Video lungo → più clip con sottotitoli, in un solo comando
Trasforma qualsiasi video lungo in N clip più brevi con sottotitoli. Trascrivi una volta sola, lascia che l'IA scelga i momenti migliori, poi taglia e sottotitola ogni clip in parallelo. Se vuoi, adatta il risultato al formato verticale (9:16) per TikTok, Reels e Shorts, quadrato (1:1) per Instagram o ritratto (4:5); la posizione dei sottotitoli si regola automaticamente.
Ricette
Esegui
Agente dell'IA
terminale
Prima volta qui? Avvio rapido
brew install pipe2-ai/tap/pipe2 go install github.com/pipe2-ai/pipe2-cli/cmd/pipe2@latest Ottieni un token API ↗
echo "$PAT" | pipe2 auth login --token - 5 clip da un episodio
Modifica il risultato
| Input | Tipo | predefinito | Descrizione |
|---|---|---|---|
--input | asset_url | predefinito— | 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 | predefinito | 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 +29:161:14:516:9 |
--highlights-count | int | predefinito5 | How many moments to pick when highlights runs (auto mode). Ignored if --clips is set. |
--highlights-style | string | predefinito | Natural-language steer for the highlights picker: e.g. "the funniest moments", "the strongest arguments". Empty uses the picker's default. |
--clips | string | predefinito | 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 | predefinito | 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 | predefinitoen | ISO 639-1 transcription language, or 'auto'. |
--no-watermark | bool | predefinitofalse | Ship the output unbranded. Skips the watermark step entirely. |
--parallel | int | predefinito4 | Max number of clips to process in parallel. |
--position | enum | predefinitoauto | 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 +1autotopmiddlebottom |
--preset | enum | predefinitoserif-editorial | Caption styling preset for every clip.tiktok-bold-yellow · minimal-white · subtle-drop +3tiktok-bold-yellowminimal-whitesubtle-dropkaraoke-gradientbig-serifserif-editorial |
--watermark-scale | int | predefinito20 | Watermark width as a percentage of the video width. |
--watermark-url | asset_url | predefinito | Override the default Pipe2 logo with your own image (URL or local path). Empty means use the bundled Pipe2 watermark. |
--watermark-variant | enum | predefinitolight | 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 +4amberaquacrimsondarkemeraldindigolight |
-
Trascrive una volta l'intero video sorgente e riutilizza la stessa trascrizione per ogni clip selezionata.
Fonte di input: OpenClaw Creator, Why 80% of Apps Will Disappear00:00:00,180 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. … -
Legge la trascrizione e sceglie N momenti rilevanti. Se --clips fornisce un elenco JSON preparato manualmente, la selezione automatica viene saltata.
[{"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}] -
Taglia ogni estratto selezionato sui confini di frase e restituisce la trascrizione corrispondente, pronta per i sottotitoli.
-
Quando è impostato --reformat, adatta ogni clip alle proporzioni richieste, mantiene visibile il parlante attivo e cambia inquadratura con tagli puliti tra i piani. In caso contrario conserva le proporzioni originali.
-
Aggiunge a ogni clip la trascrizione corrispondente, con lo stile e la posizione dei sottotitoli scelti.
-
Sovrappone nell'angolo in alto a sinistra il logo Pipe2 o l'immagine indicata in --watermark-url. Usa --no-watermark per produrre le clip senza filigrana.