{
  "schema_version": "1.1",
  "id": "archive:https://vercel.com/blog/elevenlabs-on-ai-gateway",
  "slug": "elevenlabs-on-ai-gateway-0z8kb7d",
  "url": "https://feed7.dev/p/elevenlabs-on-ai-gateway-0z8kb7d",
  "title": "ElevenLabs on AI Gateway",
  "why_included": "Vercel AI Gateway adds 14 ElevenLabs models across transcription, realtime voice, music, effects, and dialogue under one API key, with shared cost and trace views. Realtime models use semantic VAD, not server VAD.",
  "summary": "AI Gateway adds **14 ElevenLabs models** across six audio types: transcription, streaming speech, realtime voice, music, sound effects, and multi-voice dialogue. Requests share one gateway key and common usage, cost, and trace views. Realtime voice models use one WebSocket session; the streaming pipeline can instead keep transcription, language, and speech models swappable.",
  "practical_implication": "Builders can choose between a modular speech pipeline and a single realtime model, and route audio alongside other models through the same gateway. Browser realtime setup requires a short-lived token, and the models support **semantic VAD** but not server VAD.",
  "agent_context": "AI Gateway adds **14 ElevenLabs models** across six audio types: transcription, streaming speech, realtime voice, music, sound effects, and multi-voice dialogue. Requests share one gateway key and common usage, cost, and trace views. Realtime voice models use one WebSocket session; the streaming pipeline can instead keep transcription, language, and speech models swappable.\n\nBuilders can choose between a modular speech pipeline and a single realtime model, and route audio alongside other models through the same gateway. Browser realtime setup requires a short-lived token, and the models support **semantic VAD** but not server VAD.\n\nThe listed 50% discount runs through **November 9**. The material does not provide comparative latency, quality, or cost results, so model selection still needs workload-specific evaluation.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/blog/elevenlabs-on-ai-gateway",
    "published_at": "2026-10-27T07:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "infra",
  "domains": [
    "audio"
  ],
  "topics": [
    "gateways",
    "observability",
    "model-selection"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The listed 50% discount runs through **November 9**. The material does not provide comparative latency, quality, or cost results, so model selection still needs workload-specific evaluation."
  ],
  "connected_context": {
    "meaning": "This expands AI Gateway audio from individual speech routes to a broad ElevenLabs menu spanning transcription, realtime voice, music, effects, and dialogue. It also makes the architecture choice explicit: use one realtime session or keep transcription, language, and speech models swappable. The shared gateway provides common usage and trace views, but the source gives no comparative results for choosing a model.",
    "corpus_size": 944,
    "generated_at": "2026-10-28T11:07:55.056Z",
    "connections": [
      {
        "title": "Gemini 3.8 text-to-speech models now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/gemini-3-8-text-to-speech-models-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/gemini-3-8-text-to-speech-models-now-available-on-ai-gateway-1ur27ch",
        "reason": "Both add speech-generation choices to AI Gateway, but Gemini divides TTS by generation style while ElevenLabs offers a wider audio surface and a realtime-versus-modular pipeline choice; neither source establishes a workload-independent winner."
      },
      {
        "title": "Routing rules now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/ai-gateway-routing-rules",
        "feed7_url": "https://feed7.dev/p/ai-gateway-routing-rules-024ifzc",
        "reason": "Routing rules provide a gateway-level way to redirect or deny model choices, which could operationalize changes between the modular and realtime audio paths without changing application code."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-10-27T07:00:00.000Z",
  "modified_at": "2026-10-27T07:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/elevenlabs-on-ai-gateway-0z8kb7d",
    "json": "https://feed7.dev/p/elevenlabs-on-ai-gateway-0z8kb7d.json",
    "markdown": "https://feed7.dev/p/elevenlabs-on-ai-gateway-0z8kb7d.md"
  }
}