A carousel and a reel are the same images with different delivery, and the reel is the one that gets pushed to people who don't follow you. convert_slideshow_to_video takes a slideshow you've already built and renders it as a video: duration_per_image sets the pace, transition sets how each slide moves into the next, and output_resolution and aspect_ratio set the shape it lands in.
The parameter to know about is use_edited_images. If you stamped text on the slides with add_text_overlay, that flag is what makes the video carry the captioned versions rather than the bare originals — the difference between a reel that works on mute and one that doesn't.
Powered by
Convert a slideshow into a video with transitions and optional audio. Use after creating a slideshow when user wants a video/reel version. The video is uploaded to cloud storage and the URL is returned.
What to tell the agent
Versely's agent maps this plain-English request directly onto convert_slideshow_to_video. You don't need to know the parameter names — just describe what you want.
“Turn my last slideshow into a 9:16 reel — 2.5 seconds per slide, use the versions with the text on them, and put a lo-fi track under it.”
How it works
1. Get the slideshow's id
get_slideshow pulls the current slideshow and its id — worth doing anyway, since it's the last chance to see the slides in order before they become a video.
2. Set the pace and the transition
duration_per_image controls how long each slide holds; transition controls how one becomes the next. Short holds suit a hook-led reel, longer ones suit an explainer.
3. Bring the audio
music_url and voiceover_url both take a track directly. Generate them first with generate_music or generate_speech if you don't already have files.
4. Choose the images and the shape
use_edited_images picks the overlay-stamped versions rather than the originals; aspect_ratio and output_resolution set the export format.
What it costs
The slide images were already paid for when the slideshow was generated — this is a render pass over them. Any music or voiceover you generate for it is billed separately on generate_music / generate_speech. Ask the agent for estimate_cost before rendering a long set.
The formula behind that number: What does editing a video cost if I keep changing it? — charges per finished export, so iteration is free and the count is the whole bill.
Limits & things to know
- It renders the slideshow as it currently stands — fix, replace or reorder slides first (see fix-a-slide-in-a-slideshow), because editing the exported MP4 afterward is much harder than editing the slideshow.
- Forget use_edited_images and you'll get a video of the untouched originals with none of your overlay text on it.
- duration_per_image is one value for the whole set, not a per-slide timing.
- music_url and voiceover_url expect existing audio — this tool doesn't write a track for you.
Who uses this
- Republishing an Instagram carousel as a Reel or TikTok
- Turning a product listicle into a narrated video
- Making a video version of a slide deck for a paid placement
- Getting a second, differently-formatted post out of one set of images
Frequently asked questions
Will my slide captions appear in the video?+
Only if you set use_edited_images. Without it the render uses the original, un-stamped images and your overlay text is missing from the video.
Can I add music and a voiceover?+
Yes — music_url and voiceover_url both take a track. Generate them first with generate_music or generate_speech if you don't already have the files.
Can different slides stay on screen for different lengths?+
No — duration_per_image applies to the whole set. For per-item timing, build the sequence with compose_video_with_overlay instead, where each image item has its own duration_sec.
What aspect ratio does it export at?+
Whatever you set — aspect_ratio and output_resolution are both parameters, so the same slideshow can go out as a 9:16 reel and a 1:1 feed post.
Related Versely tools
Related editing jobs
Turn a Slideshow Into a Video inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.