Skip to content

All effectsTiny Desk AI

Tiny Desk AI: your photos become the Outstanding band

Tiny Desk AI turns 1 to 5 photos, or one group photo, into the 15-second office concert clip from TikTok: a singer at a red keyboard, a laughing close-up and a sax solo, vertical 9:16, with "Outstanding" on the sound, from 7 credits.

  • Free 2-second preview
  • 1 to 5 photos
  • 15 seconds
  • Vertical 9:16
  • Song included

Photo 1 gets the most screen time, the six-second laughing close-up.

Video settings

Length15 sEvery video is 15 s, the length of the scene.
Format9:16Every video is 9:16, the frame of the original clip.

First time here? See 2 seconds of your own video free, one per account. The full 15-second video is 7 credits. View pricing

Updated

Your video

Your video shows here when it is ready, and stays in My creations.

Real render
  1. Band shot
  2. Close-up
  3. Laugh
  4. Sax solo

The video

What the video looks like

A Tiny Desk AI video is a 15-second vertical clip of a small band squeezed into an office in front of shelves full of records and souvenirs. Everyone wears studio headphones. One person sits at a red keyboard and sings the first word, "Outstanding", one person gets a long laughing close-up, and one person closes the clip with a saxophone solo.

The people are the ones in your photos. The office, the three camera shots, the cuts and the sound come from the post that started the trend, @theburnerfromhe11's Tiny Desk parody on TikTok. That post is linked here and not shown, because its band is made of real, well-known coaches.

Real render

Second by second

The three shots, second by second

The timing below is read from the reference clip itself, one frame per second. Your video keeps the same cuts.

TimeWhat is on screen
0:00 to 0:05The band shot, framed from the chest up. The lead singer sits front and center behind a red keyboard and sings "Outstanding" into the microphone, hands moving. Two backing singers stand behind, pumping their fists to the beat.
0:05 to 0:08Hard cut to one person in close-up in front of the shelves, face turned to the left of the frame, starting to smile.
0:08 to 0:12The same person turns to the camera and laughs out loud, then lifts a hand in front of the chest.
0:12 to 0:15Hard cut to the sax solo: a player in headphones, eyes down on the saxophone, with the top of the singer's head in the bottom corner.

How it works

How to make a Tiny Desk AI video in three steps

  1. Choose the band size and add photos. Pick 1 to 5 people and upload one clear photo of each, or switch to a single group photo of 2 to 5 people.
  2. Check the order. Photo 1 gets the laughing close-up, photo 2 sings at the keyboard, photo 3 plays the sax. The length is fixed at 15 seconds in 9:16; you only choose the resolution.
  3. Create and download. The exact price is on the Create button. When the render is done you download an MP4 with the song already on it, with no watermark.

If your account has never bought credits, the button first offers one free 2-second preview: the opening band shot with the first "Outstanding", at 480p, to watch on the page. One preview per account.

Versions

Who plays which part, by band size

Tiny Desk AI gives every photo a part in the order you upload it. With fewer than five photos, people who are already in the band also stand in the back row, so that no stranger from the reference clip is left in your video.

PhotosLaughing close-upLead singerSax soloBack row
1Photo 1Photo 1Photo 1Empty
2Photo 1Photo 2Photo 1Photo 1, on the right
3Photo 1Photo 2Photo 3Photo 3 left, photo 1 right
4Photo 1Photo 2Photo 3Photo 4 left, photo 1 right
5Photo 1Photo 2Photo 3Photo 4 left, photo 5 right

With one group photo, the parts are handed out from left to right in the photo. The price is the same for one person and for five.

Price

What it costs

Every Tiny Desk AI video is 15 seconds, vertical 9:16, with sound. The only setting that changes the price is the resolution: 7 credits at 480p, 12 at 720p or 24 at 1080p. The smallest pack is 10 credits for $9.99, pack credits never expire, and a render that fails gives its credits back automatically.

