Skip to content

Use case

Turn one long upload into a week of vertical posts.

One recording carries more than one short video. It is transcribed with word-level timings, the moments come back scored, and each one is cut to vertical 9:16 with the captions in the picture.

Source

One long file in.

MP4, MOV or WebM, within your plan's size and length ceilings. Before the run you choose the clip length, from 10 to 180 seconds as far as your plan reaches.

The upload panel, with a source file staged and the run settings on the right.
Transcript

Word timings drive the cuts and the captions.

The recording is transcribed with word-level and segment-level timings. The same timings place each cut on a word edge and light up each word as it is spoken in the finished clip.

The same workspace while a run is still cutting.
Candidates

Several clips out of one upload.

Every strong qualifying candidate comes back up to your plan's limit, ordered by score and carrying its ranges, title, description and three to eight hashtags.

One finished clip as it appears in the list.
Output

A stack of vertical posts from one recording.

Every clip renders vertical at 9:16, 1080 x 1920 or 720 x 1280. When captions are enabled, they are burned in; 12 presets are the starting points, and the font, size, colours, outline or box, position and words per line behind them are yours to set. Fill-frame crops to the centre of the source; the default pads with a blurred copy instead. Your handle can be burned in under the captions.

The clips workspace, rendered by the app's own components with a sample run.

Sample run

What one 31-minute take returned.

A single desk-setup recording, one run, three posts. The ledger below is that run's own arithmetic, and the clip list beside it is the same three clips it produced.

Source file
desk-setup-review-take2.mp4
Length
30:46
Credits charged
31
Clips returned
3
Ranges cut
3 across 3 clips
Highest score
8.2
That clip's title
The cheapest thing on this desk is the one I would replace last
Start clipping
The clips workspace, rendered by the app's own components with a sample run.

The parts that matter here.

AI clipping
Reframe
Captions

What a run costs.

The charge follows the upload, not the output. A 30:46 take costs 31 credits, and every clip cut from it is inside that number: three posts and twelve posts bill identically.

See pricing

Other recordings this works on.

Podcasts

Turn a 60-minute episode into a queue of reviewable vertical cuts.

Interviews

Find the compact answer without replaying the full recording.

Webinars

Pull reusable teaching moments out of a long session.

Business content

Cut the recordings your team already has into short clips.

Questions about long uploads.

Every strong qualifying moment the AI finds, up to the cap your plan sets. The run costs the same whether the recording contains one strong moment or many.

One of five bands, set before the run: 10 to 35, 15 to 60, 30 to 90, 60 to 120 or 90 to 180 seconds, as far as your plan reaches. The model chooses the original range. While the source is retained, you can shorten the generated clip or re-extend it inside its original timeline, but you cannot pick a new source moment.

Yes, while its source is still retained. You can change the caption text, caption style, framing, burned-in title and boundaries inside the clip's original timeline, then re-render without spending credits. Once the source expires or is deleted, the finished MP4 stays downloadable but can no longer be edited or re-rendered.

Each candidate carries a title, a description of one to three sentences written in the speaker's tone, three to eight hashtags and a score from 0 to 10. You copy them out of the clip list yourself: nothing is posted for you, because a finished clip is an MP4 you download.

Yes, while the source is retained with READY status. Start from one of 12 named presets, then set the font from 7 faces, the size, the weight, uppercase, the base and highlight colours, the outline colour and width, the shadow, a solid background box, the vertical position and the words per line. A style carries an outline or a background box, never both, because the renderer's box replaces the outline instead of sitting behind it. Free plans get 2 presets and their highlight colour; paid plans get all 12 and every field.

Ready when the recording is

One upload is already a week of posts.