Cilvelim AI TrendSing Baran Mengüç's Song in the Back Seat
You sit in the back seat of a car and sing the sped-up chorus straight into the phone: a finger pointed at the camera, a pout on the long note, the eyes closed for the feeling, a shy smile and a wave at the end. One photo of you or your pet, and the 14-second clip comes with the song.
The Cilvelim AI trend is the Turkish back-seat lip-sync of November 2026: one photo becomes a close phone video of the person in the back of a car singing the sped-up chorus of Baran Mengüç's "Cilvelim", pointing at the camera, closing the eyes, smiling and waving. Add one photo of yourself or your pet. Adults and pets only.
Also called Back-seat lip-sync trend · Cilvelim car trend
Example
What the Cilvelim video looks like
Made from the Human prompt on this page with an AI-made woman, not a real person. The song is put on after the run, the same as on your video. Your result will differ from run to run.
Input
Made with Smew AI from one photo of an AI-made woman: she sits belted in the back seat, mouths Cilvelim, points at the camera, leans in, smiles and waves to the beat.
Everything runs in the browser. No editing app, no prompt to write, no watermark.
Add your photo
Press "Create your own" and add you (adults only), face clear. Take it with the camera or pick it from your library.
Press Generate
The button shows the price. Seedance 2.5 films the Cilvelim scene straight from your photo, with no in-between picture, for 14 seconds, with the trend's original song. You write no prompt.
Download or share
The video is ready in a few minutes as a 9:16 MP4. Download it, share it from your phone, or find it later in My videos.
Which photo works best?
One photo, one person or one pet, face to the camera, sharp and in good light. The video is a close-up, so the face matters most.
Human: you, a partner, a friend or a parent, from the chest up. You keep your own face, hair and clothes, and you sit belted in the back seat. Adults only: never a child's photo.
Pet: your dog or cat with the whole head, the eyes and the ears in view. It sits in a padded pet car seat and sings with its own face.
Glasses, beards and headscarves stay when the photo shows them.
Use your own photo or a photo of an adult who said yes. Never a celebrity or a stranger.
Where did the Cilvelim trend start?
The song is "Cilvelim" by the Turkish singer Baran Mengüç, the son of Tarık Mengüç. The single came out on 6 March 2026, and its official video has 25.3 million views on YouTube (8 November 2026). On TikTok the sped-up version, the sound "cilvelim speedup", is the one people use and search as cilvelim speed up, and Baran Mengüç's own dance clip on it from 25 October 2026 has 1.2 million views.
The cilvelim akımı is an AI one. On 5 November 2026 AI video apps started Turkish ads for a one-photo template: the subject sits in the back of a car, filmed close from the front seat, mouths the chorus "Ölüyorum aşkından, ooo cilvelim, tuz bastı yarama cilvelim", points at the camera, closes the eyes, smiles and waves. By 8 November we had seen 11 of these ads on Meta and TikTok, 3 of them new ad videos from 7 November. On TikTok, #cilvelim has 2,024 videos and 52.4 million views, and #baranmengüç 1,616 videos and 66.6 million views.
Baran Mengüç releases "Cilvelim" as a single; the official video goes up on YouTube the day before. Haberler.com
Baran Mengüç posts a dance clip on the sped-up sound "cilvelim speedup"; it reaches 1.2 million views and the song is hot again. TikTok
AI video apps start Turkish ads for a one-photo template: the subject lip-syncs the sped-up chorus in the back of a car, points at the camera and waves.
11 ads of the template seen on Meta and TikTok, 3 of them new ad videos from 7 November. #cilvelim has 2,024 TikTok videos and 52.4 million views.
Smew AI adds the template with a Human version for adults and a Pet version.
Copy and paste
The Cilvelim prompts
You do not need this: the one-tap flow runs it for you. [Image 1] is your photo: the video model takes it as a reference and films the scene straight from it, with no photo step first.
Human
1 photo: you (adults only), face clearSeedance 2.514 s · 480P · 9:16177 credits
Video prompt
A sweet, flirty back-seat lip-sync video, one continuous take, no cuts: the back seat of a parked car in soft overcast daylight: grey fabric seats, a side window with a light sky behind, the front-seat headrests at the edges of the frame, filmed like a real phone video held by someone in the front seat who turns back toward the back seat, close, at face height, slightly handheld. Photorealistic live action, vertical 9:16.
WHO: the singer is the person in [Image 1], in every frame: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), with the hair and the clothes from [Image 1]. The same real person from the first frame to the last, so their friends recognize them at once. They keep their own age, never younger. Never morph, never change the face. They sit as an adult passenger on the normal back seat with the seat belt across the chest, no child seat. If [Image 1] shows an animal, the singer is that animal sitting on the back seat, with its own face and fur, not a person.
THE PERFORMANCE, a cheeky, loving sing-along straight into the phone from the very first frame:
Shot 1 [0-14 s]: one continuous take, the face large and sharp in the middle of the frame.
[0-1 s] sits back in the seat, looks into the camera and starts to sing, both hands loose in front.
