Tiny Desk AI
Tiny Desk AI Solo, Duo or Trio: Who Plays Which Seat
How many people you can put in a Tiny Desk AI video, which photo replaces the lead singer, sax player and keyboard player, and how to choose between Solo, Duo and Trio.
Updated
A Tiny Desk AI video can star one, two or three people from your photos. Each photo fills one seat in the band, the seats always appear in the same shots, and all three options cost the same credit.
The three seats
| Seat | Photo | Where they appear | On screen |
|---|---|---|---|
| Lead singer | Photo 1 | About 5–11 s | The close-up: turn, wave, big laugh. The star of the meme. |
| Sax player | Photo 2 | About 11–15 s | The closing sax solo, in headphones. |
| Keyboard player | Photo 3 | About 0–5 s | Front row of the opening band shot at the red keys; also at the corner of the sax shot. |
Photos never swap seats. If you want a friend to have the laughing close-up, put their photo first.
Solo: 1 photo
You are the lead singer. This is the classic version of the meme and the best choice when the video is about one person: a birthday, a win, a reaction to good news. The keyboard player, sax player and backing singers are AI-generated musicians.
Duo: 2 photos
Photo 1 sings lead, photo 2 plays the sax solo that closes the video. Good for couples, best friends, or a manager-and-team joke. Because the sax solo is the last thing people see, it works well as a punchline.
Trio: 3 photos
Adds a third person at the keyboard in the opening band shot. Best for group chats, roommates or a small team. Keep in mind the keyboard player is on screen mostly in the wide shot, so their face is smaller than the lead singer’s.
What about everyone else?
The two backing singers, and any seat you don’t fill, are played by AI-generated musicians. They can look a little different in each video and sometimes pick up colors from your photos. They are never created from another customer’s photo. More than three people is not possible: the clip has three featured seats.
Picking the right photos for each seat
- Lead singer: the sharpest, most front-facing photo you have. The head tilts back and a hand passes across the face, which is where AI drifts most.
- Sax player: a waist-up photo; the instrument covers the mouth area, so hair and clothes help make them recognizable.
- Keyboard player: waist-up with clear clothes; this seat is smaller in the frame.
One adult per photo, no sunglasses or heavy filters. You can crop a group photo into separate photos, as long as each crop is sharp and larger than 300 pixels per side. Everyone must have agreed to be in the video; no celebrities, public figures or minors.
Price and changing your mind
Solo, Duo and Trio all use one credit: $9.99 for one video, less per video in larger packs. With a multi-video pack you can make a Solo first and a Trio next from the same private order link, without paying again.