Every page in this cluster performs the same operation with a different destination attached, and the interesting part is never the ratio — it is what you give up to reach it. Going from widescreen to vertical throws away roughly two thirds of the width, so the only real question is whether the subject gets re-framed or the missing space gets filled.
Reformatting also sits at a specific point in the pipeline: after the cut, before captions and before any upscale. Do it later and you are paying to re-render text you already burned in, or resolution you are about to crop away.
The order to run these in
These jobs are cheap in the right sequence and expensive in the wrong one. This is the order that avoids re-rendering work you have already paid for.
1. Decide the destination
Vertical for short-form feeds, square for in-feed placements, widescreen for long-form and sites. The destination decides the crop, not the other way round.
2. Choose crop or pad
Crop when the subject can be re-framed and stay legible. Pad or extend the background when it cannot — a cropped-off head is worse than a letterbox.
How to do it →3. Re-frame the subject
Vertical is a portrait format: the subject belongs in the upper middle, clear of the caption zone and the platform's own interface.
How to do it →4. Then caption, then upscale
Both steps are frame-dependent. Doing either before the reformat means doing it twice.
Every job in this cluster
Each one names the real Versely agent tool that performs it, so you can see which jobs share a mechanism and which are genuinely different work.
Change a Video's Aspect Ratio
One clip. Any frame.
edit_videoMake a Video Vertical
Landscape in. Full-screen mobile out.
edit_videoResize a Video for TikTok
Reformatted, trimmed, ready to post.
edit_videoConvert a Video to Shorts
Find the best 30 seconds. Reformat it. Post it.
cut_videoCrop a Video to Square
Full-frame square, ready for the feed.
edit_videoConvert a Vertical Video to Horizontal
Phone-shot footage, made presentation-ready.
edit_videoPick the Right Format for Each Platform
Reformat toward what your account already proves works.
get_content_insightsThe agent tools behind them
5 tools from Versely's real agent surface do all 7 of these jobs. Ask for the outcome in plain English and the agent picks the tool.
edit_video
Agent-driven EDL render via the Versely editor pipeline (POST /features/editor-render). Stitch, trim, speed-change, caption, overlay, and mix user media (workspace/generation HTTPS URLs) into ONE final video. Prefer this over chaining cut_video + attach_audio + add_*_captions when the user wants a multi-clip assembly in a single step. Billing: preview:true is free 480p (per-user cooldown); final export (preview:false, default) charges the normal single editor_export price. Prefer preview:true while the user is iterating; only final-render after confirmation. Clips must be HTTPS URLs (file:// and other schemes rejected). Returns { video_url, credits_charged, preview_notes } or a 402-style insufficient-credits error.
cut_video
Cut a single video down to one or more time ranges and concatenate the kept ranges into a single output video. Covers three intents in one tool: (1) TRIM — pass one segment to keep just [start, end). (2) CUT OUT a middle section — pass two segments [0, badStart] and [badEnd, end] to skip the unwanted middle. (3) SPLIT-AND-KEEP arbitrary ranges — pass N segments and they're stitched in the given order. Segments are kept ranges (NOT delete ranges), all in seconds from the start of the source video. The output is uploaded to cloud storage and the URL is returned. If you want to merge across MULTIPLE source videos (with optional per-clip trims), use compose_video_with_overlay instead — its base_media[] accepts start_sec/end_sec per video item.
get_content_insights
Analytics-driven content strategy summary for the user's recent social posts — by platform and format (image/video/carousel/text): post counts, avg/median views & engagement, top 3 posts, best posting hour/day when timestamps allow. Use BEFORE creating content explicitly for the user's social channels to recommend what format/platform performs best. Not a mandatory gate — offer insights when planning social content.
get_social_analytics
Get analytics overview for the user's social media posts — total engagement, views, likes, platform breakdown, and top-performing posts. Use when the user asks about their post performance, engagement rates, or social media stats.
analyze_content
Analyze a previously generated image or video for quality, composition, and suggest improvements. Use when the user asks for feedback on a generation or wants to iterate. Pass the generation ID or 'latest'.
What these jobs cost
Every job here bills in credits. These are the scenarios whose formulas govern the arithmetic.
Questions about this cluster
Will resizing cut off my subject?+
It will if you crop without re-framing. A centred widescreen subject often survives a vertical crop; anything at the edges will not. Re-frame around the subject, or keep the full width and fill the remaining space instead.
Which aspect ratio should I generate first?+
The one you publish most. For almost everything short-form that is 9:16, and the widescreen version is derived from it rather than the reverse — going up in width means inventing pixels that were never filmed.
Does reformatting lose quality?+
A crop reduces the pixels you keep, so the smaller the region you crop to, the softer the result. Reformat from the highest-resolution source you have, and upscale afterwards if the destination needs it.
Make the material first
The rest of the pipeline
Captions & On-Screen Text
The last thing you add and the first thing anyone reads.
Audio, Voice & Dubbing
The biggest cluster on the surface, and the easiest to do in the wrong order.
Trim & Cleanup
Do these before you pay to render anything.
Upscale & Extend
The only jobs that add something the file never had.
Merge & Assemble
Where the pieces stop being clips and start being a video.
Ask the agent for it in plain English
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.