{
  "schema_version": "1.1",
  "id": "s4:https://vercel.com/changelog/gpt-live-1-now-available-on-ai-gateway",
  "slug": "gpt-live-1-now-available-on-ai-gateway-18x7ban",
  "url": "https://feed7.dev/p/gpt-live-1-now-available-on-ai-gateway-18x7ban",
  "title": "GPT-Live 1 now available on AI Gateway",
  "why_included": "GPT-Live 1 supports simultaneous listening and speaking plus delegation to a separate text model, enabling interruptible voice agents without coupling conversation and deep work.",
  "summary": "**GPT-Live 1** is available through Vercel AI Gateway as a full-duplex voice model that can listen while speaking. Its **client delegation** lets an application send deeper work to a separately chosen text model while the voice session continues.",
  "practical_implication": "For a voice agent, keep conversational interaction in the live model and explicitly govern delegated tools or text models with permissions, confirmations, and cancellation. Wait for `session-started` before sending audio.",
  "agent_context": "**GPT-Live 1** is available through Vercel AI Gateway as a full-duplex voice model that can listen while speaking. Its **client delegation** lets an application send deeper work to a separately chosen text model while the voice session continues.\n\nFor a voice agent, keep conversational interaction in the live model and explicitly govern delegated tools or text models with permissions, confirmations, and cancellation. Wait for `session-started` before sending audio.\n\nIntegration requires **AI SDK 7**, `@ai-sdk/openai` 4.0.67 or later, and a WebSocket client. Delegated requests are billed separately, voice usage continues during them, and the shown snippets omit several production concerns.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/gpt-live-1-now-available-on-ai-gateway",
    "published_at": "2026-09-17T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "model",
  "domains": [
    "audio"
  ],
  "topics": [
    "generative-media",
    "tool-use",
    "agent-sdks"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "Integration requires **AI SDK 7**, `@ai-sdk/openai` 4.0.67 or later, and a WebSocket client. Delegated requests are billed separately, voice usage continues during them, and the shown snippets omit several production concerns."
  ],
  "connected_context": {
    "meaning": "This turns GPT-Live-1 into a concrete gateway integration and separates continuous conversation from delegated deep work. Relative to modular transcription pipelines, it offers a managed full-duplex loop, but adds concurrent billing and a new authorization boundary around delegated models and tools. The experimental dependencies and omitted production controls keep it an evaluation path, not a default architecture.",
    "corpus_size": 807,
    "generated_at": "2026-09-18T10:05:03.869Z",
    "connections": [
      {
        "title": "Build more natural voice experiences with GPT‑Live‑1 in the API",
        "source_name": "OpenAI",
        "source_url": "https://openai.com/index/introducing-gpt-live-1-in-the-api",
        "feed7_url": "https://feed7.dev/p/introducing-gpt-live-1-in-the-api-13b77cz",
        "reason": "OpenAI establishes the model-level full-duplex voice capability, while Vercel adds the gateway-specific integration contract, delegation behavior, dependencies, and billing consequences."
      },
      {
        "title": "AI Gateway now supports streaming transcription",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/ai-gateway-now-supports-streaming-transcription",
        "feed7_url": "https://feed7.dev/p/ai-gateway-now-supports-streaming-transcription-1sq8mn3",
        "reason": "Streaming transcription represents the modular alternative: it can add voice input to an existing text agent, whereas GPT-Live-1 owns the bidirectional conversational loop and can delegate deeper text work."
      },
      {
        "title": "Grok Voice Think Fast 2.0 now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/grok-voice-think-fast-2-0-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/grok-voice-think-fast-2-0-now-available-on-ai-gateway-1dacr27",
        "reason": "Grok is the closest realtime gateway alternative and reinforces that interruption handling, tool timing, short-lived credentials, and workload tests are now central voice-model selection criteria."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-09-17T00:00:00.000Z",
  "modified_at": "2026-09-17T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/gpt-live-1-now-available-on-ai-gateway-18x7ban",
    "json": "https://feed7.dev/p/gpt-live-1-now-available-on-ai-gateway-18x7ban.json",
    "markdown": "https://feed7.dev/p/gpt-live-1-now-available-on-ai-gateway-18x7ban.md"
  }
}