Credits per Tiny Desk AI video, by length and resolution
Length480p720p1080p
15 seconds7credits12credits24credits

The trend

Where the trend and its song come from

The trend started on TikTok on 18 October 2026, when @theburnerfromhe11 posted an AI parody that cast that week's losing college football coaches as an office band. Other creators then rebuilt it with athletes, families and friend groups, and it picked up more names along the way: the Outstanding AI trend, the outstanding Tiny Desk and Tiny Desk concert AI all mean the same clip.

The parody borrows from a real performance. Charlie Wilson's Tiny Desk Concert, published by NPR on 5 June 2023, ends with "Outstanding", a song from his group The Gap Band. The sound on your clip is the 15 seconds heard in the trend's first post, starting on that first word.

VideoEffect is not affiliated with NPR, Tiny Desk Concerts, Charlie Wilson, The Gap Band, TikTok or CapCut.

Photos

Photos that work, and what the test render showed

  • Waist-up and facing the camera. All three shots are tight: the band shot stops at the chest and the other two are close-ups, so the face matters more than the outfit.
  • One person per photo gives sharper faces than a group photo, where each face is small.
  • Put the best laugh first. Photo 1 holds the close-up for about six seconds, the longest shot in the clip.
  • Use your own photo, or photos of people who agreed to be in the video.
  • Headphones are added for everyone. Hats and glasses appear only if they are in the photo.

This setup was test-rendered on the same video model on 3 November 2026 with five made-up, AI-generated friends at 480p. Each photo came out in its own part. One backing singer came out wearing a watch that was not in his photo, so small added accessories can happen. One-person and two-person bands have not been test-rendered.

Good to know

What it cannot do

  • It cannot change the length, the shape or the scene: always 15 seconds, always 9:16, always the office with the red keyboard.
  • It cannot use your own song or your own voice. The sound is the trend's clip, and the singer's mouth follows it.
  • It does not take more than five people, and it is not set up for pets.
  • It is not for faces of coaches, athletes or other famous people. The trend's first posts did that; this page is for you and people who said yes.
  • It is not a real Tiny Desk Concert and should not be posted as one. Turn on the AI label when you share it.

Prompt

The prompt, in full

Below is an English version of the instructions this effect uses, one for each band size from one to five. They name every person in the reference clip by what they wear, say which of your photos replaces them, and go through the three shots. It is a translation, not a word-for-word copy of what the generator runs, and the instructions alone will not rebuild the video elsewhere: they work together with the 15-second reference clip and its sound.

1 person

Edit [Video 1]: replace only the people in [Video 1] with the subject below; everything else stays exactly as it is in [Video 1]. What stays unchanged includes: the framing, distance, camera position and camera movement of every shot; the two hard cuts at 5.3 and 11.6 seconds; the bookshelves, the lighting, the red keyboard and the microphones; and every move, gesture, head turn, expression and mouth shape, moment by moment, of the person who is replaced. Nothing of the replaced person is kept: that person's face, hair, beard, glasses, hat, clothes and the words and logos on the clothes are all replaced with the subject's own.

Subject lock (two images per subject: the face comes only from their original photo; hairstyle, build and clothes come only from their waist-up portrait):
Subject A: face from [Image 2]; hair, build and clothes from [Image 1]. Subject A is the lead singer in the band shot, the person in the laughing close-up, and the one playing the saxophone in the sax shot.

There are five people in [Video 1]; each is replaced with a subject above or removed, and none of them is left:
The lead singer sitting front and center behind the red keyboard (white baseball cap with a red and black G logo, black jacket with red lettering on the chest) is replaced with subject A ([Image 1], [Image 2]): none of the lead singer's face, hair, white baseball cap and black jacket is kept; all of it is replaced with subject A's own.
The backing singer at the back on the left (short black hair, white zip-neck top with an orange bull-head logo on the chest) is removed and not replaced with anyone; the bookshelves behind show there.
The backing singer at the back on the right (silver-framed glasses, dark brown hair, red jacket with a white IU logo on the chest) is removed and not replaced with anyone; the bookshelves behind show there.
The person in the laughing close-up (red baseball cap with a white script-letter logo, black hoodie with ALABAMA printed on a red bar across the chest) is replaced with subject A ([Image 1], [Image 2]): none of the close-up person's face, hair, red baseball cap and black ALABAMA hoodie is kept; all of it is replaced with subject A's own.
The person playing the saxophone (dark skin, short hair, beard, navy blue hoodie with a white hood lining) is replaced with subject A ([Image 1], [Image 2]): none of the saxophonist's face, hair, beard and navy blue hoodie is kept; all of it is replaced with subject A's own.

