LazyCut

Turning a talking-head recording into a tight vertical short takes time and skill: trimming dead air, cutting filler words and fluffed takes, framing for 9:16 and adding captions. The alternatives were editing it yourself or paying an editor. The brief: let AI do the whole first pass from raw footage, while keeping every AI decision reviewable and adjustable before render.

At the centre is one edit list per video: the AI proposes changes to it, the user adjusts them, and the export is made from the same list, so what you see in the editor is what you get. We designed everything around one clip’s journey, from raw upload to a file ready to post.

1. 1. Upload: a first cut from raw footage

   The system pulls the audio out, transcribes it word by word with timings, finds silences and filler words, and has AI plan the cuts, always snapped to the edge of a word so names are never clipped mid-word. The heavy lifting runs in the background with its progress shown, and every outside AI service can be swapped without touching the editing itself.

2. 2. Finishing touches: emoji, sound effects and memes

   Emoji land on key words, sound effects at the cuts and one or two memes along the way, placed the same way every time and each one removable, along with word-by-word captions in five styles.

3. 3. Review: nothing is cut until you approve

   A CapCut-style browser editor opens on the full take. The cuts the AI proposes are highlighted on the timeline to keep or cut take by take, and the subtitle list is split into sections labelled good take, bad take, dead air or filler, each one a click from its spot in the preview. A multi-track timeline carries B-roll you can position and scale.

4. 4. Export: the file matches what you saw

   The 1080×1920 vertical video is made from the same design as the editor preview, with cuts joined frame-accurately so no flash appears between them, and a Thai font built into the file so Thai captions render correctly.

5. 5. Nothing unproven switched on

   Automatic reframing is in place but stays off until face tracking passes a test on a real render, and the credits and billing system is built but not yet switched on.

The online studio and the background video processing are both live.

• A first cut from raw footage

  Upload a talking-head clip, podcast or screencast, and the AI transcribes it, proposes cuts and adds captions in one pass.

• Every AI change stays editable

  Cuts, captions, emoji, sound effects and memes can all be adjusted or removed in the studio, and nothing is cut until the user approves it.

• Word-by-word captions

  Captions follow speech word by word in five styles, with adjustable font and position, and Thai renders correctly in the export.

• Ready for vertical feeds

  Exports a 1080×1920 vertical video for TikTok, Reels and Shorts.