Quick answer
Starrd's Like 700 MPH template recreates the viral 'like 700 mile per hour' interview meme from two photos. Photo 1 is the driver, the slow, slack-jawed one who says his favourite car is a 2006 Lamborghini Gallardo and that the fastest he has ever driven is "probably like 700 mile per hour", then "777", "on the highway". Photo 2 is the interviewer, who gets more confused with every answer. The full 29-second clip is rebuilt shot for shot, all 17 cuts in a wood-panelled boardroom, with both people lip-syncing the original audio and keeping their own look. Vertical 9:16, Seedance 2.5, 250 credits (about $12.50).
Two photos in, and out comes you and a friend recreating the viral "like 700 mile per hour" interview: one of you is the deadpan driver who hit 777 mph on the highway in a 2006 Lamborghini Gallardo, the other is the interviewer losing their mind. All 17 shots, every line lip-synced. Here it is:
Like 700 MPH
Two photos. One of you swears they hit 777 mph on the highway, the other can't believe it. The full 29-second interview meme, lip-synced.
What You Get
- The whole interview. All 29 seconds and all 17 cuts, at the same moments as the original.
- Two people, two roles. Photo 1 is the driver, photo 2 is the interviewer, and nobody ever swaps.
- Real lip sync. Both of you mouth your own lines to the original audio, and the listener keeps a straight, still face while the other one talks.
- The performances. The driver's slack jaw, head tilts and eye rolls to the ceiling; the interviewer's squint, knitted brows and dropped jaw on "700?".
- The original camera. Three-quarter close-ups, the low wide shot across the table, and the punch-in on "777".
- 29 seconds, vertical 9:16, ready for TikTok, Reels and Shorts.
What the Meme Actually Is
The clip was posted by @tyreesegulpington on October 11, 2026, captioned "Meme coin dropping soon in discord!", and passed 8.2 million plays, 500,000+ likes and 100,000 shares within days. It's a sit-down interview in a corporate boardroom: a serious interviewer, and a character in a big orange bowl-cut wig, gold grills and a chain who answers every question like he just woke up.
The whole joke is the escalation. He doesn't say 700 once: he says it four times, then upgrades it to 771, then 777, drawn out over four seconds, while the interviewer slowly realises that's faster than a commercial airplane. Then the closer: "It was on the highway."
Why it suits AI: the humour is all timing and faces. Two photos let you and a friend play it straight without memorising a script or finding a boardroom.
The Script, Beat by Beat
| Time | Who | Line |
|---|---|---|
| 0:00 | Driver | "I stole a car." |
| 1.5s | Interviewer | "What's your favorite car?" |
| 3.5s | Driver, eyes rolled up to think | "Lamborghini Gallardo… 2006." |
| 5.9s | Interviewer | "What's the fastest you've ever driven?" |
| 7.7s | Driver, slumped in the chair (wide) | "Probably like 700 mile per hour." |
| 9.5s | Interviewer, squinting | "Seventy?" |
| 10.4s | Driver | "700 miles." |
| 11.2s | Interviewer, jaw dropping | "700?" |
| 12.3s | Driver, cheek on his hand | "700. So like 771 miles per hour…" |
| 16s | Driver, cheek on his fist | "…seven… seven… 777…" |
| 18.7s | Interviewer | Silent, baffled stare |
| 20.3s | Driver, eyes up | "777 miiile… per hour." |
| 23.9s | Interviewer | "That's faster than, like, a commercial airplane." |
| 26s | Interviewer | "Was it on a track or on the street?" |
| 28.1s | Driver | "It was on the highway." |
Who plays who: photo 1 is the driver, photo 2 is the interviewer. Put the friend with the best deadpan first.
Your Look, Their Boardroom
- Your own face, hair and clothes. Nobody gets the original's wig, grills, chain or blazer.
- Your own glasses. If your photo has sunglasses, you keep them on; if it doesn't, you don't get any.
- Their set. Both of you sit in the original's wood-panelled boardroom, with the long table, the leather chair and the glass of water.
Use clear, well-lit face photos where you're looking roughly at the camera. Most of the 29 seconds are close-ups, so your face carries the whole video. If you and your friend are dressed alike, that's fine: the template tells the two of you apart by hairstyle as well as clothes.
The Fastest Way
Like 700 MPH
Two photos, the full 29-second interview with the original audio, every line lip-synced.
Two photos, 250 credits (about $12.50), no prompt. It renders on Seedance 2.5 at 480p, vertical 9:16.
Build It Yourself
1. Turn the clip into a depth map, one shot at a time. Run the 29-second clip through a depth-estimation model (Depth Anything V2 works). Set the contrast per shot, not for the whole clip: the close-ups and the wide shot have very different depth ranges, and one curve crushes one or the other.
2. Scrub the burned-in captions. The original has subtitles burned into the picture, and their letters show up faintly in the depth map, which tempts the model to write text. Find the white, black-outlined caption pixels in each source frame and inpaint them out of the depth frame. Blur the chain's lettered pendant too.
3. Make one storyboard sheet with a panel per camera setup. Seventeen cuts boil down to a handful of setups: the driver's close-up, the interviewer's three-quarter close-up, the driver's low wide shot in the chair, the interviewer's medium shot, the driver's cheek-on-fist medium shot, and a baffled interviewer close-up. Generate them all from the two photos in the boardroom.
A close-up of the person from reference image 2, head and shoulders, seen in three-quarter view with the head turned toward the right edge of the frame, looking past the camera at someone off-screen right, never at the lens. One hand raised to the chin, serious, the brows slightly drawn together, mouth closed. A warm wood-panelled boardroom softly out of focus behind. No text.
4. Drive it with the depth map and the dialogue. Feed the sheet, both photos and the depth video (with the original audio inside it) to a model that copies motion from a reference video (we recommend Seedance 2.5). Then write three things it can't get from a depth map:
- A timed shot list: who is on screen, the framing, and the line for each of the 17 cuts.
- The speaking windows: exactly when each person's mouth moves, so the listener stays still while the other talks off-screen.
- The faces: the driver's sleepy eye rolls, and the interviewer's squint, knitted brows and dropped jaw.
Lay the original audio back on at the end.
Common Mistakes
Driving with the raw clip. The wig, the grills and the captions come straight through. Use the depth map.
Leaving the captions in the depth map. Faint letter shapes are enough for the model to invent subtitles.
Describing both people only by their clothes. If two friends are dressed alike, the image model can't tell them apart and swaps the roles. Lead with hairstyle.
No speaking windows. Without them, whoever is on screen mouths along to the other person's lines.
A blank interviewer. Half the joke is his face. Write when he squints, when his brows knit, and when his jaw drops, or he sits there smiling politely.
Facing the lens. The original is a two-camera interview: both people look just past the camera at each other. Say so, or they talk to the viewer.
FAQ
How many photos? Exactly two: the driver and the interviewer.
Is it the full clip? Yes, all 29 seconds and all 17 shots.
How long is it? 29 seconds, vertical 9:16.
What does it cost? 250 credits, about $12.50.
Related Reading
- How to Make the 'Hit the Road Dude' AI Video: another viral clip, lip-synced line for line
- How to Make the 'How I Become a Millionaire' AI Video: the ChatGPT voice-memo skit, starring you
- How to Make the Alors On Danse AI Video: another two-friends video from one viral clip
- Viral AI Video Trends 2026: every trend we've turned into a template this year