Shot 1 (0 to 5.3 s): the band, in a close group shot framed from the chest up as in [Video 1], the keyboard at the very bottom of the frame. There is exactly one person in the picture: subject A ([Image 1], [Image 2]), sitting front and center, who sings "Outstanding" into the microphone on the very first note, gesturing with the hands and playing the keyboard while singing; nobody is behind the singer, where the crammed bookshelves show. None of the three people originally in the band shot of [Video 1] is left: not standing behind or beside the subjects, and not holding a subject in their arms.
Shot 2 (5.3 to 11.6 s): a hard cut. A close-up of subject A ([Image 1], [Image 2]) in front of the bookshelves: first with the face side-on, looking toward the left of the frame and smiling; at about 8.4 seconds turning to the camera with a hearty laugh; at about 9.5 seconds lifting one hand and gesturing in front of the chest; laughing on until the shot ends. The whole shot is one and the same person, subject A, from start to finish: it is them side-on, and still them after the turn, never another subject. Subject A wears their own clothes; the black ALABAMA hoodie and the red baseball cap of [Video 1] do not appear. Only subject A is in the picture.
Shot 3 (11.6 to 15 s): a hard cut. This shot is replaced too: the one playing the saxophone is subject A ([Image 1], [Image 2]) from its first frame to its last, not the man who plays the saxophone in [Video 1] (dark skin, short hair, beard, navy blue hoodie with a white hood lining); that man does not appear in a single frame, and his face, hairstyle, beard and navy blue hoodie are all replaced with subject A's. Subject A's age, sex, face, build and clothes come only from their own photos: if the photo shows a small child, the one playing the saxophone is that child, holding the saxophone in both arms to play it if it is bigger than they are, and not drawn as an adult or a teenager. A close-up of the saxophone solo, to the end: subject A wears headphones and plays with full concentration, the mouthpiece in the mouth, the saxophone held at subject A's own height. The head that shows in the bottom right corner of the frame in [Video 1] is removed here; the microphone and the bookshelves behind show there. Only subject A is in the picture.

People: the photos and waist-up portraits are used only to see the person; whatever and whoever is behind or beside them in the photo is not brought into the video; the background of every shot is the bookshelf office of [Video 1]. Each subject's size in the picture, distance from the camera and direction of head and body are the same as those of the person they replace. Age, height, build, sex characteristics, face shape, features, skin tone, hairstyle and hair color are the same as in their own photo: a child in the photo is a child in the video; a woman in the photo is a woman in the video. A child keeps a child's age, size and face in every shot: singing, playing the keyboard, playing the saxophone and standing at the back alike, holding the instrument or microphone even when it is bigger than they are, and is never drawn as an adult or a teenager. When singing and laughing, the eyes keep the size and shape they have in the photo. Subject A has the same face and the same clothes from start to finish, and is the same person in the band shot and in the close-ups. In the band shot and the sax shot everyone wears black over-ear headphones, on top of their own hair or hat; subject A in the laughing close-up wears no headphones. Hats and accessories are kept only if they are in the subject's own photo, with the same look and position; not one hat from [Video 1] is kept. Glasses follow only their own photo: if the photo shows glasses or sunglasses, the same pair is worn from start to finish; if the photo shows none, no glasses are worn. The silver-framed glasses of the person in the back row on the right in [Video 1] are not put on any subject.

Sound: use [Audio 1] as the sound of the whole video, kept exactly as it is, with no new lyrics, no re-singing and no other music or voices; subject A's mouth when singing is in sync with the lead vocal in [Audio 1].

9:16 vertical.

