Wan3.0 Goes Live: Stable, Real, Textured
Welcome back to Learn English with Podcasts! Sarah, quick question - how long can most AI video models film in one single go?欢迎回到 Learn English with Podcasts！Sarah，问个问题——大多数 AI 视频模型一次最多能生成多长的视频？
A few seconds, usually five or ten. Long enough for a looping clip, not long enough for a story.一般就几秒钟，五秒或十秒。够做一段循环动画，但不够讲一个故事。
Right, and that changed today. Alibaba's video model Wan3.0 is now officially live, and it can generate 30 seconds in one take.没错，今天这事儿变了。阿里巴巴的视频模型 Wan3.0 正式上线了，单次就能生成 30 秒的视频。
30 seconds in one take? That's basically a full scene with a beginning and an end.一次生成 30 秒？那基本就是一个有开头有结尾的完整场景了。
Exactly. It was in public testing since August 6, and today is the official launch day. And there's a second surprise - you can feed it documents.对。它从 8 月 6 日就开始公测了，今天是正式上线。还有第二个惊喜——你可以喂文档给它。
Documents? Like Word files and spreadsheets?文档？就像 Word 文件和表格那种？
Yes - doc, xls, ppt, pdf, even markdown files. Upload them, and the model builds a video from the content.对——doc、xls、ppt、pdf，甚至 markdown 文件都行。上传之后，模型会根据内容做出一段视频。
Wait, so I could upload my meeting notes and get a video version? That's a strange new superpower.等等，那我上传会议记录就能得到一个视频版？这是个奇怪的新超能力。
Welcome to 2026. But the word people keep repeating about this model is "real". Real faces, real light, real physics.欢迎来到 2026。不过大家提到这个模型时反复说的一个词是"真实"。真实的脸、真实的光、真实的物理效果。
Okay, prove it. What did people actually make with it?好，证明给我看。人们用它到底做出了什么？
One creator made a short film called The Bar That Sells Memories - a bar where customers buy memories. Great premise already.有一位创作者拍了一部短片，叫《出售回忆的酒吧》——一家顾客可以购买回忆的酒吧。这个设定本身就很棒。
Oh, I want to watch that already. What about the quality?哦，我已经想看了。画质怎么样？
The hero's face stays the same from a wide shot to a very close close-up. That's the hardest part for AI, because faces usually drift.主角的脸从中景推到大特写都保持一致。这是 AI 最难的部分，因为脸通常会变来变去。
I've seen that drift. By shot five, your character looks like a cousin of shot one.我见过那种漂移。到第五个镜头，角色看起来像第一个镜头的表亲。
Ha, exactly. And the bar itself kept one color mood - warm amber lights, wooden furniture, and glass bottles reflecting the whole room.哈，就是。而且酒吧本身保持了统一的色彩氛围——温暖的琥珀色灯光、木质家具，玻璃瓶还反射着整个店内的景象。
Glass reflecting the room? Even professional crews struggle with that.玻璃反射店内景象？连专业摄制组都觉得难。
Now the business side. An AI review team called Flova kept saying one word: stable. Not just pretty frames - stable output you can plan real work around.再说说商业这边。一个叫 Flova 的 AI 评测团队反复说一个词：稳定。不只是画面好看，而是稳定到你敢围绕它安排真正的生产。
For companies, boring words like stable are actually exciting words.对公司来说，"稳定"这种无聊的词其实才让人兴奋。
In their test clip, one single shot had eye reflections, moving hair, flowing white fabric, and shiny water - four things AI usually breaks.在他们的测试片段里，一个镜头同时出现了眼球反射、飘动的头发、白纱的运动和水面光泽——这四样通常是 AI 容易翻车的。
Four hard things in one shot? And the skin didn't look plastic?一个镜头四个难点？皮肤也没有塑料感？
No plastic at all. It even held a cold grey-blue color tone all the way through.完全没有塑料感。它甚至还全程守住了冷灰蓝的色调。
Did anyone outside China test it?有海外的团队测试吗？
Yes. Koyal.ai tested six animation categories, and Wan3.0 ranked number one overall.有。Koyal.ai 测评了六个动画类别，Wan3.0 总分排名第一。
Number one across six categories - that's not luck anymore.六个类别综合第一——这就不是靠运气了。
They loved its high-energy motion, like fast action scenes, and its realistic style scored high too.他们特别喜欢它的高动态表现，比如快节奏的动作场面，写实风格的得分也很高。
