{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiecu7wqenjknvfcuxan4kmoeoqytqw4vflr5ievkiqvaymcgntxfy",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mlqne744myx2"
  },
  "path": "/t/voice-ai-people-are-you-using-agents-sdk-on-prod/1380748#post_3",
  "publishedAt": "2026-05-13T14:59:58.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@f10w",
    "https://openai.com/index/the-next-evolution-of-the-agents-sdk/",
    "New Realtime Voice Models in the API",
    "Announcements",
    "Realtime and audio",
    "Using realtime models",
    "Voice agents"
  ],
  "textContent": "Hi @f10w!\n\nI am probably biased here, but I wanted to add a few details.\n\nThe Agents SDK did get a major recent update, centered on Sandbox Agents, controlled execution environments, memory/resume, and harness customization. The caveat is that this is still version 0.14.0.\n\nJust a few days ago, the default model for realtime agents was updated to the newest model, gpt-realtime-2.\n\nIn the context of using the newest realtime models, I suggest following the best practices guidance. I recently created a list of relevant sources and will link it below.\n\nHope this helps!\n\nhttps://openai.com/index/the-next-evolution-of-the-agents-sdk/\n\nNew Realtime Voice Models in the API Announcements\n\n> Additional Documentation and Guides related to this release: Realtime and audio Updated overview for choosing between voice agents, realtime translation, realtime transcription, and request-based audio APIs. It explicitly routes low-latency voice agents to gpt-realtime-2. Using realtime models New/updated prompting guide for gpt-realtime-2, including reasoning effort, preambles, tool policies, unclear audio handling, exact entity capture, and long-session behavior. Voice agents Updat…",
  "title": "Voice AI people: Are you using Agents SDK on prod?"
}