Must not appear: the faces and bodies of the five original people of [Video 1], including moved to the edge of the frame or showing only half a face, a hand or a bit of sleeve; anyone other than subject A; the camera pulling back, a wide angle, or legs, feet or the ceiling in shot; the white baseball cap, red baseball cap, white top, red jacket, black ALABAMA hoodie and navy blue hoodie of those people in [Video 1], and the silver-framed glasses of the one in the back row on the right; the letter G, the script letter, IU, the bull head and ALABAMA as logos or lettering, and any other team logo, letter, university name or brand logo; captions, text, watermarks; split screen; distorted faces.

3 people

Edit [Video 1]: replace only the people in [Video 1] with the three subjects below; everything else stays exactly as it is in [Video 1]. What stays unchanged includes: the framing, distance, camera position and camera movement of every shot; the two hard cuts at 5.3 and 11.6 seconds; the bookshelves, the lighting, the red keyboard and the microphones; and every move, gesture, head turn, expression and mouth shape, moment by moment, of the person who is replaced. Nothing of the replaced person is kept: that person's face, hair, beard, glasses, hat, clothes and the words and logos on the clothes are all replaced with the subject's own.

Subject lock (two images per subject: the face comes only from their original photo; hairstyle, build and clothes come only from their waist-up portrait):
Subject A: face from [Image 2]; hair, build and clothes from [Image 1]. Subject A appears in the back row of the band shot on the right, and is the person in the laughing close-up.
Subject B: face from [Image 4]; hair, build and clothes from [Image 3]. Subject B is the lead singer in the band shot, and their head also shows in the bottom right corner of the sax shot.
Subject C: face from [Image 6]; hair, build and clothes from [Image 5]. Subject C appears in the back row of the band shot on the left, and is the one playing the saxophone in the sax shot.

There are five people in [Video 1]; each is replaced with a subject above, and none of them is left:
The lead singer sitting front and center behind the red keyboard (white baseball cap with a red and black G logo, black jacket with red lettering on the chest) is replaced with subject B ([Image 3], [Image 4]): none of the lead singer's face, hair, white baseball cap and black jacket is kept; all of it is replaced with subject B's own.
The backing singer at the back on the left (short black hair, white zip-neck top with an orange bull-head logo on the chest) is replaced with subject C ([Image 5], [Image 6]): none of the backing singer's face, hair and white top is kept; all of it is replaced with subject C's own.
The backing singer at the back on the right (silver-framed glasses, dark brown hair, red jacket with a white IU logo on the chest) is replaced with subject A ([Image 1], [Image 2]): none of the backing singer's face, hair, silver-framed glasses and red jacket is kept; all of it is replaced with subject A's own.
The person in the laughing close-up (red baseball cap with a white script-letter logo, black hoodie with ALABAMA printed on a red bar across the chest) is replaced with subject A ([Image 1], [Image 2]): none of the close-up person's face, hair, red baseball cap and black ALABAMA hoodie is kept; all of it is replaced with subject A's own.
The person playing the saxophone (dark skin, short hair, beard, navy blue hoodie with a white hood lining) is replaced with subject C ([Image 5], [Image 6]): none of the saxophonist's face, hair, beard and navy blue hoodie is kept; all of it is replaced with subject C's own.

