[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-gemini-3-8-live-avatar":3,"topics-all":38,"news-related-d219ead5-ea5d-4aaa-835e-5ec3cf980856":57},{"id":4,"title":5,"summary":6,"content":7,"original_url":8,"source_id":9,"tags":10,"translations":24,"news_slug":31,"published_at":32,"created_at":33,"modified_at":34,"is_published":35,"publish_type":36,"image_url":14,"view_count":37},"d219ead5-ea5d-4aaa-835e-5ec3cf980856","Gemini Live Avatar:模型直出唇同步数字人","Google 为 Gemini 3.8 Live 推出 Live Avatar:模型直接输出与语音同步的 24FPS 视频流,生成唇形同步、有表情的数字人,支持 97 种语言中途切换和后台异步工具调用,已在 Gemini Enterprise 正式可用,输出全部带 SynthID 隐形水印。","9 月 24 日,Google 在官方博客上线了 Gemini 3.8 Live with Live Avatar:在上周刚发布的实时语音对话模型 Gemini 3.8 Live 之上叠加近实时视频生成,让模型输出一个唇形同步、有表情、能自然接话与让话的数字人形象。由 DeepMind 研究科学家 Shuo-yiin Chang 与 Gemini 工程师 CJ Zheng 发文,即日起在 Gemini Enterprise 正式可用([官方公告](https:\u002F\u002Fblog.google\u002Finnovation-and-ai\u002Fmodels-and-research\u002Fgemini-models\u002Fgemini-3-8-live-with-live-avatar\u002F))。\n\n## 脸是模型自己生成的,不是贴皮动画\n\n最值得注意的技术点是\"原生\"二字。Live Avatar 不是语音模型加独立动画引擎的两段式拼装——按 Google 开发者文档(经 WindowsForum 核实),3.8 Live 经 Live API 直接输出与合成语音同步的 24 FPS MP4 视频流,开发者像请求音频一样把 VIDEO 加进 response_modalities 即可,人脸由模型本体生成。视觉与音频输入同时处理,嘴型、表情与内容实时对齐。\n\n## 97 种语言切换,工具在后台跑\n\n官方称其具备原生多语言语音到语音同步:对话中途切换语言,唇形与表情动态适配,跨 97 种语言不降低视频保真度、不出现视觉漂移。另一亮点是异步工具调用:Avatar 在后台触发工具、拉取数据的同时对话不中断,官方演示场景是酒店入住——边跟客人确认信息,边调接口完成操作。Cloud 博客补充,原生 speech-to-speech 架构让打断恢复更自然,不丢上下文、不断后台事务([GA 公告](https:\u002F\u002Fcloud.google.com\u002Fblog\u002Fproducts\u002Fai-machine-learning\u002Fgemini-3-8-live-with-live-avatar-is-now-generally-available))。\n\n## 企业先吃,水印与白名单先行\n\n目前 Live Avatar 仅面向 Gemini Enterprise 客户(美欧节点),消费级 Gemini 应用尚未开放。企业提供预设形象库,也能用一张高质量参考图生成保留相似度的定制 Avatar,通道走企业白名单验证。所有音视频输出织入 SynthID 隐形水印,保持 AI 生成内容可检测。同系列 3.8 Live Extended Thinking 仍处私有预览。\n\n## 所以呢\n\nThe Register 的报道点出一个微妙的错位:Google 自己的研究者花了多年警告\"拟人化的 AI 会让用户过度信任\",而企业级产品已经出货([报道](https:\u002F\u002Fwww.theregister.com\u002Fai-and-ml\u002F2026\u002F09\u002F25\u002Fgoogle-gemini-can-present-cartoon-or-lifelike-avatars-to-lip-sync-generative-chatter\u002F5299016))。技术演进上,这条路线把数字人管线压缩成端到端多模态输出——部署更简单,语言一致性由模型自己保证。对企业,这是客服、导购、互动终端的新标配候选;对普通用户,值得留意的是那枚隐形水印:当屏幕里的脸越来越像人,可验证的\"这是 AI\"标记,可能是我们最后的抓手。","https:\u002F\u002Fblog.google\u002Finnovation-and-ai\u002Fmodels-and-research\u002Fgemini-models\u002Fgemini-3-8-live-with-live-avatar\u002F","d884df39-706a-45db-b7ed-371f12e54f1f",[11,15,18,21],{"id":12,"name":13,"slug":13,"description":14,"color":14},"a9524a82-a7c5-4daa-bb4b-a7ee77bb0b94","gemini",null,{"id":16,"name":17,"slug":17,"description":14,"color":14},"8cf7490f-2449-4ba7-be19-61befa0d92b4","google",{"id":19,"name":20,"slug":20,"description":14,"color":14},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"id":22,"name":23,"slug":23,"description":14,"color":14},"499f4b56-819d-49a3-9609-33e775143b86","multimodal",[25],{"id":26,"lang":27,"title":28,"summary":29,"content":30},"05f426f9-91cf-479d-9c59-fbdc2d781d18","en","Gemini 3.8 Live Avatar generates its own lip-synced face","Google ships Live Avatar on Gemini 3.8 Live: native 24 FPS lip-synced video, 97 languages, async tool calls, SynthID watermark. GA in Gemini Enterprise.","On September 24, 2026, Google introduced Gemini 3.8 Live with Live Avatar on its official blog: a near real-time video layer on top of the live dialogue model launched the week before, producing a lip-synced, expressive persona that listens, sees and speaks. The post came from Google DeepMind research scientist Shuo-yiin Chang and Gemini software engineer CJ Zheng, and the feature is generally available in Gemini Enterprise starting today ([official announcement](https:\u002F\u002Fblog.google\u002Finnovation-and-ai\u002Fmodels-and-research\u002Fgemini-models\u002Fgemini-3-8-live-with-live-avatar\u002F)).\n\n## The face is generated by the model itself\n\nThe technically interesting part is \"native\". Live Avatar is not a voice model feeding a separate animation engine: per Google's developer documentation (verified by WindowsForum), 3.8 Live outputs a 24 FPS MP4 video stream synchronized with synthesized speech through the Live API — developers request video as an output type (response_modalities=[\"VIDEO\"]) the same way they request audio, and the face is produced by the model itself. Visual and audio inputs are processed simultaneously, keeping mouth movement, expression and content aligned in near real time.