A speaking passenger
The passenger follows the reference gestures, mouth movement and held stare.
Video preview
A passenger delivers the speech beside a silent driver, followed by a wide view through the beige car’s windshield.
Two front seats with different jobs
Brick by Brick AI Video puts your chosen adults into a fixed car conversation. The passenger speaks for most of the close shot; the driver listens, keeps their lips closed and turns their head near the end.
Use a separate photo for each seat. Photo 1 supplies the passenger’s identity and outfit, while Photo 2 supplies the driver’s. The same people remain in those roles when the view cuts to the windshield.
The car, the cut and the original voice
The reference controls the beige cabin, window framing, gestures, reactions and cut near the end. It does not use your photo background or add another vehicle or location.
The finished MP4 keeps the original voice, words and timing. Your photos do not supply voices or rewrite the speech. The audio contains strong swearing and a racial slur.
Cast the speech without recording it
A listening driver
The second adult stays at the wheel, with their own face, hair and clothes.
The complete short scene
The 14-second landscape window includes the final wide windshield view.
How to make your video
Choose the speaker and driver
Use two clear adult portraits. Put the person giving the speech in the first slot.
Confirm both people’s permission
Review the explicit original audio, confirm consent and generate for 10 credits.
Review the two-shot and ending
Check lip timing, closed lips on the driver and consistent identities across the cut, then download.
Photos for the close shot and the wide shot
- Keep the speaker’s entire head and hair visible in even light.
- A three-quarter or side view can help describe the driver’s face.
- Choose distinct portraits so the two roles are easy to tell apart.
- Wear the clothes you want each person to have in the scene.
- Review the original audio before choosing who will receive or see the clip.
Frequently asked questions
What is Brick by Brick AI Video?+
It is a two-photo video template that casts a passenger speaker and a listening driver in the fixed 14-second car speech.
How many photos do I need?+
Two. Both slots are required, with one consenting adult per photo.
Who belongs in the first photo slot?+
Photo 1 is the passenger who delivers the speech. Photo 2 is the mostly silent driver at the wheel.
Do we keep our own clothes?+
Yes. Each person’s face, hair, build and visible clothes come from their corresponding photo. The beige car and movement come from the reference.
Does the driver speak?+
The driver follows the reference listening reactions and closed-lip timing. The passenger owns the speech.
Will it use my voice?+
No. The download uses the original reference voice and timing. No voice recording is required.
Is the audio explicit?+
Yes. The fixed original audio includes strong swearing and a racial slur. This template does not edit or replace the words.
How long is the video and what is its format?+
The complete reference window is 14 seconds. The output is a 16:9 landscape MP4 at 720p.
Can I change the car or write different dialogue?+
This template keeps the car, camera cuts and dialogue fixed. It has no custom scene or script input.
Whose photos can I upload?+
Use your own adult photo or photos of adults who have agreed to appear. Both people must be at least 18.
How many credits does a generation use?+
Each video uses 10 ReelTada credits. Sign in and check your balance before starting.
Cast Your Brick by Brick Scene
Add the speaker and driver photos to make the complete car moment.