Quick answer
Starrd's That's My OPINION!! template recreates the viral Real Housewives of Orange County reunion clip with you in it. Upload one to three photos: photo 1 delivers the opinion ('I said, I don't think that he's good for you') and then screams 'That's my OPINION!' with both hands on the chest, photo 2 snaps back 'How do you know what's good for me?', and photo 3 is the friend on the couch frozen in silent shock. Any role without a photo gets an AI-cast stranger, and if every photo is a pet the strangers are animals too. Everyone keeps the outfit from their photo, every line is lip-synced to the original audio, and the four shots cut on the same frames as the original. 7 seconds, 9:16, Seedance 2.5, 480p, 150 credits (about $7.50).
The "That's my OPINION!" Real Housewives reunion meme, with you and your friends on the couch, or your dog. Here it is with one photo of a golden retriever:
That's My OPINION!!
1-3 photos. You give your opinion, your friend snaps back, you scream 'That's my OPINION!' 7 seconds, people or pets.
What You Get
- The whole exchange. "I said, I don't think that he's good for you." "How do you know what's good for me?" "That's my OPINION!"
- The scream. You lean in, hands pressed to your chest, and hold the "-INION!" with your whole face.
- The reaction shot. The edit cuts to your third friend on the couch, eyes wide, one slow blink, not a word.
- The reunion stage. Red velvet couches, purple and teal stage lights, bright TV lighting.
- Lip sync. Every line is timed to the original audio.
- Your own outfits, the original sound, 7 seconds, vertical 9:16.
What the Video Actually Is
The clip comes from The Real Housewives of Orange County, the Season 9 reunion (Episode 19). It's a four-shot argument cut so tight it plays like a sketch: a calm opinion, a sharp comeback, a scream and a silent reaction.
Bravo reposted it on TikTok on October 3, 2026 with the caption "This is your reminder that this sound exists". It passed 8.5 million plays, a million likes and 72,000 saves, and the sound took off as a reaction meme for any argument nobody asked you to join.
Why it suits AI: you can't get a reality-TV reunion stage, but you can get the scream. One photo is enough, and the joke lands just as well with a dog.
The 7 Seconds, Shot by Shot
| Time | Shot | What happens |
|---|---|---|
| 0:00 | Photo 1, close-up | "I said, I don't think that he's good for you." Calm, pointed, head tilting |
| 2.24s | Photo 2, close-up | Turns and fires back: "How do you know what's good for me?" |
| 4.17s | Photo 1, closer | Leans in, hands on the chest: "That's my… OPINION!" (the scream runs to 5.6s) |
| 5.91s | Photo 3, close-up | Frozen on the couch, eyes wide, one slow blink, silent to the end |
Your Look, Your Roles
- Photo order sets the roles. Photo 1 has the opinion, photo 2 snaps back, photo 3 is the witness.
- Your own outfits. Whatever each of you wears in your photo, you wear on the couch.
- Empty roles get strangers. Upload one photo and the other two are cast for you: glamorous reunion guests for people, other animals for pets.
Put the loudest person in your group in photo 1: they get two of the four shots, including the scream. A clear, front-facing photo works best because the shots are all tight close-ups.
The Fastest Way
That's My OPINION!!
1-3 photos on a reality-TV reunion couch, lip-synced to the original sound.
One to three photos, 150 credits (about $7.50), no prompt. It renders on Seedance 2.5 at 480p, vertical 9:16, 7 seconds.
Build It Yourself
1. Clean the clip, then turn it into a depth map. The repost has word-by-word captions, an emoji and a channel logo burned in. Mask them out first, or the depth model reads the letters as raised shapes and the video model draws them back in. Then run the clip through a depth-estimation model (Depth Anything V2 works). The depth map keeps every head turn and mouth movement and drops the faces, hair and dresses.
2. Make a character sheet. A face close-up of each person across the top and a full turnaround of each below, with the reunion stage softly out of focus behind every panel.
A photorealistic VERTICAL 9:16 CHARACTER REFERENCE SHEET in four bands: three head-and-shoulders face close-ups on top, then a four-angle turnaround of each subject, a glossy reality-TV reunion stage with deep-red velvet couches and purple stage lights softly out of focus behind every panel. No text.
3. Drive it with the depth map and the audio. Feed the sheet, your photos and the depth video, with the dialogue track inside it, to a model that copies motion from a reference video (we recommend Seedance 2.5). Then write what it can't read from a depth map:
- Who says what: one line per shot, and only the person on screen talks.
- The mouth windows: when each mouth opens, and that the witness keeps it shut.
- The faces: smug, then furious; insulted; stunned.
Lay the original audio back on at the end.
Common Mistakes
Leaving the captions in. They survive the depth map as raised letters and come back as text in your video.
Letting the original's hair through. All three women have long blonde hair. Soften the heads in the depth map or short-haired friends grow waves.
Letting the off-screen voice move a mouth. Each line starts a beat before the cut. Mute that sliver in the driver audio, or the wrong person mouths the first syllable.
A side-on photo 1. Every shot is a tight close-up; a front-facing photo keeps the likeness.
FAQ
How many photos? One to three.
How long is it? 7 seconds, vertical 9:16.
What does it cost? 150 credits, about $7.50.
Pets? Yes, in any role.
Related Reading
- How to Make the 'Deep Down in My Heart' AI Video: another two-person reaction meme
- How to Make the 'Needs More Salt' AI Video: this month's other skit, people or pets
- How to Make the 'Waiting On My Fries' AI Video: a lip-synced skit for two
- Viral AI Video Trends 2026: every trend we've turned into a template this year