Outstanding Tiny Desk AI Template: Every Shot and Seat

What the Outstanding Tiny Desk AI template is

Most AI video trends run on a template: a short base clip that stays the same for everyone, with one thing swapped out. In this trend the base clip is a few seconds of Charlie Wilson and his band playing "Outstanding" at NPR's Tiny Desk in 2023, and the thing swapped out is the people.

Not every tool starts from that clip. Some build a desk-concert-style scene from scratch around a single photo; from a distance it looks like the trend, but it is not the performance people know. Ours is cut from the real footage, already trimmed, cropped and timed, so the template is ready before you add a single photo.

The three shots, in order

Both lengths use the same three shots in the same order. This is what is on screen in each:

• Shot 1, the backing singers. Three women fill a tight frame: one seated in the middle behind a red keyboard, with long braids, and two standing behind her, one on the left with short black hair and big hoop earrings, one on the right in a black leather cap. They sing, clap and laugh along with the office shelves behind them.
• Shot 2, the lead singer. A close-up of Charlie Wilson in a blue knit cap, gold-rimmed sunglasses, a patterned jacket and a gold chain, head tilted back mid-note.
• Shot 3, the saxophone. The sax player, in glasses and a black hoodie, plays the closing phrase. In the lower right corner, part of the keyboard singer's face peeks into the frame.

There are no other cuts. Everything you see in a finished video happens inside these three shots.

Why these three shots

The stretch was not picked at random. The clips that made the trend famous swap the same five people across the same run of shots, so viewers already expect a new face in each of those places. A template that used a different moment, or a different set of musicians, would look like a near miss to anyone who has seen the originals.

The template also ends with the saxophone shot, before the camera cuts to a wide shot of the whole band. That keeps every frame on the people you can replace, instead of spending the last seconds on musicians nobody gets to recast.

How the 10- and 15-second cuts differ

The two lengths are not one clip at two speeds. The 15-second cut starts earlier and holds on the opening shot longer; the 10-second cut joins that shot near its end. Roughly how long each shot stays on screen:

• 15 seconds: about 5 seconds on the backing singers, about 6 on the lead singer and about 3.5 on the sax player.
• 10 seconds: about 2 seconds on the backing singers, about 6 on the lead singer and just under 2 on the sax player.

The lead singer's close-up is the same length in both cuts, so a version with only that seat filled loses almost nothing in the shorter one.

Who sits in each seat

The generator has 5 photo slots, one per seat. This is the person each slot replaces in the template:

• Lead vocals: Charlie Wilson, the singer in the close-up of shot 2.
• Sax: the saxophone player in shot 3.
• Keys: the woman seated behind the red keyboard in the middle of shot 1.
• Left backing vocals: the singer standing behind her on the left in shot 1.
• Right backing vocals: the singer in the leather cap, standing behind her on the right in shot 1.

Left and right mean left and right as you look at the screen. Whoever you put in a seat appears exactly where that musician was, in the same pose and at the same moments.

Casting around the template

Once you know the shots, a few casting choices follow straight from the timing:

• Lead vocals gets the spotlight. It is the longest shot and the biggest face on screen, so put the main joke, or the guest of honor, there.
• The three backing singers share one frame. Viewers see them side by side and compare them, so three people from the same team, office or family land better than a random mix.
• Keys is the hidden second lead. That seat is front and center in the opening shot and returns in the final one, so it rewards someone with a big reaction face.
• Sax closes the clip. The last shot is what people see right before the video loops, which makes it a good seat for the punchline.
• In the 10-second cut the backing singers are gone almost as soon as they appear. If most of your cast sits in those three seats, choose 15 seconds so people can actually see them.

The lead vocals close-up is also where photo quality shows most: every blur or shadow is blown up to fill the screen. If one of your photos is sharper than the rest, give it to that seat.

Why the template is vertical

The original concert was filmed for a wide screen. To make the template fit TikTok, Reels and Shorts, we cropped every shot to a 9:16 frame, 720 pixels wide by 1,280 tall, and moved the crop with the faces, so nobody in a seat slides out of the picture.

The trade-off is the edges of the room: a tall, narrow frame keeps the people and gives up some of the shelves on either side of them. The finished video comes out in that same vertical shape, so there is nothing to re-crop before you post.

What the template does not let you change

A fixed template is what makes every version instantly recognizable, and it also sets a few limits. You cannot move to another part of "Outstanding" or to a different concert. The three shots always play in the order above, at the timing of the length you pick. And the template carries no text, so captions go on when you post, in TikTok, Instagram or YouTube.

Template questions