Tiny Desk AI Video

Make the Tiny Desk meme from one photo: you or your pet on the mic, a band in black behind a crowded desk and a sax solo. 125 credits for 10 s.

This Tiny Desk AI page turns one photo into a 10-second vertical desk concert in four hard cuts: you, your pet or two adults sing at a vintage microphone in front of a crowded office desk, three backing singers in black sway behind a red keyboard, and a saxophonist plays a short solo. MiniMax H3 Max is asked for its own funk and soul groove, not the song "Outstanding", and this is not an NPR video. 10 seconds at 480P is 125 credits, quoted before you generate.

  • From 63 credits per clip
  • From your photos
  • 5s / 10s / 15s
  • 480P
  • Audio available

Loading your account…

Model

MiniMax H3 Max

Browse by task

One clear, well-lit photo: yourself, an adult who agreed to appear, two consenting adults together, or your pet. Pick the scene that matches the photo. JPG, PNG or WebP, up to 10 MB each.

What scene would you like to create?

Choose a scene. The prompt is fixed and cannot be edited.

Prompt960/2000

This page runs only the scenes above, so the prompt cannot be edited.

Actual output: 10s, 9:16, 480P. Writing “4K” in the prompt does not change this resolution. Faces and details may change; successful results still cost credits if you dislike them.

More settings · 9:16 · 10s · Audio
Aspect ratio
Duration
Resolution
Audio

Checking generation and private storage configuration.

Billing and delivery

Generate charges the displayed quote for the current length and resolution. If generation fails or the file fails our check, the credits come back automatically; a finished clip you don’t like is still charged. Finished clips stay in My videos.

Estimated cost: 125 credits
Sign in to generate

Sample result

10s · MP4
Lead singer at the desk concert.Made on Cicadas · MiniMax H3 Max · 10s
Made from these photos (AI-made, fictional)
  • Your photoYour photo
Use this recipe

About Tiny Desk AI video on Cicadas

The Outstanding Tiny Desk meme recasts the moment Charlie Wilson and his band perform "Outstanding" in his 2023 NPR Tiny Desk concert with a cast that clearly doesn't belong there; one of the most popular early examples featured college football coaches whose teams had just lost. This page makes the format, not the original clip. Pick the lead singer, pet or duet scene and add one clear photo. MiniMax H3 Max then builds a crowded desk concert around it in four cuts (a profile at the mic, the band, a laughing close-up, the sax solo) with a groove of its own underneath.

To sing your own recording in a train seat, use subway singing AI; for a dance trend from your photo, the Gangnam Style AI video. For a cat that nods to a beat, try cat jam AI; the MiniMax H3 page lists what the model behind this page costs per second.

Tiny Desk AI video examples made on Cicadas

From your photos10s · 480P

Lead singer at the desk concert.

MiniMax H3 Max reference to video, 10 seconds at 480P with sound, vertical, from the site's sample photo of a woman. Four cuts: she stands in profile beside a vintage microphone in an office full of books, lamps and a cluttered desk; three backing singers in black clap behind a red keyboard, the middle one shaking a tambourine; a chest-up close-up where she throws her head back laughing, sings and raises a hand; a saxophonist in black holding his saxophone, not playing it, his face cut off at the top of the frame. Her curly hair, mustard sweater and jeans match the photo. The front of the keyboard carries made-up lettering. The sound was not listened to.

Made from these photos (AI-made, fictional)
  • Your photoYour photo
Use this recipe ↗
From your photos10s · 480P

The dog takes the mic.

MiniMax H3 Max reference to video, 10 seconds at 480P with sound, vertical, from the site's sample photo of a terrier. Four cuts: the dog sits on a wooden stool behind a vintage microphone in front of a desk and shelves of records; three backing singers in black sing into microphones behind a red keyboard, one shaking a tambourine; a close-up of the dog at the microphone opening its mouth as if singing, ears lifting; a saxophonist in black playing. The wiry tan coat, dark ears, white chest and teal collar match the photo. The front of the keyboard carries made-up lettering. The sound was not listened to.

Made from these photos (AI-made, fictional)
  • Your photoYour photo
Use this recipe ↗

Why use Cicadas for Tiny Desk AI video

You on the mic, a band behind you

Your photo is a reference, not the first frame, so the model can place you at the microphone and cut away to the band. You are in two of the four shots: the opening profile and the laughing close-up. For the backing singers and the saxophonist, the scenes ask for new, anonymous musicians.

Four cuts in the meme's order

Every scene asks for the same sequence: a profile at the mic, a wide shot of three backing singers in black behind a red keyboard, a chest-up close-up where the lead laughs and sings, then a saxophone solo. You pick lead, pet or duet; the shot order and wording stay the same.

Its own music, not "Outstanding"

The scene asks the model for an upbeat funk and soul groove with wordless backing vocals and no lyrics; it is not given "Outstanding" or any other recording. If you want a particular track under your clip, add it in your editor, and only use music you have the right to post.

