Inizia
Shorts Slicer - Long Video to Ranked 9:16 Clips

Shorts Slicer - Long Video to Ranked 9:16 Clips

Turn one long video plus its transcript into ready-to-post vertical shorts. Ranked by a published hook score, cut on sentence boundaries only, reframed to 1080x1920 with burned captions, and shipped with titles, captions and hashtags per clip. You also get cutplan.csv, publish.csv and the exact ffmpeg commands, so the same transcript and flags always produce the same plan. No speech recognition, no face tracking, no promises about reach.
#Video#Social media#Produttività
Valutazione
Servono altre valutazioni
Venduti
0
Come si usa
Esegui su Capafy
Anche su app esterne
Fornito dal publisher
deepseek-flash

Paste a long video, get a ranked cut plan

Bring the video and its .srt / .vtt. The tool proposes windows at sentence boundaries, scores each one with a published rule list, and renders only the winners - so nobody has to re-watch the timeline to find out why clip 3 was chosen.

What lands in the output folder

File What it is
plan/cutplan.csv rank, start, end, length, hook score, hook type, opening line
plan/publish.csv title, caption, hashtags per clip
clips/clip-N.mp4 1080x1920, 30fps, H.264 + AAC, -16 LUFS, captions burned in
captions/clip-N.srt / .ass clip-relative captions, <= 42 characters per line
thumbs/clip-N.jpg frame at 0.8s of the finished clip
report.json plan hash, per-clip bytes, verification output

Why the cut is reproducible

A clip is a pure function of (transcript, clip count, min length, max length, platform). Run the same job next month and cutplan.csv matches. The score is arithmetic from references/hook-weights.md, not a model's mood.

Reframe, not crop

Landscape sources get a blurred fill behind a centred picture, so no speaker is cut out of frame. The creator's own audio is normalised; no music is added.

Limits, stated before purchase

  • No speech recognition. A transcript is required.
  • No face tracking, no auto B-roll, no auto zoom.
  • No translation - captions stay in the transcript's language.
  • No promises about reach, retention or revenue. The platform decides distribution.
  • 2h+ videos work, but rendering is roughly 1x realtime per clip on one core.

Built for podcasters, coaches, course sellers, editors and agencies sitting on hours of footage they never reposted.