[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-gemini-3-8-flash-tts-voice-design":3,"topics-all":38,"news-related-bdb6361a-d1da-45bb-8744-cb6922077e14":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},"bdb6361a-d1da-45bb-8744-cb6922077e14","谷歌Gemini 3.8双TTS:30秒克隆,逐行导演","谷歌发布 Gemini 3.8 Flash TTS 与 Flash-Lite TTS:自然语言从零设计音色,30 秒样本克隆(需语音同意验证),支持 100+ 语言、2000+ 预置音色、逐行表演指令与双说话人剧本,输出全部带 SynthID 水印,已在 Gemini API 与 AI Studio 上线。","谷歌把文生语音(TTS)从「选一个预置音色」改成了「进录音棚当导演」。Google 9 月 23 日发布 Gemini 3.8 Flash TTS 与 Gemini 3.8 Flash-Lite TTS,官方称这是「从静态预设到动态创意工作室」的转变。两个模型即日起在 Gemini API 与 Google AI Studio 上线,消费侧进入 Gemini Notebook 和 Google Vids,企业版 API 即将跟进。\n\n## 双模型分工:一个管创意,一个管走量\n\nFlash TTS 面向深度创作:游戏角色、有声书、播客、互动媒体。核心卖点是「从零设计音色」——用自然语言描述角色、口音和声音特征,模型生成一个原本不存在的声音。官方示例包括墨尔本高能 DJ、尖细单调的机器人、会说话的日本龙,覆盖超过 100 种语言和方言。Flash-Lite 走低成本大批量路线,面向配音、音频内容生产和语音 Agent,仍保留对语调、节奏和表现力的细粒度控制。\n\n预置音色库从 30 个扩到 2000+ 个,含墨西哥西班牙语、魁北克法语、苏格兰英语等区域变体。声音复刻只需 30 秒音频样本,但流程强制嵌入同意环节:必须提交声音所有者的口头同意录音,系统校验与参考说话人匹配后才建立声音。复刻声音带 C2PA 内容凭证,所有 Gemini Audio 输出均内嵌 SynthID 不可见水印。\n\n## 逐行导演,而不是整段念稿\n\n两个模型都支持逐行表演指令:给每行台词写舞台指示,控制节奏、情绪、方言切换,可插入 \u003Claughs>、\u003Csigh> 这类非言语线索和 |mhm|、|yeah| 这类倾听式插话。单条脚本可编排原生双说话人场景,两个声音自然分离;长篇生成可连续数小时保持音色与角色特征,官方称说话人漂移降至最低。TTS 正从「读稿工具」变成「表演工具」。\n\n## 榜单成绩:官方口径,注意归因\n\n官方博客公布:Flash TTS 在 Hume AI Voice Design Benchmark 以 71.4 分拿下总榜第一,口音建模 60.8 分同样领先;Hume AI Overall Quality Index 上两模型分列一、二位;对比基线是自家上一代 Gemini 3.1 Flash TTS,长篇与双说话人控制提升明显。Voice Arena 盲测里,两模型在日语、巴西葡萄牙语、越南语、阿拉伯语、墨西哥西班牙语、印地语等关键语言位居前列。注意:以上均为谷歌官方口径,第三方独立复现尚待时日。\n\n## 生态与合规红线\n\n发布即带生态:Agora、LiveKit、Pipecat、Vercel 已接入,Figma、HeyGen、Wondercraft 等正在集成。合规侧,声音复刻在伊利诺伊、得克萨斯、EEA、英国、瑞士和印度不可用——合规边界直接画进产品功能。\n\n## 所以呢\n\nTTS 赛道近两个月不安静:Qwen3-TTS、B 站 IndexTTS-2.5、BreezeBlue Breeze TTS 2 等开源阵营连续出招,拼多语种、低延迟、情感控制。谷歌这一手没卷参数量,卷的是「可控性」——音色可从零设计、表演可逐行导演、克隆有同意门槛、输出有水印可溯源。对做有声书、配音、语音 Agent 的团队,选型问题正从「哪家念得像人」变成「哪家听得懂导演」。开源阵营在榜单上未必输,但在「导演工作流 + 合规凭证」这层产品化能力上,谷歌把标杆抬了一格。下一步盯第三方评测的独立复现,以及开源社区在可控表演维度的接招。\n\n参考:\n- 官方发布: blog.google\u002F...\u002Fgemini-3-8-text-to-speech\u002F\n- 独立报道: thenextweb.com\u002Fnews\u002Fgemini-tts-3-8-flash-voice-design-cloning","https:\u002F\u002Fblog.google\u002Finnovation-and-ai\u002Fmodels-and-research\u002Fgemini-models\u002Fgemini-3-8-text-to-speech\u002F","04a519f6-0341-4693-a20c-742a7db35036",[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},"44f7b754-0efa-4188-8f03-2f3027743fe7","en","Google's Gemini 3.8 Flash TTS: Design Voices, Direct Lines","Google's Gemini 3.8 Flash TTS designs voices from prompts and clones them from 30 seconds of audio, with consent checks and SynthID watermarks.","Google has quietly redefined what a text-to-speech model is supposed to be. On September 23 the company shipped Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, describing the release as a shift \"from static presets into a dynamic creative studio.\" Both models are live now in the Gemini API and Google AI Studio, with enterprise APIs following soon; on the consumer side they land in Gemini Notebook and Google Vids.\n\n## Two models, two jobs\n\nFlash TTS is built for deep creative direction: game characters, immersive audiobooks, podcasts, interactive media. Its headline capability is generative voice design — describing a role, accent and voice characteristics in natural language, and getting back a voice that never existed. Google's own examples include a high-energy DJ from Melbourne, a super-tinny monotone robot, and a Japanese dragon, covering more than 100 languages and dialects.\n\nFlash-Lite TTS is the volume tier: optimized for high-volume dubbing, audio content production and expressive voice agents, while keeping fine-grained control over tone, pacing and expressive nuance.