Price before you generate

At 480P, 10 seconds is 125 credits, about $1.24 on the $9.90 first pack of 1,000 credits; 5 seconds is 63 and 15 seconds is 188, and 768P makes them 100, 200 and 300. The quote sits on the button, and a failed job returns its credits.

How to use Tiny Desk AI video

  1. 01

    Sign in and pick a scene: Lead singer (one person), On the mic (a pet) or Duet (two adults).

  2. 02

    Add one clear, well-lit photo, keep 10 seconds or choose 5 or 15, and check the quote.

  3. 03

    Tick the photo confirmation, generate, and download the MP4 from My videos.

Four shots, not the template's five

The remakes that copy the original run about 19 seconds in five shots and end on the band. One generation here is 5, 10 or 15 seconds, so the scenes ask for four shots and end on the sax solo. If you want the band shot again at the end, make a second clip and join them in your editor.

Which photo works best

A face looking roughly toward the camera, even light and nothing covering the mouth give the model the most to keep in the close-up, where your face is largest. For the Duet scene use one photo with both adults in it; sunglasses, masks and heavy filters make the singer harder to hold.

Other music memes on Cicadas

To sing your own recording in a train seat, see subway singing AI. For a cat that nods along to a beat, there is cat jam AI, and for a new music-video scene from your photos, burning bridges AI.

Tiny Desk AI video prompt ideas

These are the tested scenes on this page. Each scene is fixed and its prompt is read-only: pick one above, or press “Use this prompt”.

  • “A small crowded desk concert in an office, vertical, four shots with hard cuts, warm desk lamps, shelves packed with books and records behind the band. Shot 1: side profile of the person from Image 1 at a vintage microphone in front of the desk, swaying their shoulders to the beat. Shot 2, hard cut: wide shot of three anonymous backing singers dressed in black behind a red keyboard, clapping and swaying, one shaking a small tambourine. Shot 3, hard cut: chest-up close-up of the person from Image 1 at the microphone, head tilting back in a big laugh, then singing with a wide open smile and waving one hand. Shot 4, hard cut: close-up of an anonymous saxophonist in black playing a short solo. Keep the person's face, hair and clothes as in the photo. Sound: an upbeat live funk and soul groove with bass, drums, keys and a saxophone line, wordless ooh backing vocals, no lyrics, no recognisable song. No text, no logos, no signs, no other close-up faces.”

  • “A small crowded desk concert in an office, vertical, four shots with hard cuts, warm desk lamps, shelves packed with books and records behind the band. Shot 1: the pet from Image 1 sits on a stool in front of a vintage microphone, bobbing its head to the beat. Shot 2, hard cut: wide shot of three anonymous backing singers dressed in black behind a red keyboard, clapping and swaying, one shaking a small tambourine. Shot 3, hard cut: close-up of the pet from Image 1 at the microphone, opening its mouth as if singing, ears perking up, head tilting with the music. Shot 4, hard cut: close-up of an anonymous saxophonist in black playing a short solo. Keep the pet's face, fur colour and markings exactly as in the photo. Sound: an upbeat live funk and soul groove with bass, drums, keys and a saxophone line, wordless ooh backing vocals, no lyrics, no recognisable song. No text, no logos, no signs, no other animals.”

  • “A small crowded desk concert in an office, vertical, four shots with hard cuts, warm desk lamps, shelves packed with books and records behind the band. Shot 1: the two consenting adults from Image 1 stand side by side at one vintage microphone in front of the desk, swaying together. Shot 2, hard cut: wide shot of three anonymous backing singers dressed in black behind a red keyboard, clapping and swaying, one shaking a small tambourine. Shot 3, hard cut: close-up of the two adults from Image 1 sharing the microphone, laughing and singing to each other with wide smiles. Shot 4, hard cut: close-up of an anonymous saxophonist in black playing a short solo. Keep both faces, hair and clothes as in the photo. Sound: an upbeat live funk and soul groove with bass, drums, keys and a saxophone line, wordless ooh backing vocals, no lyrics, no recognisable song. No text, no logos, no signs, no other close-up faces.”

Tiny Desk AI video FAQ

Tested on Cicadas · reviewed 2026-11-03

Local implementation, 2026-11-03. Three locked MiniMax H3 Max reference-to-video scenes (one person, one pet, two adults at a microphone in a crowded office desk concert, four hard cuts, model-made music with no song). Two samples recorded on 2026-11-03 (docs/research/claude-tiny-desk-20261103/samples/, owner cap USD 1.50, USD 0.50 each at list price), 10 seconds at 480P, vertical, sound on: Lead singer (sample woman) and On the mic (sample terrier). Both show the four cuts in order: profile beside the microphone, three backing singers in black behind a red keyboard with a tambourine, the laughing and singing close-up, the saxophonist (holding the horn without playing it in the lead clip). Likeness, clothes, coat and collar match the photos; in both clips the keyboard front carries made-up lettering. Not run: the Duet scene, 5 and 15 seconds, 768P. The audio was measured, not listened to.

Updated Nov 3, 2026 · How we test