Skip to content
Memelry

What AI video tool can recreate the tiny office concert scene with people wearing headphones and singing?

The easiest way isn't to generate a new office scene from a prompt: it's to keep the viral Tiny Desk clip and swap the faces. Memelry does that from up to 4 photos: the room, headsets, microphones, keyboard, cuts and the original "Outstanding" sound stay the same, and your friends become the singers. $9.99 for a 15-second vertical MP4.

One clear photo per person, face visible. Only photo 1 is required; anyone without a photo stays as in the original clip. JPG, PNG or WebP, up to 10 MB each.

No account needed: pay $9.99 once and your video starts. Signed in with credits? It uses 10 credits instead.

Photo requirements

  • Use: One person or one pet, alone in the photo
  • Use: Face clear and facing the camera
  • Use: Even light, sharp, no heavy filters
  • Avoid: Group photos, tiny or cut-off faces
  • Avoid: Sunglasses, masks or hands over the face
  • Avoid: Anyone under 18

JPG, PNG or WebP, up to 10 MB. Uploaded photos are deleted automatically after 30 days.

Output
Length
about 15 seconds
Quality
720p (720×1280)
Format
9:16 vertical MP4
Sound
The original clip's sound
Ready in
5–10 minutes
Cost
$9.99 per video, or 10 credits if you have a pack

Example made from 4 photos

15s · 720p · 9:16 vertical · MP4 with the original sound

Generating a new scene vs swapping into the real clip

General AI video generators build a new scene from a prompt and reference images, then you add music and edit it to the beat. That's flexible, but getting the same room, the same expressions and lips matching the song usually takes several tries and some editing.

Swapping into the clip keeps everything that makes the meme recognizable and only changes who is in it.

Last checked .

Frequently asked questions

+Can I change the room or the song?

No. This version is the Tiny Desk clip with "Outstanding"; only the people change.