Shot 1 (0 to 5.3 s): the band, in a close group shot framed from the chest up as in [Video 1], the keyboard at the very bottom of the frame. There are exactly three people in the picture, in the three places of [Video 1]: subject B ([Image 3], [Image 4]), sitting front and center, who sings "Outstanding" into the microphone on the very first note, gesturing with the hands and playing the keyboard while singing; subject C ([Image 5], [Image 6]) standing in the back row on the left and subject A ([Image 1], [Image 2]) standing in the back row on the right, pumping their fists to the beat and singing along. None of the three people originally in the band shot of [Video 1] is left: not standing behind or beside the subjects, and not holding a subject in their arms.
Shot 2 (5.3 to 11.6 s): a hard cut. A close-up of subject A ([Image 1], [Image 2]) in front of the bookshelves: first with the face side-on, looking toward the left of the frame and smiling; at about 8.4 seconds turning to the camera with a hearty laugh; at about 9.5 seconds lifting one hand and gesturing in front of the chest; laughing on until the shot ends. The whole shot is one and the same person, subject A, from start to finish: it is them side-on, and still them after the turn, never another subject. Subject A wears their own clothes; the black ALABAMA hoodie and the red baseball cap of [Video 1] do not appear. Only subject A is in the picture.
Shot 3 (11.6 to 15 s): a hard cut. This shot is replaced too: the one playing the saxophone is subject C ([Image 5], [Image 6]) from its first frame to its last, not the man who plays the saxophone in [Video 1] (dark skin, short hair, beard, navy blue hoodie with a white hood lining); that man does not appear in a single frame, and his face, hairstyle, beard and navy blue hoodie are all replaced with subject C's. Subject C's age, sex, face, build and clothes come only from their own photos: if the photo shows a small child, the one playing the saxophone is that child, holding the saxophone in both arms to play it if it is bigger than they are, and not drawn as an adult or a teenager. A close-up of the saxophone solo, to the end: subject C wears headphones and plays with full concentration, the mouthpiece in the mouth, the saxophone held at subject C's own height; the head and half the face of subject B show in the bottom right corner of the frame. Only subject C and the head of subject B are in the picture.

People: the photos and waist-up portraits are used only to see the person; whatever and whoever is behind or beside them in the photo is not brought into the video; the background of every shot is the bookshelf office of [Video 1]. Each subject's size in the picture, distance from the camera and direction of head and body are the same as those of the person they replace. Age, height, build, sex characteristics, face shape, features, skin tone, hairstyle and hair color are the same as in their own photo: a child in the photo is a child in the video; a woman in the photo is a woman in the video. A child keeps a child's age, size and face in every shot: singing, playing the keyboard, playing the saxophone and standing at the back alike, holding the instrument or microphone even when it is bigger than they are, and is never drawn as an adult or a teenager. When singing and laughing, the eyes keep the size and shape they have in the photo. Each subject has the same face and the same clothes from start to finish, and is the same person in the band shot and in the close-ups; the faces of the different subjects stay their own. In the band shot and the sax shot everyone wears black over-ear headphones, on top of their own hair or hat; subject A in the laughing close-up wears no headphones. Hats and accessories are kept only if they are in the subject's own photo, with the same look and position; not one hat from [Video 1] is kept. Glasses follow only their own photo: if the photo shows glasses or sunglasses, the same pair is worn from start to finish; if the photo shows none, no glasses are worn. The silver-framed glasses of the person in the back row on the right in [Video 1] are not put on any subject.

Sound: use [Audio 1] as the sound of the whole video, kept exactly as it is, with no new lyrics, no re-singing and no other music or voices; subject B's mouth when singing is in sync with the lead vocal in [Audio 1].

9:16 vertical.

Must not appear: the faces and bodies of the five original people of [Video 1], including moved to the edge of the frame or showing only half a face, a hand or a bit of sleeve; anyone other than the three subjects above; the camera pulling back, a wide angle, or legs, feet or the ceiling in shot; the white baseball cap, red baseball cap, white top, red jacket, black ALABAMA hoodie and navy blue hoodie of those people in [Video 1], and the silver-framed glasses of the one in the back row on the right; the letter G, the script letter, IU, the bull head and ALABAMA as logos or lettering, and any other team logo, letter, university name or brand logo; captions, text, watermarks; split screen; distorted faces.

5 people

Edit [Video 1]: replace only the people in [Video 1] with the five subjects below; everything else stays exactly as it is in [Video 1]. What stays unchanged includes: the framing, distance, camera position and camera movement of every shot; the two hard cuts at 5.3 and 11.6 seconds; the bookshelves, the lighting, the red keyboard and the microphones; and every move, gesture, head turn, expression and mouth shape, moment by moment, of the person who is replaced. Nothing of the replaced person is kept: that person's face, hair, beard, glasses, hat, clothes and the words and logos on the clothes are all replaced with the subject's own.

