Features

AI montage

One clip out of everything they sent

Sometimes the output you need is a video. Twenty people answered on camera, you have twenty files and no evening free — say what the piece should be, and get a cut back.

AI montageCutting 10 clips · 1:05
0:000:100:200:300:400:50
captions · sentiment · transcript

A sentence, not a control panel

"A two-minute cut where fans argue about the opening track." That sentence is the whole brief. It gets compiled into a program and a tone, and those decide what survives and in what order.

It cuts on words, not on the clock

Cut points come from the audio and the transcript, so a clip starts on a breath and ends on a full stop instead of slicing a syllable in half.

Vertical, square and wide from the same cut

One montage renders 9:16, 4:5 and 16:9. The frame follows the speaker rather than letterboxing them into grey bars.

What actually happens

Same answers plus same brief produce the same script, every time. "Regenerate" means "change the brief", not "roll the dice again". You get a coverage figure telling you what was dropped and why, and it disappears the moment you start trimming by hand — a statistic about a script you've since rewritten is worse than none.

Then it's an editor, not a black box. Trim, reorder, drop a clip, change the cut style, burn captions from the transcript. Every cut gets a soft audio edge so nothing clicks.

Your audience has something to say.

Give them a way to say it. We'll walk through what Wall of Voice could look like for your audience.

See what Wall of Voice could look like for your audience.