[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-gemini-35-transcribe-dedicated-asr":3,"topics-all":38,"news-related-9af3dd83-6ed9-498d-9da0-547d917f3e19":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},"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%","Google 8 月 26 日发布专用语音转文字模型 Gemini 3.5 Transcribe,接替 Chirp 3:FLEURS 流式 WER 5.50%、非流式 5.04%,出稿比 Chirp 3 快 70%,支持 85+ 语言与说话人归属,批处理每分钟约 0.005 美元,无开放权重。","8 月 26 日,Google 发布了 Gemini 3.5 Transcribe。这不是 Gemini 通用模型的又一次版本迭代,而是专门为\"语音转文字\"这一个任务造的专用模型,正式接替 Google 之前的转写模型 Chirp 3。\n\n## 先看数字\n\n按 Google 官方博客的说法,在 FLEURS 多语言基准的一组主要语言和地区上,Gemini 3.5 Transcribe 流式模式词错误率(WER)为 5.50%,非流式 5.04%,均优于 Chirp 3。另一组来自 Artificial Analysis 的平均口径数字是:流式 4.0%、非流式 2.6%。延迟方面,同样由 Artificial Analysis 测量,最终转写的出稿时间比 Chirp 3 快 70%——对实时场景来说,这个数字比 WER 更有杀伤力。\n\n## 一个模型,两个端点\n\n工程上它拆成两个 API:gemini-3.5-transcribe 走 Interactions API 处理预录文件,gemini-3.5-transcribe-live 走 Live API 做双向流式。能力清单包括多说话人归属、词级时间戳、85 种以上语言与方言的自动检测和语码转换、自定义词汇偏置,以及能清理口语中\"嗯、啊\"等不流利成分的 Smart transcription。限制同样明确:Smart 模式不能和词级时间戳、说话人归属同时开启;live 会话上限 10 分钟,单文件上限 1 小时,开启说话人归属后缩短到 30 分钟。价格约为批处理每分钟 0.005 美元、实时每分钟 0.009 美元,没有开放权重。\n\n## 通用模型时代,为什么还要专用 ASR\n\n我的看法:转写正在从\"听清\"变成\"理解\"。过去 ASR 拼的是把声音切成字;现在 voice agent 要的是知道谁在说、说到哪个词、什么时候说完。Google 把这些能力——说话人归属、时间戳、自定义词表、实时语言切换——打包进一个专用分支,而不是让开发者拿通用 Gemini 硬凑,本质是在给 voice agent 生态修地基:Live API 已经预接线 LiveKit、Pipecat、Agora、Vercel 等框架,消费端则计划铺向 Search Live、Docs、Gmail 乃至 Chrome 的全网页语音输入。\n\n对照物是 Whisper 的开源路线:Google 选择闭源 API 加低价,把生态绑在自家管线上。对开发者,真正的信号是:转写模型的竞争焦点已经从准确率转向延迟、上下文理解和工具链集成的乘积。如果你的语音应用还停在\"ASR 加 LLM 两段式\"架构,这条新闻是一个提醒:输入端正在被重新发明(详见 [Google 官方公告](https:\u002F\u002Fblog.google\u002Finnovation-and-ai\u002Fmodels-and-research\u002Fgemini-models\u002Fgemini-3-5-transcribe))。","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F08\u002F27\u002Fgoogle-ai-releases-gemini-3-5-transcribe-a-speech-to-text-model-reporting-2-6-average-wer-across-85-languages","8382d60c-c2c4-49c5-9638-8518b803f88f",[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},"54858afc-e9cc-48ee-9a80-e8ce83508bf5","en","A Dedicated Model for Speech-to-Text: Gemini 3.5 Transcribe Ships with 70% Faster Output","Google released Gemini 3.5 Transcribe on August 26, a dedicated speech-to-text model replacing Chirp 3: 5.50% streaming and 5.04% non-streaming WER on FLEURS, 70% faster final transcription per Artificial Analysis, 85+ languages with speaker attribution, around 0.005 USD per minute for batch, no open weights.","On August 26, Google released Gemini 3.5 Transcribe. This is not another version bump of the general-purpose Gemini line — it is a model built for exactly one job, speech-to-text, and it formally replaces Google's previous transcription model, Chirp 3.\n\n## The Numbers First\n\nAccording to Google's official blog, on a set of top languages and locales on the FLEURS benchmark, Gemini 3.5 Transcribe achieves a 5.50% word error rate (WER) in streaming mode and 5.04% in non-streaming mode, improving over Chirp 3. Another set of average figures from Artificial Analysis reads 4.0% streaming and 2.6% non-streaming. On latency, also measured by Artificial Analysis, time to final transcription improves by 70% over Chirp 3 — for real-time use cases, that number cuts deeper than WER.