I built a Tiny Desk AI generator that turns one photo into a 15-second concert video

Description and use

A web tool turns 1–5 photos into a 15‑second Tiny Desk‑style concert video with synchronized audio and a no‑music option.

Problem

Users want to create a Tiny Desk‑style concert video from a single photo without complex editing.

Outcome

The tool produces a short concert video with consistent identities and audio sync, offering both music and no‑music versions for platforms that mute copyrighted audio.

Workflow

• Upload 1–5 photos to the site
• The system generates a reference portrait for each person
• Video generation is conditioned on these portraits
• Audio is synced to the video
• The service outputs a 15‑second 720p MP4 and a no‑music cut

Evidence

You upload one to five photos. The first person sings lead, the second plays sax, the rest sing backup, and any empty spots get filled with AI musicians.

Source

About a minute later you get a 15-second vertical 720p MP4 with the stage audio, plus a no-music cut for platforms that flag copyrighted audio.

Source

Multi-person identity consistency is the hard part. Keeping the same face across a wide, moving stage shot meant generating a reference portrait per person first, then conditioning the video generation on those, rather than trying to do face swap afterwards.

Source

Audio sync matters more than resolution. People forgive 720p, they do not forgive the singer's mouth being off by 200ms.

Source

A no-music export is not optional. TikTok and Reels muting the whole clip is worse than shipping two files.

Source

Guests should not have to make an account. It is a guest checkout at $7.99 per video; adding a signup wall cut conversions badly in testing.

Source