\n\n## 97 languages and background tool calls\n\nThe feature ships native multilingual speech-to-speech synchronization: mid-conversation language switching adapts lip-sync and expressions across 97 languages without degrading video fidelity or introducing visual drift. Another engineering highlight is asynchronous tool execution — the avatar can trigger tool calls and fetch data in the background while the dialogue continues; Google's demo scenario is a hotel check-in where the agent confirms details with the guest while completing the operation via APIs. Google's Cloud blog adds that the native speech-to-speech foundation recovers from interruptions naturally, without dropping conversation context or backend transactions ([GA post](https:\u002F\u002Fcloud.google.com\u002Fblog\u002Fproducts\u002Fai-machine-learning\u002Fgemini-3-8-live-with-live-avatar-is-now-generally-available)).\n\n## Enterprise first, watermarks and allowlists included\n\nLive Avatar currently targets Gemini Enterprise customers (US and EU endpoints); consumer Gemini apps don't have it yet. Enterprises get a library of preset avatars and can generate custom ones from a high-quality reference image that preserves likeness — through enterprise allowlisting. All audio and video output carries the invisible SynthID watermark to keep AI-generated content detectable. The sibling 3.8 Live Extended Thinking remains in private preview.\n\n## So what\n\nThe Register noted the awkward timing: Google's own researchers have spent years warning that humanlike AI leads people to trust it more than they should — and the enterprise product has already shipped ([report](https:\u002F\u002Fwww.theregister.com\u002Fai-and-ml\u002F2026\u002F09\u002F25\u002Fgoogle-gemini-can-present-cartoon-or-lifelike-avatars-to-lip-sync-generative-chatter\u002F5299016)). Technically, the route compresses the two-stage \"voice model plus animation engine\" pipeline into end-to-end multimodal output — simpler to deploy, shorter latency path, and language consistency guaranteed by the model itself. For enterprises this is a strong candidate default for customer service and kiosk scenarios; for everyone else, the detail worth watching is the invisible watermark: as on-screen faces look more human, a verifiable \"this is AI\" mark may be the last thing we can hold onto.","gemini-3-8-live-avatar","2026-09-26T17:06:00Z","2026-09-26T17:11:43.725361Z","2026-09-26T17:11:43.725376Z",true,"agent",772,[39,48],{"slug":40,"tag_slug":40,"title_zh":41,"title_en":42,"intro_zh":43,"intro_en":44,"id":45,"is_active":35,"created_at":46,"modified_at":47},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":49,"tag_slug":49,"title_zh":50,"title_en":51,"intro_zh":52,"intro_en":53,"id":54,"is_active":35,"created_at":55,"modified_at":56},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":58},[59,64,69,74,79,84],{"id":60,"title":61,"news_slug":62,"published_at":63},"bdb6361a-d1da-45bb-8744-cb6922077e14","谷歌Gemini 3.8双TTS:30秒克隆,逐行导演","gemini-3-8-flash-tts-voice-design","2026-09-23T19:10:29+00:00",{"id":65,"title":66,"news_slug":67,"published_at":68},"8303f420-b3f1-485a-aa6f-7775256c84a7","Gemini 3.8 Audio 双发:Live 和 Extended Thinking 把思考+说话压到近实时","gemini-3-8-audio-live-extended-thinking","2026-09-16T03:00:00+00:00",{"id":70,"title":71,"news_slug":72,"published_at":73},"039ff515-68e7-4f11-866a-1da97e26eb45","Gemini 3.8 Live 拿下 S2S 实时语音榜第一","gemini-3-8-live-voice-s2s-number-one","2026-09-15T17:00:00+00:00",{"id":75,"title":76,"news_slug":77,"published_at":78},"1ba7e499-d93d-4566-bbeb-0b762904c0ab","Google 把 Lyria 3.5 装进 Gemini 与公开 API:音乐生成从独立工具变成默认选项","lyria-3-5-gemini-app-api","2026-09-06T23:06:32+00:00",{"id":80,"title":81,"news_slug":82,"published_at":83},"9af3dd83-6ed9-498d-9da0-547d917f3e19","语音转文字有了专用模型:Gemini 3.5 Transcribe 上线,出稿快 70%","gemini-35-transcribe-dedicated-asr","2026-08-31T13:30:00+00:00",{"id":85,"title":86,"news_slug":87,"published_at":88},"5ef6f8fe-9877-4632-bb4a-690c7e73975e","Gemini 3.5 Flash 内置 Computer Use：OSWorld 78.4 把屏幕操控推成工程能力","gemini-3-5-flash-computer-use-osworld-78","2026-06-26T00:00:00+00:00"]