Vision-based AI video editing and retrieval tool that can actually see, not just listen
MontSum watches every frame of your footage, so you can retrieve any moment, cut highlights, narrate scenes, and merge clips. Describe what you want and download the result.
How it works
From raw footage to the cut you asked for
Use cases
Describe any moment, retrieve the exact clip.
Multi-video-summary
Analyze several clips to form a single summary.
Many sources → one cut
Upload many videos of various or same topics. One prompt will stitch them into a single summary. Reprompt if you want more options.
Frame Search
Search a video for specific moments.
Full narration
Add professional commentary
Build a vision and audio guided story in your summaries
MontSum generates documentary-grade voiceover, watching the scenes to write and time narration that matches the action — no existing soundtrack required.
Apps add-in
Right inside your editorComing soon
Search footage, cut highlights, and pull the good parts without leaving your timeline. Native add-ins for the montage tools you already use are on the way.
Adobe Premiere Pro
Adobe After Effects
DaVinci Resolve
Final Cut Pro
CapCut
and more