Slides in, video out: convert_slideshow_to_video does not invent the board

Slides in. A finished video out. Turn a slideshow into a video is a render of a slideshow you already have. convert_slideshow_to_video needs a slideshow_id. It does not write slides, does not generate a cinematic clip from a sentence, and does not compose random stills you never put on a board. Using it as a text-to-video shortcut, or converting a board you still intend to reorder, spends a render on an MP4 you will throw away — and the slide images were already paid if they were generated.

The tool sets per-image duration, transition, output resolution, aspect, and optional voiceover_url / music_url. Audio URLs must already exist; this call does not write a track. use_edited_images is whether stamped overlays come along. Forget that flag and you render bare originals. The AI slideshow maker is the wider slideshow surface; this agent job is the convert.

You need a slideshow first

No board, no convert. Build from a prompt with generate a slideshow from a prompt, or from your own photos with turn photos into a slideshow. Change a slide with edit an existing slideshow. Then convert. "Make me a vertical video about coffee" into this job is the wrong noun: that is either a clip generate or a slideshow create, depending on whether you wanted motion or cards.

Stitching loose images into one video without a slideshow project is also not this tool. That is a compose/stitch job. Convert is the carousel you already named, paced, and (if you stamped copy) overlaid.

Rendering is a flat processing step, not a per-model generation. The exact cost is shown before it runs. Cheap compared with a video model, still not free, and a second convert after you fix slide 3 is a second process. Fix the board first.

Pace is one number

duration_per_image is one hold for the set. It is not per-slide storytelling and it is not a camera move. If you needed a six-second push-in on one product still, that is image-to-video, not a 3-second crossfade across eight cards. Pick the job that matches the motion you actually want.

FAQ

Can convert_slideshow_to_video generate the slides for me?

No. It renders slideshow_id. Create or edit the slideshow in its own jobs, then convert.

Should I convert a draft to "see the pace"?

Only if you accept a throwaway MP4. Reorder and overlay on the board; convert the signed set. Each convert is a process you do not need twice.

Does this write the voiceover?

No. Pass a voiceover_url or music_url you already have, or attach later. Speech and music are their own generates.

Is this the same as text-to-video?

No. Text-to-video invents motion in one clip. This tool paces stills you already arranged. Different artifact, different credit shape.