AI Photo Slideshow

An AI photo slideshow is a video built automatically from a set of still photos, with the pacing, transitions, on-screen text and background music decided by AI rather than assembled by hand. You supply the images and a few choices about mood, shape and length, and the tool works out how long each photo holds, where the scene changes fall against the music, and what the captions say. It is the difference between arranging a timeline yourself and describing the feeling you want.

AI Photo Slideshow runs on credits, and the Generate Video button always shows what a video will cost before you click, calculated from how many photos you uploaded and which duration you picked. If you are on a free account and have no credits available, a 15-second generation is applied at no cost instead, and that video is fully downloadable rather than a locked preview. It works once per account, so choose the photos you actually care about.

For images you can upload JPG, PNG and WEBP files, up to 120 images in one video, with each file up to 10 MB and an aspect ratio between 1:2.5 and 2.5:1. Anything outside those limits is skipped during upload and you are told which files did not make it, so a single odd file will not block the rest of the batch. If you bring your own soundtrack it needs to be an MP3, at least 15 seconds and no longer than 10 minutes, up to 900 MB.

MyEdit recommends the minimum number of photos based on the duration and tempo you select, and updates the recommendation whenever you change either one. As a guide, we recommend 3 to 5 photos for a 15-second video, 6 to 8 for 30 seconds, 11 to 15 for 60 seconds, and 15 to 23 for 90 seconds, with the higher number applying to Fast tempo. These are only guidelines, though: you can upload fewer or many more photos and still generate your video.

Yes. Under Background Music, choose Import audio and upload an MP3, or simply drop a file onto the upload field and the selection switches over for you. The field becomes a small player so you can check you picked the right track. One thing worth knowing: the Slow, Normal and Fast tempo options only apply when the music is being matched by AI, because that is what allows scene changes to be placed on the beat. Switch back to Automatch with AI and your previous tempo choice returns.

The generated text elements can be written in English or Japanese. The default follows the language your interface is set to, so a Japanese interface produces Japanese text and every other locale falls back to English, and you can change it in the Language dropdown before generating. Prefer a video with no words at all? Switch the Add AI Text toggle off and the result is photos and music only, with the text tab hidden from the editing view.

Yes, and this is where most of the shaping happens. Click any scene in the preview and its contents open in the right panel, split into a Text tab and a Photo tab. Text can be rewritten and restyled: font, size, color, line height, and position on screen. Photos can be scaled, nudged into a better position inside the frame, or swapped out with Replace Image. You can also hide the AI text on one scene without regenerating anything.

Four aspect ratios are available: 16:9 for YouTube and desktop viewing, 9:16 for Reels, Stories and TikTok, 4:5 for a taller social post, and 1:1 for square grids. Lengths are 15, 30, 60 and 90 seconds. Both are chosen before you generate rather than cropped or trimmed afterward, which matters because the layout and text placement are composed for the shape you selected instead of being squeezed into it later.

No. The tool runs in a browser tab on your desktop or laptop, so there is nothing to install, no plugin and no updates to chase, and you can begin without entering payment details. Note that this feature is currently built for computer browsers rather than phones. Finished videos are saved to your cloud library under a Photo Slideshow Video folder in the Video tab, and exporting saves a copy there automatically alongside the file you download.