Subject lock (two images per subject: the face comes only from their original photo; hairstyle, build and clothes come only from their waist-up portrait):
Subject A: face from [Image 2]; hair, build and clothes from [Image 1]. Subject A appears only in the laughing close-up.
Subject B: face from [Image 4]; hair, build and clothes from [Image 3]. Subject B is the lead singer in the band shot, and their head also shows in the bottom right corner of the sax shot.
Subject C: face from [Image 6]; hair, build and clothes from [Image 5]. Subject C appears only in the sax shot; there is no subject C in the band shot.
Subject D: face from [Image 8]; hair, build and clothes from [Image 7]. Subject D appears only in the back row of the band shot, on the left.
Subject E: face from [Image 10]; hair, build and clothes from [Image 9]. Subject E appears only in the back row of the band shot, on the right.

There are five people in [Video 1]; each is replaced with a subject above, and none of them is left:
The lead singer sitting front and center behind the red keyboard (white baseball cap with a red and black G logo, black jacket with red lettering on the chest) is replaced with subject B ([Image 3], [Image 4]): none of the lead singer's face, hair, white baseball cap and black jacket is kept; all of it is replaced with subject B's own.
The backing singer at the back on the left (short black hair, white zip-neck top with an orange bull-head logo on the chest) is replaced with subject D ([Image 7], [Image 8]): none of the backing singer's face, hair and white top is kept; all of it is replaced with subject D's own.
The backing singer at the back on the right (silver-framed glasses, dark brown hair, red jacket with a white IU logo on the chest) is replaced with subject E ([Image 9], [Image 10]): none of the backing singer's face, hair, silver-framed glasses and red jacket is kept; all of it is replaced with subject E's own.
The person in the laughing close-up (red baseball cap with a white script-letter logo, black hoodie with ALABAMA printed on a red bar across the chest) is replaced with subject A ([Image 1], [Image 2]): none of the close-up person's face, hair, red baseball cap and black ALABAMA hoodie is kept; all of it is replaced with subject A's own.
The person playing the saxophone (dark skin, short hair, beard, navy blue hoodie with a white hood lining) is replaced with subject C ([Image 5], [Image 6]): none of the saxophonist's face, hair, beard and navy blue hoodie is kept; all of it is replaced with subject C's own.

Shot 1 (0 to 5.3 s): the band, in a close group shot framed from the chest up as in [Video 1], the keyboard at the very bottom of the frame. There are exactly three people in the picture, in the three places of [Video 1]: subject B ([Image 3], [Image 4]), sitting front and center, who sings "Outstanding" into the microphone on the very first note, gesturing with the hands and playing the keyboard while singing; subject D ([Image 7], [Image 8]) standing in the back row on the left and subject E ([Image 9], [Image 10]) standing in the back row on the right, pumping their fists to the beat and singing along. None of the three people originally in the band shot of [Video 1] is left: not standing behind or beside the subjects, and not holding a subject in their arms.
Shot 2 (5.3 to 11.6 s): a hard cut. A close-up of subject A ([Image 1], [Image 2]) in front of the bookshelves: first with the face side-on, looking toward the left of the frame and smiling; at about 8.4 seconds turning to the camera with a hearty laugh; at about 9.5 seconds lifting one hand and gesturing in front of the chest; laughing on until the shot ends. The whole shot is one and the same person, subject A, from start to finish: it is them side-on, and still them after the turn, never another subject. Subject A wears their own clothes; the black ALABAMA hoodie and the red baseball cap of [Video 1] do not appear. Only subject A is in the picture.
Shot 3 (11.6 to 15 s): a hard cut. This shot is replaced too: the one playing the saxophone is subject C ([Image 5], [Image 6]) from its first frame to its last, not the man who plays the saxophone in [Video 1] (dark skin, short hair, beard, navy blue hoodie with a white hood lining); that man does not appear in a single frame, and his face, hairstyle, beard and navy blue hoodie are all replaced with subject C's. Subject C's age, sex, face, build and clothes come only from their own photos: if the photo shows a small child, the one playing the saxophone is that child, holding the saxophone in both arms to play it if it is bigger than they are, and not drawn as an adult or a teenager. A close-up of the saxophone solo, to the end: subject C wears headphones and plays with full concentration, the mouthpiece in the mouth, the saxophone held at subject C's own height; the head and half the face of subject B show in the bottom right corner of the frame. Only subject C and the head of subject B are in the picture.

