长视频 → 带字幕的 Shorts

把长视频和剪辑要求交给 AI，即可获得一组精选、已重构画幅并配好字幕的社交短视频。

配方

运行

  • 视频
  • 5 个流水线
  • ≥ 2 积分

人工智能代理

终端

初次使用? 快速开始
01
Homebrew brew install pipe2-ai/tap/pipe2
↳
Go go install github.com/pipe2-ai/pipe2-cli/cmd/pipe2@latest
02
获取 API 令牌 ↗ echo "$PAT" | pipe2 auth login --token -

同一集中的 3 个片段

更改结果

--input必填
asset_url默认—Source video: a YouTube or social URL, direct media URL, local file, or existing Pipe2 asset.
--instructions
string默认Find the five strongest self-contained moments. Prefer clear ideas, surprising claims, useful explanations, or complete stories. Each clip should make sense without the rest of the video.Editorial brief describing which moments to select and what makes a good clip.
--max-clips
int默认5Maximum number of clips Video Trim may return.
--max-seconds
int默认45Maximum duration of each selected clip, in seconds.
--aspect
enum默认9:16Output aspect ratio for every clip.
9:16 · 1:1 · 4:5 +1
9:161:14:516:9
--preset
enum默认serif-editorialCaption style used for every clip.
tiktok-bold-yellow · minimal-white · subtle-drop +3
tiktok-bold-yellowminimal-whitesubtle-dropkaraoke-gradientbig-serifserif-editorial
--corrections
string默认Optional comma-separated word corrections in the form from=to,from=to.
--lang
string默认autoISO 639-1 transcription language, or auto.
--parallel
int默认4Maximum number of selected clips processed in parallel.
--position
enum默认autoCaption position. Auto keeps text away from the main subject when possible.
auto · top · middle +1
autotopmiddlebottom
工作原理 5 个流水线
  1. transcription

    生成带时间戳的语音地图，供 Video Trim 确保每个选中的观点完整。

    输入来源: OpenClaw Creator: Why 80% Of Apps Will Disappear
    文本 
    Today, I'm sitting down with Peter Steinberger, the creator of OpenClaw, the open source personal AI agent that has completely taken over the internet.
The GitHub repo exploded to over 160,000 stars practically overnight.
The community has built countless projects like Maltbook, where bots talk among themselves,
and now the bots are even renting humans to do tasks in the real world.
In our conversation, we discuss his aha moment, his contrarian development philosophies, and what this means for builders in 2026.
Let's dive in.
[upbeat music] So good to see you, man.
Hey, what's up?
Um, so you've made something people want.
…
  2. video-trim

    审看完整的源视频，根据剪辑要求选出最有力的片段，并以独立片段返回。

    视频
  3. video-reframe

    将每个选中的片段重构为所选的社交平台画幅比例，同时让说话者和重要内容保持在画面内。

    视频
  4. transcription

    转录每个重构后的片段，使字幕与最终剪辑和时间轴一致。

    文本 
    Are apps just gonna go away?
Uh, I think 80% of them are going away.
Why do I need MyFitnessPal?
Like, my agent already knows that I'm making bad decisions.
I'm at, I don't know,
uh, Smashburger something,
and it will already assume that I eat what I like to eat.
If I don't make a comment, it will just, like, automatically track it, or I make a picture and it'll just store it somewhere.
I don't even need to care, right?
  5. captions

    按所选样式和位置，将对应的转录文本烧录进每个片段。

    视频
为什么有效以及可以更改什么

为什么有效

配方先为源视频生成带时间戳的转录，然后由 video-trim 审看完整录像，将候选片段与你的指令逐一对照，并返回多个各自完整的片段。无需另外维护一份精彩片段清单，也无需准备时间戳文件。

之后，每个选中的片段都会单独完成后期处理。画幅重构在转录之前进行，因此转录文本和烧录字幕与最终剪辑完全一致。各个分支并行运行：要求更多片段会增加工作量，但不会让配方变成一条漫长的串行队列。

关键设置

  • instructions：同时描述主题和剪辑标准。“五个最有力、可独立成立的论点”比“有趣的片段”效果更好。
  • max_clips：限制片段数量的上限；当满足要求的片段较少时，不会强迫智能体用弱片段凑数。
  • max_seconds：设置每个片段的最大时长。钩子片段用较短的上限，完整讲解用较长的上限。
  • aspect：Shorts、Reels 和 TikTok 使用 9:16；目标平台需要时可改为 1:1、4:5 或 16:9。

配方选项中还包括字幕样式、语言、纠错和并行控制。

注意事项

即使源视频质量很好，也不一定有你要求数量的合适片段。智能体可能会返回更少的片段，而不是重复同一个观点或剪出弱片段。发布前请在上下文中检查每个片段：断章取义的引用可能丢失原对话中的重要限定。

示例集基于已署名的 OpenClaw 访谈，在一次可恢复的运行中生成。它展示的是输出格式；重新运行时，AI 可能会选择不同的片段。