[1-2.5 s] leans toward the camera and points one finger straight at the lens on the beat.
[2.5-4.5 s] the face comes close to the lens, the lips pushed round on a long note, a cheeky look in the eyes.
[4.5-6 s] half closes the eyes and tilts the head, singing with feeling, one open palm toward the camera.
[6-8 s] eyes closed, sways the head and both hands softly with the beat, still singing.
[8-9.5 s] opens the eyes with a shy smile, looks down for a moment, then back at the camera.
[9.5-12.5 s] leans close to the lens again with a big smile and a little laugh, singing on.
[12.5-14 s] waves one hand at the camera with a big, warm smile.
Sound: none of its own; a song is put on afterwards, so the singing must be easy to see: clear lip movements in sung phrases with short breaths between them, the lips pushed round on the long "ooo" notes, the mouth closed only while smiling. No dialogue throughout the entire video. No background music.
Only this one person, nobody else in the car is seen. Natural skin, real hands with five fingers each. No extra people, no child, no text, no subtitles, no captions, no logo, no watermark, no picture-in-picture, no split screen, no morphing.
1 photo: 你的寵物,戴耳機(留在電梯)Seedance 2.514 s · 480P · 9:16177 credits
Video prompt
A sweet, flirty back-seat lip-sync video, one continuous take, no cuts: the back seat of a parked car in soft overcast daylight: grey fabric seats, a side window with a light sky behind, the front-seat headrests at the edges of the frame, filmed like a real phone video held by someone in the front seat who turns back toward the back seat, close, at face height, slightly handheld. Photorealistic live action, vertical 9:16.
THE SINGER is the pet in [Image 1], in every frame: the same species and breed, face, eyes, ears, muzzle, fur colors, fur length and markings as in [Image 1], with the natural body volume and proportions of that animal: never flattened, squashed, stretched or merged with anything. Its owner recognizes it at once. It sits upright in a padded grey pet car seat on the back seat, a short harness strap clipped to it, facing the camera, and sings: it keeps its own animal face, teeth and tongue, only its mouth moves like a singer. No clothes on the pet.
THE PERFORMANCE, a cheeky, loving sing-along straight into the phone from the very first frame:
Shot 1 [0-14 s]: one continuous take, the pet's face large and sharp in the middle of the frame.
[0-1 s] sits up in the pet seat, looks into the camera and starts to sing.
[1-2.5 s] leans toward the camera and points one front paw straight at the lens on the beat.
[2.5-4.5 s] the face comes close to the lens, the lips pushed round on a long note, ears up, a cheeky look.
[4.5-6 s] half closes the eyes and tilts the head, singing with feeling.
[6-8 s] eyes closed, sways the head softly from side to side with the beat, still singing.
[8-9.5 s] opens the eyes with a shy, happy face, looks down for a moment, then back at the camera.
[9.5-12.5 s] leans close to the lens again with a big happy face, singing on.
[12.5-14 s] lifts one front paw and waves it at the camera.
Sound: none of its own; a song is put on afterwards, so the singing must be easy to see: clear lip movements in sung phrases with short breaths between them, the lips pushed round on the long "ooo" notes, the mouth closed only while smiling. No dialogue throughout the entire video. No background music.
Exactly one animal and no people. One head, four legs and one tail, real furry paws, no human hands. No cartoon look, no plush toy, no extra animals, no text, no captions, no logo, no watermark, no split screen, no morphing.
You pay in credits. The Generate button shows this price before you spend anything. These are the options on this page.
Option
Model
What you get
Credits
Human
Seedance 2.5
14 s · 480P · 9:16
177
你 + 寵物
Seedance 2.5
14 s · 480P · 9:16
177
One-time packs and plans are on the pricing page. A failed video gives its credits back.
What does each version make?
Version
Photo
What you get
Human
1, an adult
14-second video. You sit belted in the back seat of a car and sing to the phone, point at the camera, pout on the long note, close your eyes for the feeling, smile and wave at the end.
Pet
1, a dog or cat
14-second video. Your pet sits in a padded pet car seat in the back, sings, points a paw at you, closes its eyes, smiles and waves a paw.
Both are vertical 9:16 at 480P, made straight from your photo by the best AI video models available, so there is no in-between picture and your face stays close to the photo. Both come with the trend's sound: the same 14 seconds of the sped-up "Cilvelim" that the trend uses, from "Ölüyorum aşkından" to "yaklaş yanıma", put on after the video. The lips follow the song's rhythm, not every word, so it reads as a cilvelim lip sync without being an exact one. The exact price shows on the Generate button before you spend anything.
Want the couch version of the same kind of trend? The İnşallah Maşallah page makes the grey-couch lip-sync with Neşe Karaböcek's song.
What happens in the video, second by second?
Time
What happens
0-1 s
You sit back in the seat, look into the phone and start to sing.
1-2.5 s
You lean in and point one finger straight at the camera.
2.5-4.5 s
Your face comes close to the lens, lips round on the long "ooo", a cheeky look.
