Cozy selfie product review
Pick a presenter and add photos of your product. Vidova makes a casual selfie video where they show your product at home and say in their own words why they love it.

What Vidova will do
Make a casual selfie review video of my product, vertical, about 10 seconds, with the presenter picture and the product photos I attached, as if the presenter filmed it at home on their phone's front camera held at arm's length. Write two short spoken lines from my key benefits in plain first-person words, the way a person says them to a friend in one take, with no slogan and no hype words: the first says what the product is to them, the second says the benefit while they show it. Pick one simple hand action that shows the benefit for real, such as holding it to the lens, tapping it, opening it or putting it on, and never a pour, a spill or liquid on a body. Keep my product exactly as it is in my photos: shape, size, colour and material, with no text or logo it does not have. Generate a 2K start frame with the presenter picture and my product photos as references: the presenter on a sofa in a cosy room at home, the phone at arm's length a little above eye level, the face in the upper third, my product held beside the face. Make shot 1 with generate_video at the highest quality with its own sound, 5 seconds, opening on the start frame: the presenter says the first line and brings my product to the lens for a close-up, then back beside the face. Make shot 2 the same way, 5 seconds, from shot 1's frame just after its last word: the presenter shows the benefit in use and says the second line. Watch both shots frame by frame: the face, teeth, hands and my product keep their shape; make a broken shot again. Shot 2 speaks in a new voice, so make the second line in shot 1's voice with generate_speech (shot 1's speech as voiceAssetId), place its words where shot 2's own words fall, and lip_sync shot 2 in dub mode to it. Cut the two shots as one continuous take, each in a pause after its last word, with their room sound and no music. Caption every spoken word with the serif-captions element, short phrases with the word that matters starred, under the chin and never over the face or my product. End on the presenter smiling with my product.




