긴 영상 하나로 자막이 들어간 클립 여러 개 만들기

긴 영상을 자막이 들어간 짧은 클립 N개로 나눕니다. 전체 영상은 한 번만 전사하고, AI가 주요 장면을 고른 뒤 각 클립의 트리밍과 자막 작업을 병렬로 처리합니다. TikTok, Reels, Shorts용 세로 화면(9:16), Instagram용 정사각형(1:1)이나 세로형(4:5)으로도 바꿀 수 있으며, 자막 위치는 화면 비율에 맞춰 자동 조정됩니다.

레시피

실행

  • 비디오
  • 파이프라인 6개
  • ≥ 11.6 크레딧

AI 에이전트

단말기

처음 오셨나요? 빠른 시작
01
Homebrew brew install pipe2-ai/tap/pipe2
↳
Go go install github.com/pipe2-ai/pipe2-cli/cmd/pipe2@latest
02
API 토큰 발급 ↗ echo "$PAT" | pipe2 auth login --token -

한 에피소드의 5 클립

결과 변경

--input필수
asset_url기본값—Source video: a YouTube or social URL, a direct media URL, a local file, or an existing pipe2 asset. Remote and local sources are uploaded automatically; use --asset <id> or --no-fetch when the asset is already available.
--reformat
enum기본값Optional output aspect ratio. Leave empty to preserve the source's native aspect (default: fastest, cheapest). Set to 9:16 for TikTok/Reels/Shorts, 1:1 or 4:5 for Instagram, 16:9 for horizontal YouTube cards from a vertical source.
· 9:16 · 1:1 +2
9:161:14:516:9
--highlights-count
int기본값5How many moments to pick when highlights runs (auto mode). Ignored if --clips is set.
--highlights-style
string기본값Natural-language steer for the highlights picker: e.g. "the funniest moments", "the strongest arguments". Empty uses the picker's default.
--clips
string기본값Optional path to a JSON file overriding the auto-picker, shaped [{"context": "...", "start_sec": 42.5, "end_sec": 78.0}, ...]. When set, the highlights step is skipped. Leave empty to let the highlights pipeline pick automatically.
--corrections
string기본값Comma-separated word-boundary substitutions applied to the transcript, in the form "from=to,from=to". Use it when the recognizer mis-hears the same word the same way every time (a name, an acronym, a domain term). To preserve a phrase that contains a substring you also want to rewrite, declare the longer phrase first as a no-op ("phrase=phrase,word=replacement"): longer matches win, so the phrase is shielded before the bare-word rule fires. Case-sensitive.
--lang
string기본값enISO 639-1 transcription language, or 'auto'.
--no-watermark
bool기본값falseShip the output unbranded. Skips the watermark step entirely.
--parallel
int기본값4Max number of clips to process in parallel.
--position
enum기본값autoVertical caption position. "auto" (default) keeps text away from the main subject when possible and otherwise places it at the bottom. Set a position explicitly to override.
auto · top · middle +1
autotopmiddlebottom
--preset
enum기본값serif-editorialCaption styling preset for every clip.
tiktok-bold-yellow · minimal-white · subtle-drop +3
tiktok-bold-yellowminimal-whitesubtle-dropkaraoke-gradientbig-serifserif-editorial
--watermark-scale
int기본값20Watermark width as a percentage of the video width.
--watermark-url
asset_url기본값Override the default Pipe2 logo with your own image (URL or local path). Empty means use the bundled Pipe2 watermark.
--watermark-variant
enum기본값lightWhich bundled Pipe2 logo to use when --watermark-url is empty. "light" for dark videos, "dark" for bright ones; coloured variants match the clip palette.
amber · aqua · crimson +4
amberaquacrimsondarkemeraldindigolight
작동 방식 파이프라인 6개
  1. transcription

    전체 영상을 한 번만 전사하고, 선택된 모든 클립에서 같은 전사문을 다시 사용합니다.

    입력 소스: OpenClaw Creator, Why 80% of Apps Will Disappear
    텍스트 
    00:00:00,180  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.
00:00:09,060  The GitHub repo exploded to over 160,000 stars practically overnight.
00:00:14,130  The community has built countless projects, like Malt Book, where bots talk among themselves.
00:00:19,560  And now, the bots are even renting humans to do tasks in the real world.
00:00:24,220  In our conversation, we discuss his aha moment, his contrarian development philosophies, and what this means for builders in 2026.
00:00:32,740  Let's dive in.
00:00:38,980  So good to see you, man.
00:00:39,960  Hey, what's up?
00:00:40,760  Um, so you've made something people want.
…
  2. highlights

    전사문을 읽고 편집하기 좋은 장면 N개를 고릅니다. --clips로 수동 JSON 목록을 제공하면 자동 선택 단계는 건너뜁니다.

    JSON 
    [{"context":"Peter explains OpenClaw's core differentiator: local execution gives it access to everything the user can do, unlike cloud-based AI.","desired_seconds":32,"start_sec":95.24000000000001,"end_sec":127.64},{"context":"The vivid moment Peter realized OpenClaw's creative problem-solving: it autonomously transcribed a voice message using ffmpeg and OpenAI's API without being explicitly programmed to do so.","desired_seconds":106,"start_sec":515.182,"end_sec":621.252},{"context":"Peter's contrarian prediction: 80% of apps disappear because personal AI agents manage data and tasks more naturally than purpose-built applications.","desired_seconds":55,"start_sec":641.792,"end_sec":696.312},{"context":"Peter's philosophy on building: minimize friction by using Unix tools and CLIs instead of inventing new abstractions, letting the model handle creative problem-solving.","desired_seconds":54,"start_sec":1178.264,"end_sec":1232.584},{"context":"Peter articulates why swarm intelligence mirrors human society: individuals alone can't build iPhones or go to space, but groups specializing together achieve anything.","desired_seconds":46,"start_sec":258,"end_sec":303.5}]
  3. video-trim

    선택한 각 구간을 문장 경계에 맞춰 자르고, 자막에 사용할 클립별 전사문을 함께 반환합니다.

    비디오
  4. video-reframe 경우에만 --reformat

    --reformat을 설정하면 각 클립을 지정한 화면 비율로 바꾸고, 현재 말하는 사람이 화면 안에 머물도록 하며, 샷 경계에서 자연스럽게 구도를 전환합니다. 설정하지 않으면 원본 화면 비율을 유지합니다.

    비디오
  5. captions

    해당 전사문을 선택한 자막 스타일과 위치에 맞춰 각 클립에 추가합니다.

    비디오
  6. watermark

    왼쪽 위에 Pipe2 로고(또는 --watermark-url로 지정한 로고)를 넣어 재게시된 뒤에도 출처가 드러나게 합니다. 워터마크를 빼려면 --no-watermark를 지정하세요.

    비디오