Launching soon — early access

Your podcast, cut into clips worth posting

AI Clip Cutter transcribes your long-form video with word-level timestamps, scores every candidate moment 0–10, and exports the winners as 9:16 clips with captions burned in — each one with the reason it was picked, so you stay the editor.

Free 10 credits at launch · No card required · No spam

You're on the list.

We'll email you the moment launch opens. Check your inbox.

3-Step
Upload → Score → Export
0
Caption presets
0–10
AI score per moment
0
Engagement dimensions
How it works

Three steps, and you approve every one

Nothing runs automatically. Analysis waits for you to press the button — and costs nothing until you do.

01

Upload your long video

Drop in a podcast, interview, or webinar — mp4, mov, webm, or mkv, up to 1024 MB. It streams straight to disk, ffprobe reads the duration and dimensions, and anything without an audio track is rejected before it costs you a credit.

ffprobe
02

The AI finds the best moments

Audio is downmixed to 16 kHz mono and transcribed by Whisper with word-level timestamps. Candidate windows of 18–75 seconds are scored 0–10 by GPT-4o on four dimensions. Every pick arrives with a plain-English reason, so you can overrule it.

Whisper GPT-4o
03

Export with captions burned in

A straight cut reframed to 9:16 with a blurred background or centre crop, encoded H.264 + AAC at 1080×1920. Captions are burned in word by word through libass. Trim points stay editable — captions rebuild against the new origin.

FFmpeg libass
Features

Built to be checked, not trusted blindly

The AI argues for every clip it picks. You read the reasoning, adjust the numbers, and decide.

01 / Transcription

Word-level Whisper timestamps

Captions land on the word, not the sentence. Groups break on punctuation or a pause of 0.35 s or more, so captions never flicker off during a natural gap.

02 / Selection

Ranked, non-overlapping picks

Up to 48 candidate windows are kept and spread across the whole timeline, then scored as 30% hook, 25% self-contained, 25% density, 20% emotion. The best non-overlapping set wins.

03 / Reasoning

A stated reason per clip

Every selected moment carries the model's plain-English reason plus its four scores, shown beside the clip. You are reading an argument you can reject, not a black-box list.

04 / Control

Trim points are editable numbers

In and out points are fields, not a fixed decision. Saving a new trim regenerates the caption groups against the new origin without re-encoding.

05 / Pricing

Credits, charged in rupees

1 credit per minute of source video to analyse, 1 credit per exported clip, both shown on the button before you press it. Billed in INR through Razorpay; a failed pipeline refunds automatically.

06 / Captions

Eight burned-in presets

Hormozi, Beast, Karaoke, Minimal, Boxed, Neon, Podcast, Bounce — each drawn from the same preset table the ASS writer hands to libass. The spoken word highlights in real time.

What it does not do
  • No face tracking — 9:16 blurs a background copy by default
  • No b-roll, zooms, or transitions — straight cuts only
  • No speaker diarisation
  • 1080×1920 is the ceiling — no 4K preset
  • Scoring and hook prompts are English-tuned

Run one real episode through it

Signing up grants 10 credits — enough to analyse a short video and export a few clips. No card, and nothing renews on its own.

Free 10 credits at launch · No card required · No spam

You're on the list.

We'll email you the moment launch opens. Check your inbox.