\n\nThe preset library has grown from 30 original voices to 2,000+ production-ready voices, including regional varieties like Mexican Spanish, Quebec French and Scots English. Voice replication needs just a 30-second sample — but Google hard-wired the consent step: users must provide a verbal consent recording from the voice owner, and the system verifies it matches the reference speaker before any voice is created. Replicated voices carry C2PA content credentials, and every clip from Google's Gemini Audio models is watermarked with SynthID.\n\n## Direct the performance, line by line\n\nBoth models support line-by-line direction: write stage directions for each line, or let Gemini steer delivery from natural script cues. Scripts can include non-verbal bursts like laughs, sighs and gasps rendered through inline tags, plus active-listening interjections such as \"mhm\" or \"yeah\" for comedic timing and reaction beats. A single script can stage a native two-speaker scene, with both voices kept distinctly separated and natural turn-taking. Long-form generation holds voice quality and character timbre across hours of continuous audio with minimal speaker drift, according to Google. TTS is becoming a performance instrument rather than a reading tool.\n\n## Benchmark numbers: official claims, read the attribution\n\nThe official announcement says Gemini 3.8 Flash TTS takes the #1 overall spot on Hume AI's Voice Design Benchmark with a score of 71.4, and leads accent modeling at 60.8. On Hume AI's Overall Quality Index, Flash and Flash-Lite sit at #1 and #2 respectively. Google's comparison baseline is its own Gemini 3.1 Flash TTS, with major improvements claimed in long-form content and dual-speaker screenplay control. In blind human preference runs on Voice Arena, the two models secure top positions in key languages including Japanese, Brazilian Portuguese, Vietnamese, Modern Standard Arabic, Mexican Spanish and Hindi. Caveat: these are Google's own published numbers; independent third-party reproduction is still pending.\n\n## Ecosystem on day one, and a compliance map\n\nThe launch ships with an ecosystem: Agora, LiveKit, Pipecat and Vercel already integrate the models, and Figma, HeyGen, Linguana, Wondercraft, 99.co and Ollang are building on them for global dubbing, regional-accent localization and conversational voice agents at scale. On the safety side, beyond SynthID and consent verification, voice replication through AI Studio is unavailable in Illinois, Texas, the EEA, the UK, Switzerland and India — compliance boundaries drawn directly into product functionality.\n\n## So what\n\nThe TTS track has been busy: Qwen3-TTS, Bilibili's IndexTTS-2.5 and BreezeBlue's Breeze TTS 2 have all shipped from the open camp in recent months, competing on multilingual coverage, latency and emotion control. Google's move competes on none of those axes. It competes on controllability — voices designed from scratch, performances directed line by line, cloning gated by consent, outputs traceable through watermarks. For teams building audiobooks, dubbing or voice agents, the selection question is shifting from \"which model reads most naturally\" to \"which model takes direction.\" The open-source camp may not lose on leaderboards, but in director-grade workflows plus compliance credentials, Google just raised the bar. What to watch next: independent reproductions on Hume and Voice Arena, and how the open community answers on controllable performance.\n\nReferences:\n- Official announcement: blog.google\u002Finnovation-and-ai\u002Fmodels-and-research\u002Fgemini-models\u002Fgemini-3-8-text-to-speech\u002F\n- Independent coverage: thenextweb.com\u002Fnews\u002Fgemini-tts-3-8-flash-voice-design-cloning","gemini-3-8-flash-tts-voice-design","2026-09-23T19:10:29Z","2026-09-23T19:10:31.232248Z","2026-09-23T19:10:31.232260Z",true,"agent",785,[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},"d219ead5-ea5d-4aaa-835e-5ec3cf980856","Gemini Live Avatar:模型直出唇同步数字人","gemini-3-8-live-avatar","2026-09-26T17:06:00+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"]