The selfie angle, held on you
The camera stays up close and personal, exactly like the original: your face fills the frame while the club lights sweep behind you.
The grime mic-check, remade
One photo, and you are the one shouting the mic check into the camera while the club crowd moves around you — the selfie angle, the beats, the hype, with the clip’s audio re-created by AI. 12 seconds vertical, 15 optional.

Your photo becomes the mic-check star; add a second photo to put a hype companion beside them. The clip's audio is re-created by AI.
Trending memes
Effects use one or two uploaded photos and the selected source effect. View pricing ·
AI Rap Video (rapaivideo.net) makes the Check One Check Two AI video from one photo: you take the mic-check role of the viral grime clip, shouting into the camera over a club crowd, 12 seconds in 9:16 (15 seconds optional), and the AI re-creates the clip’s audio in the downloaded MP4. It starts at 7 credits (Standard, 480p); packs start at 10 credits for $6.99, a failed render is refunded, and a video takes about 5 to 15 minutes.
Updated
The trend
“Check one, check two” is the classic microphone check. In the clip behind this trend — linked to British grime MC JME — a bald man in a white tee holds the camera on himself in a dark club and shouts the check over the beat while the crowd moves behind him. TikTok creators have been remaking that exact energy with their own faces.
Here it is a trending meme template: Check One Check Two under Trending memes. The video model gets the original clip — picture and sound together — as the performance to restage, and your photo as it is; the AI re-creates the clip’s audio in the finished MP4.
This is not a voice tool. It does not make anyone sing new words in someone else’s voice: the audio is re-created by AI from the clip’s track, and the person on screen is you. For a song of your own, the AI rap generator writes and raps a new one about your topic.
Three steps
One clear photo of one person, face visible, no sunglasses. That person takes the mic-check role. A second photo is optional — it joins as a hype companion beside them.
It is always vertical 9:16, 12 seconds by default with a 15-second option. It starts on the Standard model at 480p; every model and resolution is priced on its own, and the button follows.
It takes about 5 to 15 minutes. The MP4 has the clip’s audio re-created by AI, ready for TikTok or Reels.
What you get
The camera stays up close and personal, exactly like the original: your face fills the frame while the club lights sweep behind you.
The mic-check energy — the calls, the nods, the arms at the crowd — restaged on you, with the pacing of the original clip.
The original clip goes in with its sound, so your mouth can follow it. The AI re-creates the audio in the finished file.
Your face and clothes come from your photo. Add a second photo and that person appears in the crowd beside you as your hype companion; everyone else stays as in the original.
The template takes one photo by default: the person in it becomes the mic-check star. If you switch to two photos, the second person is not a second lead — they join the first as a hype companion in the crowd beside them, like the friends hyping the mic in the original crowd.
For a template where two people share the lead, the Hotel Lobby rap duo on the home page is made for two.
People search this trend with CapCut, Dreamina and “free AI video generator”. Apps make it one of three ways: a face swap on the original clip, a prompt that describes the club from scratch, or a model that follows the clip’s moves with a new person. This template is the third, because providers refuse the original clip with its sound as input. It is not free: this template is paid with credits.
Add one photo, keep the template selected and tap create. You get a 12-second vertical MP4 (15 seconds optional) of you shouting the mic check over the club crowd, with the audio re-created by AI.
The original clip, with its sound, is passed to the model as the reference, so your mouth can follow it; the AI re-creates the audio in the finished MP4.
Yes. One photo is the default: that person takes the mic-check role. Add a second photo and that person joins as a hype companion in the crowd beside them.
12 seconds by default, with a 15-second option, always vertical 9:16. It takes about 5 to 15 minutes to make.
Not fully. The 12-second version starts at 7 credits on the Standard model at 480p; every model and resolution is priced on its own. Credits are paid when you create; the smallest pack is 10 credits for $6.99, and a failed render is refunded automatically.
No. Your face and clothes come from your photo; the clip only guides the moves, the framing and the moment. Results vary from render to render: a failed render is refunded, a finished one you do not like is not.
No. AI Rap Video is an independent tool and is not affiliated with JME, Boy Better Know or any rights holder of the original clip.
Check the mic
One photo, the shout and the crowd. The price is shown before you create.