TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Midjourney for Language Learning Videos

5 点作者 cmuguythrow6 个月前
Demo: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;fXj5VYYaoeY" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;fXj5VYYaoeY</a> Website: <a href="https:&#x2F;&#x2F;plusonechinese.com" rel="nofollow">https:&#x2F;&#x2F;plusonechinese.com</a><p>Hey HN, we&#x27;re Patrick and Thomas and are building an app that uses generative video to teach languages (currently Mandarin only).<p>Background: We think the &quot;Comprehensible Input&quot; theory of language learning has a lot of merit - TL;DR: consume native content that you can understand a high % of and pick everything else up as you go with context. For more detail see <a href="https:&#x2F;&#x2F;refold.la&#x2F;roadmap&#x2F;" rel="nofollow">https:&#x2F;&#x2F;refold.la&#x2F;roadmap&#x2F;</a> or <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Input_hypothesis" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Input_hypothesis</a> However, it is quite difficult to find content that is interesting to you, at your level, and in a format you can study it. Generative AI can help bridge this content gap.<p>What we&#x27;ve built: An AI video agent that takes your vocab level and a short prompt and spits out a ~2-minute video. The video will have dialogue that is 85% comprehensible at the given vocab level, making learning the remaining 15% of new words easier and more effective.<p>For example, this video was generated with a 2,150 word vocab and the prompt “Bringing a pet capybara to the public pool”. <a href="https:&#x2F;&#x2F;youtu.be&#x2F;B7zRNl60hPY" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;B7zRNl60hPY</a><p>Video Details: From that simple prompt we make a story, break down the characters and environment, write the script and ensure it’s properly levelled, break it down into shots, bring those to life with tts&#x2F;image&#x2F;video&#x2F;lipsync, and stitch it together with music. As far as we can tell, this is the first end-to-end automated story video workflow of its kind, with no manual steps or cherry-picking, no choosing from character templates, etc.<p>The app is free for watching videos and studying flashcards, and doesn’t require an email to sign up. After the first free video generation, making your own videos is $15&#x2F;mo for 1 video&#x2F;day. Excited to hear everyone’s feedback!

2 条评论

bli9405056 个月前
First end-to-end automated story video workflow of its kind Videos like these [1][2] are a dime a dozen and have been out for years. Surprised you think this is completely novel.<p>[1] <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=tzE7TYwAYq4" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=tzE7TYwAYq4</a> [2] <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=az7KfOQkMu0" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=az7KfOQkMu0</a>
评论 #42248624 未加载
hitchhiker25266 个月前
Curious, why Mandarin only? Is there something about the language that makes it more feasible or more attractive to the business?. FWIW I would consider using something like this if it could teach Japanese.
评论 #42248407 未加载