People: the photos and waist-up portraits are used only to see the person; whatever and whoever is behind or beside them in the photo is not brought into the video; the background of every shot is the bookshelf office of [Video 1]. Each subject's size in the picture, distance from the camera and direction of head and body are the same as those of the person they replace. Age, height, build, sex characteristics, face shape, features, skin tone, hairstyle and hair color are the same as in their own photo: a child in the photo is a child in the video; a woman in the photo is a woman in the video. A child keeps a child's age, size and face in every shot: singing, playing the keyboard, playing the saxophone and standing at the back alike, holding the instrument or microphone even when it is bigger than they are, and is never drawn as an adult or a teenager. When singing and laughing, the eyes keep the size and shape they have in the photo. Each subject has the same face and the same clothes from start to finish; the faces of the different subjects stay their own. In the band shot and the sax shot everyone wears black over-ear headphones, on top of their own hair or hat; subject A in the laughing close-up wears no headphones. Hats and accessories are kept only if they are in the subject's own photo, with the same look and position; not one hat from [Video 1] is kept. Glasses follow only their own photo: if the photo shows glasses or sunglasses, the same pair is worn from start to finish; if the photo shows none, no glasses are worn. The silver-framed glasses of the person in the back row on the right in [Video 1] are not put on any subject.

Sound: use [Audio 1] as the sound of the whole video, kept exactly as it is, with no new lyrics, no re-singing and no other music or voices; subject B's mouth when singing is in sync with the lead vocal in [Audio 1].

9:16 vertical.

Must not appear: the faces and bodies of the five original people of [Video 1], including moved to the edge of the frame or showing only half a face, a hand or a bit of sleeve; anyone other than the five subjects above; the camera pulling back, a wide angle, or legs, feet or the ceiling in shot; the white baseball cap, red baseball cap, white top, red jacket, black ALABAMA hoodie and navy blue hoodie of those people in [Video 1], and the silver-framed glasses of the one in the back row on the right; the letter G, the script letter, IU, the bull head and ALABAMA as logos or lettering, and any other team logo, letter, university name or brand logo; captions, text, watermarks; split screen; distorted faces.

The instructions for 2 and for 4 people follow the same three shots; they differ only in which person takes which place in the band.

FAQ

Questions people ask

Something else? Contact us or see pricing.

What is Tiny Desk AI?

Tiny Desk AI is a TikTok trend of AI videos that put new people into a short office concert set to "Outstanding": a band at a red keyboard, a laughing close-up and a sax solo. On VideoEffect it is a 15-second video made from 1 to 5 photos.

How do I make a Tiny Desk AI video?

Open the generator on this page, pick how many people are in the band, upload a photo of each or one group photo, and press Create. The finished MP4 comes with the song on it.

Is it free?

The full 15-second video costs credits, from 7. Accounts that have never bought credits get one free 2-second preview of the opening band shot before paying.

What song is in the trend?

"Outstanding" by The Gap Band, as Charlie Wilson sang it to close his 2023 NPR Tiny Desk Concert. The clip uses the part heard in the trend's first TikTok post.

Is there a CapCut template for it?

TikTok tutorials for the trend point to CapCut templates. You do not need one here: the office, the cuts and the sound are already set in the generator, and only the people change.

How many people can be in the band?

One to five. One person plays all three featured parts; with five, every photo has its own part.

Can I use one group photo instead of separate photos?

Yes, for 2 to 5 people. Parts go from left to right in the photo. Separate photos keep faces sharper.

Can my dog or cat be in the band?

The effect is written and tested for people. Pet photos are not supported in this one.

How long does a video take to make?

The generator shows an estimated wait under the Create button before you pay. You can leave the page; the video is saved to your account.

Is the video a real performance?

No. The real performance is Charlie Wilson's 2023 concert. Trend videos, including yours, are AI remakes of a few seconds in the same style.

Tiny Desk AI

Make yours

The price is on the Create button before anything is charged, and a render that fails gives its credits back.