Reverse-engineer a creator’s style: an AI persona and style guide from their latest videos

Disclosure: I build TubeText. This post uses our Video Breakdown AI Actor on Apify. The output below is from a run I did today. When you study a creator, the useful question isn’t “what is this video about?” but “what does this person do every time?”: which hooks they open with, how fast they cut, what they sell, how they end. Answering that means watching a dozen videos with a notepad. Here’s how I get a first draft of that notepad from one API call: a persona and style guide built from a creator’s latest videos, using Video Breakdown AI.

披露：我开发了 TubeText。本文使用了我们在 Apify 上运行的 Video Breakdown AI Actor。以下输出是我今天运行的结果。当你研究一位创作者时，有用的问题不是“这个视频讲了什么？”，而是“这个人每次都做了什么？”：他们以什么样的钩子开头，剪辑速度有多快，他们推销什么，以及他们如何结尾。要回答这些问题，意味着要拿着笔记本观看十几部视频。以下是我如何通过一次 API 调用获得该笔记本初稿的方法：使用 Video Breakdown AI，根据创作者的最新视频构建人物画像和风格指南。

One call: a channel in, a style guide out curl -X POST “https://api.apify.com/v2/acts/tubetext~video-breakdown-ai/run-sync-get-dataset-items?token=$APIFY_TOKEN”
-H ‘Content-Type: application/json’
-d ’{“urls”:[“https://www.youtube.com/@mkbhd/shorts”],“maxVideosPerSource”:5,“accountSummary”:true}’

一次调用：输入频道，输出风格指南 curl -X POST “https://api.apify.com/v2/acts/tubetext~video-breakdown-ai/run-sync-get-dataset-items?token=$APIFY_TOKEN”
-H ‘Content-Type: application/json’
-d ’{“urls”:[“https://www.youtube.com/@mkbhd/shorts”],“maxVideosPerSource”:5,“accountSummary”:true}’

The Actor takes the 5 newest Shorts, breaks each one down (hook, shot list, cut pacing, products shown, script), then condenses them into one extra row with “rowType”: “account_summary”. It works with a YouTube channel or an Instagram profile, and it needs at least 3 analyzed videos.

该 Actor 会获取最新的 5 个 Shorts 视频，对每个视频进行拆解（钩子、镜头列表、剪辑节奏、展示的产品、脚本），然后将它们浓缩成一行“rowType”: “account_summary” 的额外数据。它适用于 YouTube 频道或 Instagram 个人资料，并且至少需要分析 3 个视频。

What came back for MKBHD’s Shorts The summary row, shortened: { “rowType”: “account_summary”, “author”: “Marques Brownlee”, “videosAnalyzed”: 5, “medianDurationSeconds”: 66, “medianCutsPerMinute”: 9.8, “medianShotCount”: 11, “medianViews”: 7170706, “accountSummary”: { “content_pillars”: [ {“pillar”: “Product Reviews & Deep Dives”, “share_pct”: 60}, {“pillar”: “Tech Industry News & Analysis”, “share_pct”: 20}, {“pillar”: “Concept & Speculative Tech”, “share_pct”: 20} ], “hook_patterns”: [ {“type”: “visual surprise”, “share_pct”: 60, “example”: “Hey Benny. Do a flip.”}, {“type”: “bold claim”, “share_pct”: 40, “example”: “All right, the folding iPhone is here. It’s real. It’s called the iPhone Duo.”} ], “ctas”: [“Get subscribed for more”, “Watch the full video”, “Follow for more”], “what_performs_best”: “Videos featuring high-interest, ‘impossible’ tech concepts or viral-worthy hardware (like the iPhone Duo or Benny robot) significantly outperform standard industry analysis…” } }

MKBHD 的 Shorts 视频分析结果 摘要行（已缩短）： { “rowType”: “account_summary”, “author”: “Marques Brownlee”, “videosAnalyzed”: 5, “medianDurationSeconds”: 66, “medianCutsPerMinute”: 9.8, “medianShotCount”: 11, “medianViews”: 7170706, “accountSummary”: { “content_pillars”: [ {“pillar”: “产品评测与深度解析”, “share_pct”: 60}, {“pillar”: “科技行业新闻与分析”, “share_pct”: 20}, {“pillar”: “概念与前瞻科技”, “share_pct”: 20} ], “hook_patterns”: [ {“type”: “视觉惊喜”, “share_pct”: 60, “example”: “嘿 Benny，翻个跟头。”}, {“type”: “大胆断言”, “share_pct”: 40, “example”: “好了，折叠屏 iPhone 来了。它是真的。它叫 iPhone Duo。”} ], “ctas”: [“订阅以获取更多内容”, “观看完整视频”, “关注以获取更多”], “what_performs_best”: “展示高关注度、“不可能”的科技概念或具有病毒式传播潜力的硬件（如 iPhone Duo 或 Benny 机器人）的视频，表现明显优于标准的行业分析……” } }

It also returns a persona, tone and voice, on-screen text style, products and brands, posting cadence, and a style guide of 5 to 8 rules. Three of the seven it wrote for this channel: “Start with an immediate visual or auditory hook that defies expectations.” “Prioritize ‘show, don’t tell’ by using high-quality B-roll to demonstrate features.” “Keep on-screen text minimal, using it only for critical data points or emphasis.”

