Langes Video → mehrere untertitelte Clips mit einem Befehl

Zerlege ein langes Video in N kürzere Clips mit Untertiteln. Transkribiere die Aufnahme einmal, lass die KI geeignete Momente auswählen, schneide alle Clips parallel und füge die Untertitel hinzu. Auf Wunsch kannst du ins Hochformat (9:16) für TikTok, Reels oder Shorts, ins Quadrat (1:1) für Instagram oder ins Porträtformat (4:5) wechseln; die Position der Untertitel passt sich automatisch an.

Rezepte

Ausführen

  • Video
  • 6 Pipelines
  • ≥ 11.6 Credits

KI-Agent

Terminal

Neu hier? Schnellstart
01
Homebrew brew install pipe2-ai/tap/pipe2
Go go install github.com/pipe2-ai/pipe2-cli/cmd/pipe2@latest
02
API-Token holen ↗ echo "$PAT" | pipe2 auth login --token -

Ergebnis ändern

--inputerforderlich
asset_urlStandardSource 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
enumStandardOptional 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
intStandard5How many moments to pick when highlights runs (auto mode). Ignored if --clips is set.
--highlights-style
stringStandardNatural-language steer for the highlights picker: e.g. "the funniest moments", "the strongest arguments". Empty uses the picker's default.
--clips
stringStandardOptional 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
stringStandardComma-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
stringStandardenISO 639-1 transcription language, or 'auto'.
--no-watermark
boolStandardfalseShip the output unbranded. Skips the watermark step entirely.
--parallel
intStandard4Max number of clips to process in parallel.
--position
enumStandardautoVertical 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
enumStandardserif-editorialCaption styling preset for every clip.
tiktok-bold-yellow · minimal-white · subtle-drop +3
tiktok-bold-yellowminimal-whitesubtle-dropkaraoke-gradientbig-serifserif-editorial
--watermark-scale
intStandard20Watermark width as a percentage of the video width.
--watermark-url
asset_urlStandardOverride the default Pipe2 logo with your own image (URL or local path). Empty means use the bundled Pipe2 watermark.
--watermark-variant
enumStandardlightWhich 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
So funktioniert es 6 Pipelines
  1. Transkribiert die vollständige Aufnahme einmal und verwendet dieses Transkript für alle ausgewählten Clips.

    Eingabequelle: OpenClaw Creator, Why 80% of Apps Will Disappear
    Text
    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. Liest das Transkript und wählt N redaktionell geeignete Momente aus. Dieser Schritt entfällt, wenn --clips eine manuelle JSON-Liste enthält.

    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. Schneidet jedes ausgewählte Zeitfenster an vollständigen Satzgrenzen und liefert ein passendes Clip-Transkript für die Untertitel.

    Video
  4. video-reframe nur wenn --reformat

    Mit --reformat wird jeder Clip in das gewünschte Seitenverhältnis gebracht, der aktive Sprecher bleibt im Bild und der Ausschnitt wechselt sauber bei jedem Szenenwechsel. Ohne diese Option bleibt das ursprüngliche Seitenverhältnis erhalten.

    Video
  5. Fügt jedem Clip das passende Transkript im gewählten Untertitelstil und an der gewählten Position hinzu.

    Video
  6. Blendet oben links das Pipe2-Logo oder das mit --watermark-url angegebene Logo ein, damit die Quellenangabe auch bei erneuter Veröffentlichung erhalten bleibt. Mit --no-watermark überspringst du diesen Schritt.

    Video