How to turn several clips into a thank-you video
Upload your clips and photos to Vizard Agent and say who the video is thanking. Vizard Agent transcribes every clip at once, tiles all their frames into a single mosaic, and reads both before cutting. That way it knows what was said and what was shown across the whole set, not clip by clip.
What do you type into Vizard Agent?
Say the occasion plainly: who is being thanked and what for, plus the length, the shape and whether the original voices should carry it. Vizard Agent works out what is in the footage on its own. What it cannot see is the relationship the video is about, and that is what decides whether a clip belongs in the cut.
Prompt
What does Vizard Agent actually do?
It does the slow per-file work in parallel, then collapses the results into one image and one set of transcripts. That way the whole collection can be judged as a whole rather than remembered clip by clip, and a large unsorted upload is not a large amount of waiting. In the session behind this article it:
- Checked the format and extracted the technical details of every uploaded video.
- Ran automatic transcription on every clip in parallel rather than one after another.
- Extracted frames from each video, combined them all into a single mosaic and read it to see what each clip actually showed.
- Checked the working directory for anything else that had arrived, then read the transcription files to verify the words spoken in each clip.
- Delivered a wide cut about a minute long, probed at 1920x1080, H.264, 30fps and 59.2 seconds, with AAC audio.
When does this not work well?
The footage was filmed by people who weren't thinking about a montage, and no edit changes where the camera was pointed. Vizard Agent chooses well among what exists, but it can't supply the shot nobody took or the audio nobody could hear over the crowd. Phone clips from different rooms vary wildly in level, and past a point music over the top is the honest answer. Mixed vertical and wide clips mean some get letterboxed or cropped. And the reason for the thanks has to come from you.
Common questions
Do I need to sort the clips first? No. Vizard Agent inspects and transcribes all of them, so unsorted is the expected input.
Can it mix photos and video? Yes. Upload everything together and Vizard Agent sequences them as one set.
How many clips can it take? A lot. Vizard Agent transcribes them in parallel and reviews their frames as one mosaic, so twenty clips is not twenty times the wait of one.