Gemini 3.5 Live Translate Preview

低延迟音频到音频模型，用于口语对话的实时翻译。

Googlegemini-3.5-live-translate-preview报告数据错误

规格

上下文: —
最大输出: 65.5K
输入价: $3.5/ 百万 Token
输出价: $21/ 百万 Token
发布日期: —

上下文

上下文: —
最大输入: 131.1K
最大输出: 65.5K

价格 · USD / 百万 Token

输入: $3.5
输出: $21
缓存读取: —
缓存写入: —

输入输出

输入: 音频
输出: 文本音频

API

接口类型: realtime

思考

支持思考: 不支持

源信息

状态: 预览
发布日期: —
知识截止: 2025-01

能力

官方未公布

调用方式

googlemodel = gemini-3.5-live-translate-preview

JSON

gemini-3.5-live-translate-preview.json

{
  "id": "gemini-3.5-live-translate-preview",
  "object": "model",
  "created": null,
  "owned_by": "google",
  "name": "Gemini 3.5 Live Translate Preview",
  "api": {
    "types": [
      "realtime"
    ]
  },
  "limits": {
    "context": null,
    "input": 131072,
    "output": 65536
  },
  "modalities": {
    "input": [
      "audio"
    ],
    "output": [
      "text",
      "audio"
    ]
  },
  "reasoning": {
    "supported": false,
    "efforts": []
  },
  "pricing": {
    "currency": "USD",
    "unit": "1M_tokens",
    "input": 3.5,
    "output": 21,
    "cache_read": null,
    "cache_write": null
  },
  "features": [],
  "info": {
    "status": "preview",
    "release_date": null,
    "knowledge_cutoff": "2025-01",
    "description": "Low-latency audio-to-audio model for real-time translation of spoken conversations.",
    "docs": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-live-translate-preview",
    "verified_at": "2026-10-11"
  }
}

官方来源

Gemini 3.5 Live Translate Preview | Gemini APIai.google.dev2026-10-10 Models | Gemini APIai.google.dev2026-10-10 Pricing | Gemini APIai.google.dev2026-10-11 Deprecations | Gemini APIai.google.dev2026-10-11 Live API | Gemini APIai.google.dev2026-10-10 Gemini 3.5 Audio - Model Card — Google DeepMinddeepmind.google2026-10-11