Singing Photos: Your Guests Sing Your Brand Jingle in the AI Photo Booth
The photo is taken. Then it starts to sing.
A guest steps up to the booth, takes a photo, and the AI does its usual work: new scene, your product in their hand, the look you configured. Then the result opens its mouth and sings your jingle. Ten seconds later the crowd around the booth knows your slogan by heart.
That is Singing photos, available today on the Pro and Enterprise plans. It is a finish step on any Live Edit booth, not a separate mode: keep your prompts, your product placement and your delivery settings, add a jingle, and every photo becomes a short singing video.
What the guest sees
- The photo is taken and transformed like any AI photo: Nano Banana, Nano Banana Pro, GPT Flare or GPT Sunburst, your choice per booth.
- The video renders and plays on the booth screen, full size, with the QR code next to it. People behind the guest watch it too.
- The guest scans the QR code and gets the same video on their phone, ready to share. Email delivery and the share page carry the video as well.
The extra wait is short: about 30 seconds more with Nano Banana, 40 with GPT Flare, 55 with GPT Sunburst. The dashboard shows the estimate next to the model you pick.
Your jingle, prepared once
The jingle lives in Assets, next to your logos and products. You make it once, before the event:
- Write the lyrics with your brand name and slogan, pick a style (pop, rock, funk, kids chorus, anything you can describe), and generate. The AI sings it in a man’s voice and a woman’s voice, and optionally a boy’s and a girl’s, so every guest gets a voice that fits. Gender detection picks the right one at the booth.
- Or upload your own brand jingle, one file for everyone or one per voice.
- Listen and approve. Every generated jingle comes back with a transcript, so you can check that the brand name is pronounced right before the first guest hears it. Not happy with a word? Add a pronunciation hint (Aitek becomes “Eye-tek”) and regenerate.
Jingles run 5 to 14 seconds. Ten seconds is the sweet spot: long enough for the brand name twice, short enough that the next guest is not waiting.
Where it lands
- Product launches: the guest holds the product and sings its name. Product placement works on all four image models, so the sponsor’s bottle, box or bag is in the shot, exact logo and colors. See our guide to product placement at events.
- Brand activations: a queue of people singing the same three lines on a big screen is the kind of moment a brand activation is built for.
- Trade shows: the booth becomes the loudest thing on the floor without a speaker system. Trade show engagement with a chorus.
- Holiday parties and weddings: the company anthem, the couple’s song, or one silly line everyone will quote for a year.
What it costs
A singing photo costs 7 credits: 1 for the photo and 6 for the video, the same 6 credits as our AI video animation. The jingle itself costs 2 credits per voice file, generated or uploaded, paid once and never again, however many guests sing it.
Both prices are shown in the dashboard before you enable anything, in line with our transparent pricing.
How to set it up
- Open a photobooth in the dashboard, or create one with the wizard.
- In the delivery step, turn on Singing photos and pick a jingle, or create one right there.
- Run a test photo. The video plays on the booth screen and on the share page.
Singing photos run on the Windows app today and come to the tablet app in its next update. As of September 2026, none of the six vendors in our comparison offers a singing mode.
FAQ
What are Singing photos?
A finish step on a Live Edit booth. After the AI photo is generated, it becomes a short video in which the guest sings a jingle prepared by the operator. The video plays on the booth screen and is delivered by QR code, email and the share page.
Do I need to record the jingle myself?
No. Write the lyrics and a style in the dashboard and the AI generates the song, in a man’s voice and a woman’s voice (kids’ voices optional). You can also upload a jingle you already have.
Can the guest hold my product while singing?
Yes. Product placement works with all four image models, so the product is in the photo and in the video.
How long is the video?
Between 5 and 14 seconds, matching the jingle. Ten seconds is the default.
Which plans include it?
Pro and Enterprise. It costs 7 credits per singing photo, plus 2 credits per voice file when you create the jingle.