{
  "schema_version": "1.1",
  "id": "s4:https://vercel.com/changelog/grok-voice-think-fast-2-0-now-available-on-ai-gateway",
  "slug": "grok-voice-think-fast-2-0-now-available-on-ai-gateway-1dacr27",
  "url": "https://feed7.dev/p/grok-voice-think-fast-2-0-now-available-on-ai-gateway-1dacr27",
  "title": "Grok Voice Think Fast 2.0 now available on AI Gateway",
  "why_included": "Grok Voice Think Fast 2.0 brings speech-to-speech reasoning and earlier tool calls to Vercel’s realtime API, with server-minted tokens keeping gateway keys off clients.",
  "summary": "**Grok Voice Think Fast 2.0** is available through AI Gateway as an audio-in, audio-out model. Vercel says it reasons while speaking, uses fewer reasoning tokens than its predecessor, and handles background noise and telephony compression.",
  "practical_implication": "Voice-agent builders can call **xai/grok-voice-think-fast-2.0** through the AI SDK realtime API. Mint a short-lived token on the server so the gateway API key never reaches browser or app clients.",
  "agent_context": "**Grok Voice Think Fast 2.0** is available through AI Gateway as an audio-in, audio-out model. Vercel says it reasons while speaking, uses fewer reasoning tokens than its predecessor, and handles background noise and telephony compression.\n\nVoice-agent builders can call **xai/grok-voice-think-fast-2.0** through the AI SDK realtime API. Mint a short-lived token on the server so the gateway API key never reaches browser or app clients.\n\nThe claimed improvements in reasoning, transcription, and conversation come without benchmark figures in the material. Earlier tool calls are described as common, not guaranteed, so test interruption timing and noisy-audio behavior on your own workload.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/grok-voice-think-fast-2-0-now-available-on-ai-gateway",
    "published_at": "2026-07-29T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "model",
  "domains": [
    "audio"
  ],
  "topics": [
    "reasoning",
    "tool-use",
    "generative-media"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The claimed improvements in reasoning, transcription, and conversation come without benchmark figures in the material. Earlier tool calls are described as common, not guaranteed, so test interruption timing and noisy-audio behavior on your own workload."
  ],
  "connected_context": {
    "meaning": "This extends the candidate model-selection landscape into realtime, bidirectional voice, where latency, interruption timing, noisy input, and client credential exposure matter alongside reasoning quality. The claims do not justify replacing existing routes without workload tests: early tool calls are only typical, improvements lack benchmark figures, and short-lived server-minted tokens are a deployment prerequisite.",
    "corpus_size": 297,
    "generated_at": "2026-07-31T10:06:09.027Z",
    "connections": [
      {
        "title": "X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2607.21550v1",
        "feed7_url": "https://feed7.dev/p/2607-21550v1-1j7d28n",
        "reason": "X³-OPD supplies reinforcing research context that audio reasoning depends on grounding in acoustic events, prosody, and dialogue—the kinds of conditions the voice model’s noise claims should be tested against."
      },
      {
        "title": "Grok 4.5 now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/grok-4-5-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/grok-4-5-now-available-on-ai-gateway-12uqu6j",
        "reason": "Grok 4.5 offers adjustable text-and-image reasoning, while Think Fast 2.0 adds a realtime audio route whose selection must account for conversational latency and interruption behavior."
      },
      {
        "title": "Inkling Small from Thinking Machines is now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/inkling-small-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/inkling-small-now-available-on-ai-gateway-1a9781l",
        "reason": "Both expose efficiency-oriented model choices through AI Gateway, but the voice model shifts evaluation from adjustable thinking effort to end-to-end audio quality and realtime behavior."
      },
      {
        "title": "Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2607.02504v1",
        "feed7_url": "https://feed7.dev/p/2607-02504v1-004kp37",
        "reason": "The speaker-recognition result shows a separate audio workload where reasoning and multimodal tools outperform acoustic baselines, reinforcing that audio agents should be evaluated on task outcomes rather than transcription claims alone."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-07-29T00:00:00.000Z",
  "modified_at": "2026-07-29T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/grok-voice-think-fast-2-0-now-available-on-ai-gateway-1dacr27",
    "json": "https://feed7.dev/p/grok-voice-think-fast-2-0-now-available-on-ai-gateway-1dacr27.json",
    "markdown": "https://feed7.dev/p/grok-voice-think-fast-2-0-now-available-on-ai-gateway-1dacr27.md"
  }
}