{
  "schema_version": "1.1",
  "id": "s4:https://vercel.com/changelog/gemini-3-8-text-to-speech-models-now-available-on-ai-gateway",
  "slug": "gemini-3-8-text-to-speech-models-now-available-on-ai-gateway-1ur27ch",
  "url": "https://feed7.dev/p/gemini-3-8-text-to-speech-models-now-available-on-ai-gateway-1ur27ch",
  "title": "Gemini 3.8 text-to-speech models now available on AI Gateway",
  "why_included": "Vercel AI Gateway now exposes two Gemini 3.8 TTS models for multilingual speech, separating high-volume generation from prompt-driven voice design.",
  "summary": "AI Gateway now offers **Gemini 3.8 Flash-Lite TTS** and **Gemini 3.8 Flash TTS**. Both generate speech in **more than 100 languages** and support long narration and two-speaker dialogue.",
  "practical_implication": "Use Flash-Lite for high-volume output with tone, pacing, and line-level controls. Choose Flash when an agent needs prompt-driven voice or character design, including acting cues, accents, and reactions.",
  "agent_context": "AI Gateway now offers **Gemini 3.8 Flash-Lite TTS** and **Gemini 3.8 Flash TTS**. Both generate speech in **more than 100 languages** and support long narration and two-speaker dialogue.\n\nUse Flash-Lite for high-volume output with tone, pacing, and line-level controls. Choose Flash when an agent needs prompt-driven voice or character design, including acting cues, accents, and reactions.\n\nThe material describes capabilities and gateway features such as routing, request-level usage tracking, and provider keys, but provides no pricing, latency, quality evaluation, or language-by-language results.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/gemini-3-8-text-to-speech-models-now-available-on-ai-gateway",
    "published_at": "2026-09-23T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "infra",
  "domains": [
    "audio"
  ],
  "topics": [
    "generative-media",
    "gateways",
    "model-selection"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The material describes capabilities and gateway features such as routing, request-level usage tracking, and provider keys, but provides no pricing, latency, quality evaluation, or language-by-language results."
  ],
  "connected_context": {
    "meaning": "This turns the Gateway’s audio offering into a clearer output-side choice: Flash-Lite targets controlled volume production, while Flash targets prompt-shaped performance and character work. It complements existing transcription routes and overlaps Fish Audio’s speech generation, but the supplied record still supports only integration-level evaluation—not a quality, latency, or cost preference.",
    "corpus_size": 875,
    "generated_at": "2026-09-25T09:06:46.953Z",
    "connections": [
      {
        "title": "Fish Audio models now available on Vercel AI Gateway for free",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/fish-audio-models-now-available-on-ai-gateway-for-free",
        "feed7_url": "https://feed7.dev/p/fish-audio-models-now-available-on-ai-gateway-for-free-0rw6kco",
        "reason": "Fish Audio is the closest existing speech-generation route, so Gemini 3.8 creates a direct workload-specific alternative while lacking the temporary free-path and billing behavior documented for Fish."
      },
      {
        "title": "Gemini 3.5 Transcribe now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/gemini-3-5-transcribe-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/gemini-3-5-transcribe-now-available-on-ai-gateway-08us8jk",
        "reason": "Gemini 3.5 Transcribe supplies the voice-input side that these TTS models lack, making the two signals complementary components for multilingual conversational audio pipelines."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-09-23T00:00:00.000Z",
  "modified_at": "2026-09-23T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/gemini-3-8-text-to-speech-models-now-available-on-ai-gateway-1ur27ch",
    "json": "https://feed7.dev/p/gemini-3-8-text-to-speech-models-now-available-on-ai-gateway-1ur27ch.json",
    "markdown": "https://feed7.dev/p/gemini-3-8-text-to-speech-models-now-available-on-ai-gateway-1ur27ch.md"
  }
}