A ready-to-use Driver Put Phone Away prompt for Veo

Updated:

Short answer

Drop the prompt below into Veo with your photo attached, vertical 9:16, roughly 14 seconds. Inside: the cab, one fixed camera, five beats and no speech. A few retries are normal, and timing will be rougher without a timing guide.

Picture from the example clip: bearded driver, minibus cab, one angry glare at the camera,Imagen de muestra: un hombre con barba al volante de una furgoneta, vuelto hacia la cámara para gritar,Imagem de exemplo: um homem barbudo ao volante de uma van, virado para a câmera e gritando
Picture from the example clip: bearded driver, minibus cab, one angry glare at the cameraImagen de muestra: un hombre con barba al volante de una furgoneta, vuelto hacia la cámara para gritarImagem de exemplo: um homem barbudo ao volante de uma van, virado para a câmera e gritando

The prompt

Task: image-to-video at 9:16, around 14 seconds.
CHARACTER = reference image 1, the minibus driver. Treat the face, hair, skin tone and build in that image as fixed. The CHARACTER is an adult.
Outfit: whatever the photo shows.
Setting: the front of a small passenger minibus, right-hand-drive cab, seen from the passenger side. The driver's seat is on the left of the frame with a big steering wheel to its right and pale curtains with fringe tassels. A padded fare counter in the foreground holds a plain card terminal, a few coins and a smartphone. Nothing carries a brand name or printed text.
Camera: a single locked-off, handheld-style view from a passenger's seat, like someone filming the driver on the sly. No cuts.
Beat 1 (0-2s): seated sideways at the wheel, the CHARACTER looks back over a shoulder at the camera with an annoyed stare.
Beat 2 (2-3s): a brief look at the road ahead, then back toward the camera.
Beat 3 (3-6.5s): turns right round to face the camera, mouth wide, and throws both hands open with the palms up, shouting angrily at whoever is filming. Loud and furious, but no clear words.
Beat 4 (6.5-9s): keeps scolding the camera with short head shakes and hand waves, then shrugs in disbelief.
Beat 5 (9-14s): the CHARACTER turns to the front again, shoulders dropping and hands resting low, and keeps staring through the windshield, never glancing at the camera again.
Audio: furious shouting with no clear words, a faint engine hum, coins rattling. No music, no singing, no lyrics. If anyone speaks at all, English only.
Look: photorealistic and natural in colour. No text, captions, logos or watermark.

Tips for Veo

  • A bright, sharp head-and-shoulders photo gives the best face.
  • Ask for a clip of roughly 14 seconds.

Questions people ask

Can Veo hold on to my face?

It often can, if the photo is crisp and well lit. Judge it at the moment the head swings to the camera, roughly a fifth of the way through.

Does the prompt mention a song or a real person?

Neither. It only describes the scene, so no song title, artist or real person is in it.

Will the result match Ozil Goal AI exactly?

Not quite. Every tool moves in its own way, and Ozil Goal AI also feeds this template a timing guide. Take the prompt as a starting point.

Take the wheel: make your own video

Add one photo. Every pack includes bonus previews, so you can check your photos before spending a credit. The finished video carries no watermark. Nothing to subscribe to.

Make my video