Gemini 3.8 Live with Live Avatar gives Google’s AI a face

Gemini 3.8 Live 推出 Live Avatar，赋予谷歌 AI 一张“脸”

Google’s new Gemini 3.8 Live update lets users have conversations with the model while watching an animated AI persona respond in real time. The “Live Avatar” will lip-sync and show different facial expressions during conversations, but it’s currently only available to Gemini Enterprise customers. 谷歌最新的 Gemini 3.8 Live 更新让用户在与模型对话时，能够看到一个动画 AI 形象进行实时响应。这个“Live Avatar”（实时虚拟形象）在对话过程中可以实现口型同步并展现出不同的面部表情，但目前仅向 Gemini 企业版客户开放。

As noted by Google, Live Avatar can transition between the 97 languages it supports “without degrading video fidelity or introducing visual drift.” One video shared by Google shows its Live Avatar talking in English and Japanese, with its mouth animation lining up with what it’s saying in both languages. It can also pull up information on-screen while it talks. 正如谷歌所指出的，Live Avatar 可以在其支持的 97 种语言之间进行切换，且“不会降低视频保真度或产生视觉漂移”。谷歌分享的一段视频展示了其 Live Avatar 分别用英语和日语交谈，其口型动画与两种语言的语音内容均能完美匹配。此外，它还可以在说话的同时在屏幕上调出相关信息。

The launch of Live Avatar comes about a week after Google revealed its new Gemini 3.8 Live model, which the company says “processes visual inputs in near real-time.” Though Google will offer a library of preset avatars for customers to choose from, it will also allow organizations to create their own. Google says output from its Live Avatar comes with its invisible SynthID watermark alongside safeguards to “respect identity.” Live Avatar 的发布距离谷歌推出全新的 Gemini 3.8 Live 模型仅过去一周左右，谷歌称该模型能够“近乎实时地处理视觉输入”。虽然谷歌将提供一个预设虚拟形象库供客户选择，但它也允许各机构创建自己的专属形象。谷歌表示，Live Avatar 的输出内容带有隐形的 SynthID 水印，并配有旨在“尊重身份”的安全防护措施。