What you say to the agent
No special syntax — just describe it like you would to a person.
What it does, step by step
- 1
Give the agent the video and one or more time ranges to keep (in seconds).
- 2
One range trims to just that window; two ranges skip an unwanted middle section; more ranges stitch arbitrary kept segments together in order.
- 3
It renders the cut/concatenated result and returns the URL.
What it needs from you
- •A video to work from
- •Which time ranges to keep
What comes back
A new video containing only the time ranges you asked to keep.
What it costs
A flat per-video processing fee, shown before rendering — not a generative model.
Good to know
- To merge ranges from MULTIPLE different source videos rather than one, use the "stitch multiple clips" capability instead.
Under the hood
This is what the agent actually calls when you ask for it — real tools from its live surface, not marketing copy.
cut_videoCut 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.
See it done in a real workflow
Morning Matcha Routine
UGC-style wellness reel — a clean-girl creator walks through her actual morning matcha ritual, then cuts to a cozy animated hero shot of the finished iced latte.
TrendingNYC Street Interview
Photorealistic street-vlog interview — Riley works three different NYC corners at golden hour asking strangers one question: "What's the wildest thing you've ever done?" Three candid OTS/two-shot clips with locked character references, real handheld energy and native spoken dialogue. Vertical 9:16.
TrendingPrimo Protein vs Other Brand
Pixar-style 3D comparison ad — the confident PRIMO PROTEIN pouch faces off against the tired old rival brand's tub across 11 talking clips: pasture vs dusty pantry, herb garden vs toxic lab, clean American lab vs grimy factory, chocolate-milkshake CTA vs "wet sand." ~40s vertical reel with native character voices.
Or start from a one-tap template
Frequently asked questions
What do I actually say to the agent to trim or cut a video?+
Just describe it in plain English — for example: "Trim this video to just the 5-15 second range" The agent handles picking the right tool and model from there.
What does the agent need from me first?+
At minimum: A video to work from; Which time ranges to keep. Anything else it needs, it asks for before running.
What do I get back?+
A new video containing only the time ranges you asked to keep.
Does this cost credits?+
A flat per-video processing fee, shown before rendering — not a generative model.
Anything I should know before asking for this?+
To merge ranges from MULTIPLE different source videos rather than one, use the "stitch multiple clips" capability instead.
You can also just ask for
Ask your Versely agent to trim or cut a video
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.