotiations with Microsoft over API access, intellectual property (IP) rights and a disputed “AGI clause” remain unresolved, forcing a delay that could push the overhaul into next year...