Google DeepMind 推出带 Live Avatar 的 Gemini 3.8 Live
原标题：Introducing Gemini 3.8 Live with Live Avatar
AI 摘要
Google DeepMind 发布 Gemini 3.8 Live with Live Avatar，在原生实时对话模型基础上加入近实时视频生成能力，实现带口型同步、自然表情和流畅轮次切换的视觉化虚拟形象。该功能支持异步工具调用、97 种语言的原生语音到语音同步，并可通过参考图定制品牌形象，即日起在 Gemini Enterprise 上线。所有输出均嵌入 SynthID 水印以提升 AI 生成内容的可检测性。
正文节选
Introducing Gemini 3.8 Live with Live Avatar Building on the momentum of last week's Gemini 3.8 Live launch, today we are excited to introduce Gemini 3.8 Live with Live Avatar — bringing near real-time visual presence to our native live dialogue models. By pairing near real-time video generation with speech, the Live Avatar feature creates an experience that listens, sees, and speaks with a dynamic visual persona. With precise lip-syncing, natural expressions, and fluid turn-taking, Live Avatar