Vidéo longue → plusieurs clips sous-titrés en une seule commande · Recettes

Recettes

Exécuter

Vidéo
6 pipelines
≥ 11.6 crédits

Agent IA

Terminal

Vous débutez ? Démarrage rapide

Homebrew brew install pipe2-ai/tap/pipe2

↳

Go go install github.com/pipe2-ai/pipe2-cli/cmd/pipe2@latest

Obtenir un jeton d'API ↗ echo "$PAT" | pipe2 auth login --token -

5 extraits d'un épisode

Modifier le résultat

Par page

Entrée	Type	par défaut	Description
`--input`requis	asset_url	par défaut—	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`	enum	par défaut	Optional 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`	int	par défaut5	How many moments to pick when highlights runs (auto mode). Ignored if --clips is set.
`--highlights-style`	string	par défaut	Natural-language steer for the highlights picker: e.g. "the funniest moments", "the strongest arguments". Empty uses the picker's default.
`--clips`	string	par défaut	Optional 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`	string	par défaut	Comma-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`	string	par défauten	ISO 639-1 transcription language, or 'auto'.
`--no-watermark`	bool	par défautfalse	Ship the output unbranded. Skips the watermark step entirely.
`--parallel`	int	par défaut4	Max number of clips to process in parallel.
`--position`	enum	par défautauto	Vertical 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`	enum	par défautserif-editorial	Caption styling preset for every clip. tiktok-bold-yellow · minimal-white · subtle-drop +3 `tiktok-bold-yellowminimal-whitesubtle-dropkaraoke-gradientbig-serifserif-editorial`
`--watermark-scale`	int	par défaut20	Watermark width as a percentage of the video width.
`--watermark-url`	asset_url	par défaut	Override the default Pipe2 logo with your own image (URL or local path). Empty means use the bundled Pipe2 watermark.
`--watermark-variant`	enum	par défautlight	Which 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`

Fonctionnement 6 pipelines

transcription

Transcrit une fois la vidéo complète et réutilise cette transcription pour tous les clips sélectionnés.

Source d’entrée: OpenClaw Creator, Why 80% of Apps Will Disappear

Texte

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.
…

highlights

Lit la transcription et sélectionne N passages intéressants sur le plan éditorial. Cette étape est ignorée lorsque --clips contient une liste JSON définie manuellement.

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}]

video-trim

Découpe chaque passage entre deux phrases complètes et fournit la transcription correspondante pour les sous-titres.

Vidéo
video-reframe seulement si --reformat

Avec --reformat, adapte chaque clip au format demandé, garde l’intervenant actif dans le cadre et change proprement de cadrage aux changements de plan. Sans cette option, le format d’origine est conservé.

Vidéo
captions

Ajoute à chaque clip sa transcription dans le style et à la position de sous-titres choisis.

Vidéo
watermark

Ajoute le logo Pipe2, ou celui indiqué par --watermark-url, dans le coin supérieur gauche afin de conserver l’attribution lors des republications. Utilisez --no-watermark pour ignorer cette étape.

Vidéo