Pets stay pets
The Pets setting keeps your animals on four legs with their own markings, so the clip reads as a talking-pet video rather than a costume.
CATS, DOGS AND EVERY PET WITH A FACE
Upload a photo of each pet. They keep their fur and faces, and rap a brand-new verse about treats, naps and you.
Clear, front-facing photos, one pet per photo, whole face in frame. JPG, PNG or WebP, up to 10 MB.
This video: 10 credits · 10 videos a month for $29.90, or 40 a year for $100
Just want one video?
Short answer: My AI Rap Video makes a pet rap video: upload one photo of each pet (or one photo of both), switch to Pets, and your cat, dog or any pet with a clear face raps a verse written from its point of view. They keep their fur, markings and faces. You get a 12-second, 9:16 MP4 with new lyrics, two AI voices and a beat, in about two to three minutes, with no watermark. One video costs $9.99; there is no free generation.
A pet rap video puts two animals at one microphone with lines written from their point of view. Upload a photo of each pet, and the voices, beat and mouth movement are generated for you.
A pet rap video puts your animals at the microphone. Upload a photo of each pet, or one photo with both of them, and My AI Rap Video generates an original performance: your cat, dog, rabbit or parrot shares one hanging microphone, trades bars with its partner and moves its mouth in time with a brand-new AI voice and beat. The lyrics are written from the pets' point of view, so the verse is about treats, naps, walks, squeaky toys and the humans who never share the sofa.
The animals stay animals. The video keeps their fur colour, markings, ears and faces as they look in your photos, and places them on a real-looking music set instead of turning them into cartoons or giving them human bodies. You can use the orange recording booth from the viral hotel lobby trend, a marble lobby, a studio, a street cypher, a birthday party or a neon set.
It is a good fit for pet accounts, birthdays and adoption anniversaries, a cat and a dog who barely tolerate each other, or two siblings from the same litter. Everything you hear is generated fresh for your video, so there is no copyrighted song to get muted on TikTok, Reels or Shorts.
Mostly, yes. The render keeps the fur colour, markings, ear shape and face from your photos, and it leaves your animals as animals on a realistic music set instead of turning them into cartoons or giving them human bodies. Small details can drift, as in any AI video, which is why a failed render refunds its credits.
Switch "Who's rapping" to Pets. Pick two photos, one pet in each, or one photo where both pets are clearly visible. The best photos look at the camera, show the whole face, and are sharp and well lit. A photo taken at your pet's eye level works much better than one taken from above.
Choose a scene and, if you like, a topic. A topic gives the verse something to argue about: who owns the window spot, the vet visit nobody talks about, or the dog who ate the birthday cake. Leave it empty and the lyrics will be about two pets who are best friends.
Press Make and pick a credit pack: $9.99 a video, or 10 credits. A few minutes later the song is in My videos, in HD with no watermark, ready to download or share with a link.
Real outputs of this generator, described in words: what went in and what came out. Each one is the first take, not edited.
In: two AI-generated photos (a ginger tabby cat, a grey terrier mix), one per rapper; Pets mode; topic: who owns the window seat; scene: orange booth.
Out: The cat and the dog trade an original verse about the window seat at one hanging mic in the deep-orange booth, in their own voices; both keep their fur and faces and stay animals. 12 s, 9:16, 720p, Seedance 2.0 Mini, first take, unedited.
Watch the MP4| Check | Why it matters |
|---|---|
| Face toward the camera | The model copies the face it can see; a turned head loses the markings. |
| One pet per photo | With two photos, crop out other animals and people. |
| Shoot at eye level | Photos taken from above shrink the face and stretch the head. |
| Daylight, no flash glare | Glowing eyes and harsh shadows change how the face is read. |
| Nothing over the face | Costumes, cones and blankets hide what makes your pet recognisable. |
| Recommended settings | Pets · Two pet photos · Orange booth · 12 s · 720p Standard |
The Pets setting keeps your animals on four legs with their own markings, so the clip reads as a talking-pet video rather than a costume.
Beat, voices and lyrics are generated per video, so there is no licensed track to get a pet rap video muted on TikTok, Reels or Shorts.
A 12-second video is $9.99. Bigger packs cost less per video, and failed renders refund.
Rabbits, hamsters, guinea pigs and parrots work when the face is clear and close. Shoot at your pet's eye level for the strongest reference.
Pet accounts live on short, surprising clips. A cat and a dog trading bars in the orange booth is the kind of video people send to friends. Make a series with the same pets in different scenes, or give each video a topic from that week's chaos.
Celebrate a pet's birthday or adoption anniversary with a verse about how far they have come, from the shy rescue in the shelter photo to the boss of the house. Share the link with the family chat or the shelter that matched you.
Some pets were not consulted about the new roommate. Let the older cat and the new puppy settle it at the microphone: one complains about the noise, the other answers with energy. It is a light way to tell the story of a house with two very different animals.
You can also mix one person and one pet. Keep "Who's rapping" on Pets so the animal stays an animal, upload your selfie and your pet's photo, and write a topic about your routine together, like the morning walk or the 3 a.m. zoomies.
Cats and dogs work best, and other animals with a clear face, like rabbits, hamsters, guinea pigs and parrots, can work too. The model needs to see the face, so avoid photos where the pet is far away, turned around, blurry or mostly hidden by a blanket.
The video keeps their fur colour, markings and face shape from your photos and keeps them as animals on a realistic music set. Like any AI video, small details can drift, which is why a failed render refunds its credits.
Yes. The rapping pet's mouth moves with the generated voice while the other one listens and reacts, then they switch. Animal mouths are not built like ours, so the lip-sync looks like a talking-pet video rather than a perfect human performance.
Neither yours nor any artist's. The voices, beat and lyrics are generated for each video. The scenes are inspired by the hotel lobby trend, but we do not use the original song or recording and we are not affiliated with Migos or COLORS.
A full standard 12-second video costs 10 credits, which is $9.99 on its own. Credit packs never expire and cost less per song, and failed renders are refunded automatically.
Use photos you took or have permission to use, and ask the owner before you share a video of their pet. Do not upload photos that show other people unless they agreed. Your photos are only used to make your video, and you can delete your videos at any time.
Find one sharp, eye-level photo of each pet, switch who is rapping to Pets, and pick something worth arguing about: the window spot, the stolen cake, the 3 a.m. zoomies. One video is $9.99.
Make our AI rap video