Video trend
Recast quote videos live or die on the mouth. If the lips move out of time with a famous line, everyone notices. The Brick by Brick template keeps the original speech and makes your speaker say it without you recording anything. Here is how that timing is produced, what can still go wrong and how to check it.
Your video keeps the clip's original audio track, unchanged. Your photos set the faces, not the voice, so the speaker sounds the same whoever you cast. The words cannot be changed, and the original speech contains strong swearing and a racial slur.
Before your people are drawn in, both original men are turned into grey silhouettes with thin lines traced over their faces. The model follows those lines for the speaker's mouth, eyes and expression, frame by frame, so the lips open and close where the original performance did.
The template sends the dialogue as a separate audio reference aligned with the silent motion guide. The model uses the speech and traced mouth movement together. Final assembly restores the original soundtrack; your photos do not change the voice or the words.
The driver's mouth stays closed for the whole clip; only the passenger speaks. If your result shows the driver talking, or both people talking at once, that is a failed run.
Watch the close shot with sound from 0 to 11 seconds and look at the speaker's lips on the loud words, around 3.5, 4.6 and 8 seconds. Then check that the mouth closes for the held stare after 10.7 seconds. Small drift is normal for AI video; if the lips clearly run ahead or behind, run it again.
Add a photo for each role shown below. All roles need a photo.
Upload a clear photo of the person who gives the speech. A sharp face with the whole head visible works best, because the speaker faces the camera for the whole close shot. Everyone pictured should have agreed to appear.
Upload the driver's photo; a side or three-quarter face works, since the driver is seen mostly in profile. Choose 480p, 720p or 1080p and review the quote, which covers the full video and both preparations.
Watch the speaker's mouth through the speech, the driver's closed lips and both faces in the wide windshield shot at 12 seconds, then download your 16:9 MP4 with the original audio.
The Speaker talks for almost 11 seconds; the Driver keeps their eyes on the road and says nothing. Each takes the face, hair, build and outfit from their own photo, so you choose who lectures whom.
All 14 seconds in landscape: the close two-shot through the passenger window with the full speech, then the cut to a wide shot through the windshield of the beige car.
Your video keeps the clip's original voice and timing. You record nothing, and your photo does not change the voice. The audio is explicit: it has strong swearing and a racial slur, so it is not for every audience.
Friends, a boss and an employee, siblings or two characters you designed. The reference performers are replaced by grey silhouettes in the motion guide, so neither of them is reused.
It is a 14-second landscape AI video of a heated talk in the front seat of a beige vintage car. The passenger turns to the driver and delivers the "I built this brick by brick" speech, gesturing with both hands, while the driver keeps looking ahead; then the shot cuts to a wide view through the windshield. Oakgen's template puts your two people in both seats and keeps the car, the cut and the original audio.
The speech is from the TV drama Snowfall (season 3, episode 9, "Blackout"), where it is also said from the passenger seat of a car. The AI clips that spread online re-cast that audio with other faces. This is an unofficial fan-style template that is not connected to the show or its makers, and its picture is not original footage.
Yes. The original speech contains strong profanity and a racial slur, and your video keeps that audio unchanged. Think about where you post it and who will hear it. The template cannot remove or replace words.
No. The video keeps the clip's original voice and timing, whoever is in the photos. You do not record anything.
Yes. The Speaker and the Driver each need a photo, because the motion guide replaces both men from the reference with grey silhouettes, so neither of them is kept.
Only the Speaker, in the passenger seat. The Driver listens with closed lips, hands on the wheel, and only turns their head near the end. Put whoever should give the lecture in the Speaker slot.
Yes. There is no costume. Each person wears the outfit from their own photo instead of the reference's t-shirt and leather jacket.
Your own, or photos of people who agreed to be in the video. Do not upload photos of actors, celebrities or anyone who has not consented, and label AI videos clearly when you share them.
The speaker's mouth follows the timing of the reference performance, and the original audio is restored at the end. These are instructions to a model, so watch the close shot before posting and re-run if the lips clearly drift.
14 seconds in landscape 16:9: about 12 seconds of close two-shot with the speech, then the wide windshield shot.
No. It is the AI reference clip the trend comes from, used as the motion and timing reference, not an Oakgen result. Its two performers are never reused.
2,829 credits per 720p video. The quote includes both photo preparations and the complete video. Check it before generating.
Plan a story, keep your character recognizable, and make the finished clip your own.
Make the Brick by Brick AI car video step by step: choose the speaker and driver photos, read the quote, check the lip timing and post it responsibly.
What the I built this brick by brick line is, why the AI car remakes spread, what is in the audio and how to decide whether to post your own version.
Upload 2 photos. Everything else is set.