4.5-8 s
You half close your eyes, tilt your head, then close them and sway with the beat, hands moving with the words.
8-9.5 s
A shy smile, a quick look down, then back at the camera.
9.5-14 s
You lean close again with a big smile and a little laugh, then wave at the camera.
The moves follow the song: the point lands on "değil mi", the pout on the first "ooo cilvelim", the closed eyes on "tuz bastı yarama", and the wave on "yaklaş yanıma", as in the trend clips. One continuous take, like a phone held from the front seat.
Which sound and hashtags should you post it with?
Your clip comes with the trend's sound, so it is ready to post. You can turn the song off on the result screen and add the TikTok sound "cilvelim speedup" when you post instead. The song belongs to its owners, and Smew AI gives you no rights to it. Check the platform's music rules before you use the clip in an ad.
Hashtags: #cilvelim (2,024 TikTok videos, 52.4 million views on 8 November 2026), #baranmengüç (1,616 videos, 66.6 million views) and the spelling without Turkish letters, #baranmenguc (112 videos). Keep the platform's AI label on.
What goes wrong, and how do you fix it?
Problem
Fix
The lips do not match every word
The song goes on after the video, so the mouth follows its rhythm, not each Turkish word. Run it again for another take.
The face looks less like the photo
Use a sharp, front-facing photo in daylight, one person per photo, and run it again.
The face goes soft when it comes close to the lens
Close-ups are where AI video works hardest. A sharp, well-lit photo helps; run it again.
Fingers look odd in the point or the wave
Hands are the hardest part for AI video. Run it again.
A pet's paws look like hands
The prompt asks for real paws. Use a photo where the pet's paws show, then run it again.
The model refuses a photo
Some photos get refused. The credits come back; try another photo.
FAQ
Cilvelim trend questions
What is the Cilvelim AI trend?+
It is a Turkish AI trend from November 2026: one photo becomes a close phone video of the subject in the back seat of a car who sings the sped-up chorus of Baran Mengüç's "Cilvelim", points at the camera, closes the eyes, smiles and waves. AI video apps started advertising the template on 5 November 2026, which is why people call it the cilvelim akımı or the cilvelim trend.
Who sings Cilvelim? (cilvelim kimin şarkısı)+
Baran Mengüç, a young Turkish singer and dancer, the son of Tarık Mengüç. He released it as a single on 6 March 2026. People search it as cilvelim baran mengüç, baran mengüç cilvelim or simply the cilvelim şarkısı. The trend uses the sped-up version, and your clip comes with 14 seconds of it.
What does cilvelim mean? (cilvelim ne demek)+
"Cilve" is Turkish for a playful, flirty charm, so "cilvelim" means something like "my flirty one" or "my coquettish darling". It is a loving word for a sweetheart, which is why the trend is all pouts, points, smiles and waves.
Which lines of the song are in the trend?+
The sped-up chorus: "Ölüyorum aşkından, ooo cilvelim, tuz bastı yarama cilvelim, ooo cilvelim, yaklaş yanıma". People look for them as cilvelim sözleri or tuz bastı yarama cilvelim. Those 14 seconds go on your video after it is made.
Is it the cilvelim speed up from TikTok?+
Yes. The cilvelim tiktok trend runs on the sped-up sound "cilvelim speedup", not on the slower album version or a cilvelim remix. The song on your clip is that faster cut, so it sounds like the trend.
How do I make the cilvelim yapay zeka video?+
Press "Create your own", pick Human or Pet, add one clear photo and press Generate. The button shows the price first. You write no prompt: this page is the cilvelim ai video maker, and the clip is ready in 5 to 15 minutes.
Is this the cilvelim ai trend from the ads?+
It is the same back-seat lip-sync that runs as the cilvelim ai trend in TikTok and Meta ads: the car, the song, the point, the closed eyes and the wave. Your video is made new from your photo, not copied from those clips.
Can I make it with a child's photo?+
No. This page makes the trend with adults and pets only. Use your own photo, a partner, a friend or a parent, or your dog or cat.
Can my dog or cat sing it?+
Yes. The Pet version puts your dog or cat in a padded pet car seat in the back: it sings, points a paw at you, closes its eyes and waves, with the same song. It is an AI pet lip sync video from one photo: your dog singing in car, filmed like a real phone video.
Is it real lip sync?+
Close, not exact. The video is made first and the song goes on after it, so the mouth sings in the song's rhythm and opens on the long notes, but it does not follow every Turkish word.
Can AI make any photo sing a Turkish song?+
For this song, yes: it is an AI lip sync video from a photo, so you can make my photo sing AI style with one picture and no prompt. In Turkish people call it yapay zeka şarkı söyletme or şarkı söyleyen yapay zeka. For other Turkish song lip sync AI trends, see the related pages below; each is an AI singing video from a photo with its own song.
How long is the video and what format is it?+
14 seconds, vertical 9:16 at 480P, an MP4 with the song and no watermark.
Is the video real?+
No. It is made with AI from one still photo; the car and the back seat are made up. Use only photos of adults who agreed, never a child, and keep the AI label on when you post.