Create · Versely Agent

    Generate a slideshow from a prompt

    One prompt. A complete, curated slideshow.

    What you say to the agent

    No special syntax — just describe it like you would to a person.

    Create a 6-slide reel about 5 morning habits that changed my life
    Make a slideshow with the caption baked into each image — cozy fall aesthetic, 8 slides

    What it does, step by step

    1. 1

      Describe the theme, format (reel, story, post, carousel), and how many slides you want.

    2. 2

      The agent plans a per-slide brief, curates or generates a matching image for each slide, and applies overlay text if you gave it a style.

    3. 3

      There are two rendering styles: text stamped on top as an overlay (default), or the caption rendered INSIDE the image by the image model itself (typography integrated with the scene) — ask for either.

    What it needs from you

    • A text prompt describing what you want

    What comes back

    A complete slideshow — a set of images, one per slide, with your captions applied.

    What it costs

    Priced per image generated across the slideshow, shown before you confirm.

    Good to know

    • The caption-baked-in-image style is async — slides land over the next 30-90 seconds, not instantly.

    Under the hood

    This is what the agent actually calls when you ask for it — real tools from its live surface, not marketing copy.

    create_slideshowcreate_slideshow_caption_in_image

    Create a slideshow for social media (reel, story, post, carousel). Given the user's prompt, the tool auto-plans per-slide search queries + overlay text, curates the best matching image for each slide, and applies overlays if text_style is provided. End-to-end — do not chain with search_pinterest or image-generation tools.

    The full tool behind it

    See it done in a real workflow

    Or start from a one-tap template

    Frequently asked questions

    What do I actually say to the agent to generate a slideshow from a prompt?+

    Just describe it in plain English — for example: "Create a 6-slide reel about 5 morning habits that changed my life" The agent handles picking the right tool and model from there.

    What does the agent need from me first?+

    At minimum: A text prompt describing what you want. Anything else it needs, it asks for before running.

    What do I get back?+

    A complete slideshow — a set of images, one per slide, with your captions applied.

    Does this cost credits?+

    Priced per image generated across the slideshow, shown before you confirm.

    Anything I should know before asking for this?+

    The caption-baked-in-image style is async — slides land over the next 30-90 seconds, not instantly.

    You can also just ask for

    Ask your Versely agent to generate a slideshow from a prompt

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.