So who is actually using this every day? Give me the industries.那现在谁在天天用它？跟我说说有哪些行业。
Short drama studios first. One tech team said close-ups of actors' faces come out clean and steady, so they can produce shows at scale.首先是短剧团队。一家技术公司说，演员面部的近景特写出来又干净又稳，所以他们可以规模化生产短剧。
At scale meaning many episodes, on schedule."规模化"就是说很多集、按进度出片。
Right. A platform called LibTV made a car chase - cars, drivers, and city streets stayed consistent for the whole 30 seconds.对。一个叫 LibTV 的平台做了一场追车戏——车辆、司机和城市街道在整个 30 秒里都保持一致。
Without restarting fifty times to roll a lucky clip?不用重开五十次去抽一段运气好的片段？
Almost no rerolling. Before, AI video felt like a slot machine - you pulled the lever again and again and hoped.几乎不用重抽。以前 AI 视频像老虎机——你得一遍一遍拉杆，然后祈祷。
And now the lever finally pays out every time. What about advertising?现在这台老虎机终于每次都出货了。广告行业呢？
An ad company in Guangzhou said products and logos stay accurate, and talking presenters look natural - close to a real commercial shoot.广州一家广告公司说，商品和 Logo 能保持准确，口播的人也很自然——接近真实广告拍摄的水平。
Logos are a big deal. Brands get angry when their logo grows an extra corner.Logo 这点很关键。品牌方看到自家 Logo 多出一个角是会生气的。
Tourism too. Creators rebuilt famous places with cinematic camera moves - an ancient city at sunset, red palace walls, cherry blossoms in Kyoto.文旅也在用。创作者用电影级的运镜重现著名景点——晚霞中的古城、红色的宫墙、京都的樱花。
So someone who may never visit Kyoto can still feel it first.这样可能永远没机会去京都的人，也能先感受一下。
And musicians. One music company uploaded a single photo of a singer, marked lip-sync singing, and got several camera angles automatically.还有音乐人。一家音乐公司上传了一张歌手的照片，标注对口型唱歌，就自动得到了好几个机位镜头。
From one photo to a finished music video? That used to need a whole film crew.从一张照片到一个成品 MV？这以前需要一整个摄制组。
During those ten-plus days of public testing, it also improved daily - better instruction following, steadier cross-shot consistency, cleaner audio.公测的十多天里，它还在每天进化——指令遵循更好，跨镜头一致性更稳，音频也更干净。
Okay, the important question - how much does it cost?好，关键问题来了——多少钱？
Through the API, 480P costs 0.3 yuan per second, 720P is 0.6 yuan, and 1080P is 1.2 yuan.API 价格是 480P 每秒 0.3 元，720P 是 0.6 元，1080P 是 1.2 元。
Any launch discount?上线有优惠吗？
Until September 23, two platforms offer a 30% discount. So yes, cheap enough to experiment with.9 月 23 日之前，两个平台有 7 折优惠。所以说，拿来试错足够便宜。
And it's easy to find. It's live on Alibaba Cloud's Bailian platform, the Wan website, and several apps including Qwen.而且很好找。阿里云百炼平台、万相官网，还有千问等多个 App 都能用上它。
You know what just hit me? All those industries - drama, ads, tourism, music - they all sell stories. And this tool makes stories cheaper.你知道吗，我突然想到一件事。刚才说的那些行业——短剧、广告、文旅、音乐——卖的都是故事。而这个工具让故事变便宜了。
Which means the bottleneck moves. It's no longer "can you afford to shoot it?" It's "do you have a story worth shooting?"所以瓶颈就转移了。问题不再是"你拍不拍得起"，而是"你的故事值不值得拍"。
Ooh, save that line for the show notes. Meanwhile, I'm going to upload my expense spreadsheet and ask for an emotional music video about taxes.哇，这句要写进节目简介。而我嘛，打算把我的报销表格传上去，让它做一支关于报税的抒情 MV。
Please send it over when the violin comes in. Try Wan3.0, and tell us - what would you feed it: a photo, a document, or your wildest idea?等小提琴响起来的时候一定要发给我们。试试 Wan3.0 吧，然后告诉我们——你会喂给它什么：一张照片、一份文档，还是你最疯狂的想法？
We'd love to hear it. See you next time on Learn English with Podcasts!我们很期待听到你的分享。下期 Learn English with Podcasts 再见！
See you next time!下期见！