A transcript is not always the story
A potter centres the clay, shapes the wall, and lifts the finished bowl. There may be almost nothing to transcribe, yet the footage has a clear progression. The key decisions are visual: where to begin, which action to show, and how long to hold the result.
Descript offers text-based editing and other AI capabilities. Choosing a different workflow does not require pretending it only edits transcripts. The question is which controls help you make this particular video.
Sources: Descript: video editing features. Feature descriptions checked 24 September 2026.
Use actions as the outline
List the moments in the source footage. For the pottery example: raw clay, shaping, the rim detail, and the finished bowl. Decide whether the final object should appear at the start as a preview or only at the end as a reveal.
Give Shorty the selected clips and that direction. Add notes about pacing, text, and any optional reference. A brief lets you describe the relationship between shots without needing spoken words to organise them.
Review the continuity
Watch whether the action makes sense from one shot to the next. Does the bowl appear finished and then unfinished without a clear reason? Is a detail shown long enough to understand? Does the ending feel earned?
Keep a manual editing option for jobs where you need exact frame-level control. This guide is published by Shorty and describes a workflow choice, not an independent ranking. Try one visual sequence before moving a larger project. The right tool should make the important decisions easier to express.
A brief to adapt to your footage
Example direction. Replace the subject, shots, and wording with your own.
Build a short visual story from my pottery clips. Show the raw clay, shaping, rim detail, and finished bowl. Use the finished bowl briefly as the opening, then return to the process. Keep the final reveal long enough to see clearly.