Most people have the photos already. A trip on their phone, a listing shot by the agent, the product on a white table, the before and after of a kitchen. What they don't have is the time to turn them into a video someone will watch. TallyReel does that: you pick the photos and short clips in the order you want, the AI writes one line for each, and it makes a video with a voice reading over them, gentle zooms on the photos, captions and music.
This page covers how a photo video gets made, the six kinds it is written for, 36 ideas, two example scripts written one line per photo, and the questions people ask first.
Updated 31 October 2026 · by Danish, who makes TallyReel
About 30 seconds each when read aloud. Paste one into TallyReel as your own script, or change the details first.
The script behind the video above
A Bright Flat by the Park
1
Come in. This is a bright two-bedroom flat, with morning light in every room.
2
The living room faces east, so the sun comes in early and stays until lunch.
3
The kitchen was redone last year, with plenty of counter space and a window over the sink.
4
The main bedroom fits a double bed and a desk, and the wardrobe is built in.
5
A small balcony looks out over the park. It's the spot for your morning coffee.
6
Two minutes to the station, five to the shops. Message us to book a viewing this week.
Script 2
Three Days in Lisbon
1
Three days in Lisbon, and I still can't believe how steep the hills are.
2
Day one, we rode the old yellow tram up to Alfama and got lost on purpose.
3
Day two was custard tarts for breakfast. And for lunch. Don't judge.
4
We watched the sunset from a viewpoint, with half the city sitting there with us.
5
Day three, a train out to Sintra and a palace painted like a birthday cake.
6
If you go, bring good shoes. Your legs will thank you.
How a photo video gets made
Photo videos start from the box on Home in the TallyReel web app: drop in your photos and clips and say what the video is.
1. Add your photos and short clips from your phone or computer, in the order you want them shown.
2. Say what it is in a line: memories, a travel diary, a product, a property tour, an event recap or a before and after.
3. Optionally write what you want said, like the address and asking price or the names of the people in the photos.
4. The AI writes one line for each photo, in your language. Read them and change any line before anything is made.
5. Pick a voice, captions and music, or choose music only, where each line becomes a short caption on screen instead.
6. Each photo gets a gentle zoom while its line is read, clips play as they are, and the video is ready to download or post.
Getting the photos right
Order matters more than anything else. A property tour should walk the way a visitor would: front door, living room, kitchen, bedrooms, the view. A trip reads best day by day. A before and after should hold the reveal until the end. Put your strongest photo first, because the first two seconds decide whether someone keeps watching.
Each photo stays on screen for about five seconds with a voice, or about three and a half with music only. So 12 photos make a video of about a minute, and 30 photos stay under three minutes. Use tall photos for Reels, Shorts and TikTok, and mix in a short clip or two if you have them: a bit of real movement keeps a slideshow from feeling like a slideshow.
Telling it what to say
Without a note, the lines are written from the kind of video and what your files are called, which works for memories and travel. For anything with facts (a listing, a product, an event), add a short note with what must be said: the number of rooms, the price, the date, the offer, who to thank. The AI follows it, and you can still edit every line. Photo videos cost what any video of the same length costs, 100 credits a minute, by the second.
Questions
How do I turn my photos into a video with AI?
Drop your photos and clips into the box on Home and say what the video is. Check the script, pick a voice and music, and it makes the video with captions.
How many photos can I use?
Up to 30 photos and clips in one video. With a voice each photo stays on screen for about five seconds.
Can I make a photo video with just music, no voice?
Yes. Choose music only and each line becomes a short caption on screen instead of being read aloud.
Can real estate agents use it for listings?
Yes. Say it is a property tour, add the details you want said, and put the photos in the order a visitor would walk through.
Can the video be in another language?
Yes. The lines are written in the language you pick, including Hindi, Urdu, Spanish and Arabic, and read by a voice in that language.
Type the idea into TallyReel, read the script, and it makes the video for you: in the browser, on your phone, or in Studio on your own computer. Start on the free plan.