它还会返回人物画像、语气和语调、屏幕文字风格、产品和品牌、发布频率，以及包含 5 到 8 条规则的风格指南。它为该频道撰写的七条规则中的三条如下： “以打破预期的即时视觉或听觉钩子开头。” “通过使用高质量的 B-roll（辅助镜头）来展示功能，优先考虑‘展示而非讲述’。” “保持屏幕文字简洁，仅用于关键数据点或强调。”

Two things I find more useful than the prose: The hook mix is countable. 3 of 5 Shorts open on a visual surprise and 2 on a bold spoken claim. Run it on three competitors and you can compare those shares directly. The medians give you a brief. About 66 seconds, about 10 cuts a minute, 11 shots. That’s a concrete target for an editor, not “make it punchy”.

比起文字描述，我发现以下两点更有用： 钩子组合是可以量化的。5 个 Shorts 中有 3 个以视觉惊喜开头，2 个以大胆的口头断言开头。在三个竞争对手身上运行此工具，你可以直接比较这些比例。 中位数为你提供了一个简报。大约 66 秒，每分钟约 10 次剪辑，11 个镜头。这对剪辑师来说是一个具体的目标，而不是“让它更有冲击力”这种模糊的要求。

The per-video rows are still there Each of the 5 videos also gets its own row, so you can check the summary against the evidence. For example, the hook row for “Apple’s Big Price Hike”: { “text”: “All right, so the memory price hikes have finally hit Apple and they have really hit.”, “type”: “bold claim”, “delivered_as”: “voice”, “why_it_works”: “It immediately addresses a major tech news story with a sense of urgency and direct impact on the viewer’s wallet.” }

每个视频的详细数据行依然存在 5 个视频中的每一个都有自己的数据行，因此你可以对照证据核实摘要。例如，“苹果的大幅涨价”视频的钩子行如下： { “text”: “好了，内存涨价终于波及到了苹果，而且影响非常大。”, “type”: “大胆断言”, “delivered_as”: “语音”, “why_it_works”: “它以一种紧迫感和对观众钱包的直接影响，立即切入了一则重大的科技新闻。” }

Cost Each video is $0.03 at Apify free-plan prices, plus $0.01 per minute past 3 minutes. The account summary row is free while it’s in beta. This run was 5 Shorts, so about $0.15, and it took about 3½ minutes. Videos that can’t be downloaded or analyzed aren’t billed. If a channel posts long videos, set “channelSort”: “popular” to study its most-viewed uploads instead of the newest, and keep maxVideosPerSource small at first.

费用 在 Apify 免费计划价格下，每个视频为 0.03 美元，超过 3 分钟的部分每分钟加收 0.01 美元。账户摘要行在测试阶段是免费的。这次运行了 5 个 Shorts，费用约为 0.15 美元，耗时约 3 分半钟。无法下载或分析的视频不计费。如果频道发布长视频，请设置 “channelSort”: “popular” 以研究其观看次数最多的上传内容，而不是最新的内容，并在一开始保持 maxVideosPerSource 的数值较小。

Caveats 5 videos is a small sample. The shares (60%, 40%) are counts, not statistics. Use 10 to 20 videos for anything you’ll act on. The persona and style guide are a model’s reading of the videos. Treat them as a first draft to check against the per-video rows, not as fact. Instagram profiles often hide view counts. When that happens, the summary says so instead of guessing what performs best. Questions or a platform you need? Open an issue on the Actor’s page. I read every one.

注意事项 5 个视频是一个很小的样本。这些比例（60%、40%）是计数，而非统计数据。对于任何你要采取行动的内容，请使用 10 到 20 个视频。人物画像和风格指南是模型对视频的解读。请将它们视为对照每个视频数据行进行核对的初稿，而不是事实。Instagram 个人资料通常会隐藏观看次数。当这种情况发生时，摘要会说明这一点，而不是猜测什么表现最好。有问题或需要支持的平台？在 Actor 的页面上提交一个 issue。我会阅读每一条。