Upload a photo, write in one sentence what moves in it, and get a video in one to three minutes. A short shot starts at two credits, and you can go up to 30 continuous seconds. And if you want the person in the photo to speak, there is a talking photo too, in Hebrew.
Upload a photo, any photo: a phone picture, an old album print, a drawing or an image you made here. Write in one sentence what happens in it, for example "she turns to the camera and smiles, the wind moves her hair, the camera slowly pushes in". The engine keeps what is already in the picture, the face, the clothes and the place, and adds motion to it. This is the most precise way to make video with AI, because the image has already decided how everything looks and the engine only has to decide how it moves.
Describe motion, not the picture. The picture is already there, so there is no point writing "a woman with brown hair in a park" again. Write what moves, in which direction and at what pace: who moves, what the background does, and what the camera does. One clear motion works better than three. And be careful with a real person's face: motion around the face, a glance, a small smile, a camera pushing in, all of these are safe. A completely new expression, a shout or tears, can change the face, so it is better not to ask for it.
To make the person in the photo speak, you build an avatar from it once, for 16 credits. From there you write a text in Hebrew, pick a voice, and get a video in which the photo speaks with lips synced to the voice. Each video costs about half a credit a second, plus a credit for up to about 750 characters of voice, and the same avatar can come back for as many videos as you like without being rebuilt. It suits a greeting video, an explainer for a business, or a character presenting a product.
A 5-second low-resolution shot costs two credits, and three to four at 720p, by engine. Heavier engines, with sound born together with the picture or a long 30-second take, cost more, and the exact price is shown next to the button before you click. Packs start from $21 for 105 credits, and a generation that fails technically is refunded automatically.
A short shot starts at two credits and the price is shown before you click, so you know exactly what each try costs. And a shot that fails technically goes back to your balance automatically.
One shot runs up to 30 continuous seconds, by engine. A longer video is built from several shots, which you can also do here, with music and captions.
Yes. Build an avatar from the photo once, write a text in Hebrew, and get a video in which the photo speaks with synced lips.
Yes, and it is one of the loveliest uses. Gentle motion works best: a glance, a small smile, a camera pushing in.
Yes, entirely. For personal, business or commercial use.
Home · Pricing · What's new · All engines · All effects · Help center · Lessons · Meital Sela · AI video · AI images · AI voice · AI music · Image to video · What it costs · Credits, not a subscription · Blog · Connect to Claude and ChatGPT · Presets · Privacy · Terms
Cadabra AI · Meital Sela · Rehovot, Israel