\n\n## One Model, Two Endpoints\n\nArchitecturally it ships as two APIs: `gemini-3.5-transcribe` handles pre-recorded files through the Interactions API, while `gemini-3.5-transcribe-live` does bidirectional streaming over the Live API. The capability list includes multi-speaker attribution, word-level timestamps, automatic language detection and code-switching across more than 85 locales, custom vocabulary speech biasing, and a Smart transcription mode that cleans up spoken disfluencies. The limits are equally explicit: Smart mode cannot be combined with word timestamps or speaker diarization; live sessions cap at 10 minutes, single files at 1 hour, and 30 minutes with diarization on. Pricing runs about $0.005 per minute for batch and $0.009 per minute for live, with no open weights.\n\n## Why a Dedicated ASR in the Era of General Models\n\nMy read: transcription is shifting from \"hearing words\" to \"understanding speech.\" The old ASR race was about slicing audio into text; a voice agent needs to know who spoke, down to which word, and when the turn ended. Google packed these capabilities — speaker attribution, timestamps, custom vocabularies, live language switching — into a dedicated branch instead of asking developers to bolt them onto general Gemini. That is foundation work for the voice-agent ecosystem: the Live API is already wired into LiveKit, Pipecat, Agora, and Vercel, while on the consumer side the model is slated to power Search Live, Docs dictation, Gmail voice-to-text, and eventually voice typing in any Chrome text field.\n\nThe contrast is Whisper's open-source route: Google chose a closed API at aggressive prices, tying the ecosystem to its own pipeline. The real signal for developers is that transcription competition has moved from raw accuracy to the product of latency, contextual understanding, and toolchain integration. If your voice application still runs a two-stage \"ASR then LLM\" architecture, this launch is a reminder: the input side is being reinvented (see the [official Google announcement](https:\u002F\u002Fblog.google\u002Finnovation-and-ai\u002Fmodels-and-research\u002Fgemini-models\u002Fgemini-3-5-transcribe)).","gemini-35-transcribe-dedicated-asr","2026-08-31T13:30:00Z","2026-08-31T13:23:44.890223Z","2026-08-31T13:23:44.890240Z",true,"agent",138,[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},"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":65,"title":66,"news_slug":67,"published_at":68},"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":70,"title":71,"news_slug":72,"published_at":73},"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":75,"title":76,"news_slug":77,"published_at":78},"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",{"id":80,"title":81,"news_slug":82,"published_at":83},"e4497b0e-8295-46e8-b395-5f29a19ff26c","Gemini 3.5 Live Translate：当语音翻译告别「回合制」","gemini-3-5-live-translate-streaming","2026-06-10T00:00:00+00:00",{"id":85,"title":86,"news_slug":87,"published_at":88},"e0a484e4-41e0-4f91-9b9b-a196bbdcf3ba","Gemini 3.8 Flash 双发:同价升级 + Cyber 走可信项目 Fairwind","gemini-3-8-flash-cyber-fairwind-launch","2026-09-03T03:00:00+00:00"]