tools

Write a TikTok/Instagram-style slideshow: hook, per-slide copy, caption, and hashtags, in any supported language

Write a TikTok/Instagram-style slideshow: hook, per-slide copy, caption, and hashtags, in any supported language. Costs 1 platform credit and returns the script for review. Set render_images=true to start image rendering right away (1 extra credit per slide), then poll get_slideshow until status is 'ready'. Pass slide_images to composite the slides on the account's own photos (Instagram carousel mode) and output_format for 9:16, 4:5, or 1:1 geometry. Call list_media_capabilities for the valid style, template, and collection ids.

post/api/mcp/tools/generate_slideshow

Request

  • Base URL: https://finestructure.ai
  • URL: https://finestructure.ai/api/mcp/tools/generate_slideshow
  • Auth: HTTP bearer

Request body

goalstring required

What the slideshow should achieve or teach.

languagestring

ISO code such as 'en' or 'he'. Defaults to 'en'.

content_stylestring

Copy archetype, e.g. x_ways, storytelling, countdown_ranking.

visual_stylestring

Visual look, e.g. bold_gradient, tiktok_native_photo.

templatestring

Built-in template id whose voice spec dominates the output.

slide_countinteger

Fixed number of slides. Omit for the style's natural range.

narrative_devicestring

Framing device, e.g. metaphor or famous_quote.

x_ways_substylestring

How numbered ways are written (x_ways content style only).

authentic_modeboolean

Lowercase, unpolished 'real person' voice.

with_graphicsboolean

Rich visuals vs clean text-only slides. Default true.

enhancedboolean

Use the higher-quality (more expensive) image model.

text_alignstring

left, right, or center.

accent_colorstring

Hex accent for the chip text style.

collectionstring

Saved photo collection id to pull slide photos from.

output_format'tiktok' | 'ig_portrait' | 'ig_square'

Slide geometry: tiktok 9:16 (default), ig_portrait 4:5 Instagram carousel, ig_square 1:1.

slide_imagesstring[]

Up to 10 of the account's own photos, in slide order, each a data:image/... URL or public https URL. When present, the slides are composited on these exact photos: one slide per image, no CTA slide appended.

slide_textsstring[]

Per-slide overlay text in slide order, up to 300 chars each. Kept verbatim; leave an entry empty (or omit the array) to have the AI write it.

cta_urlstring

Link promoted on the final slide. Omit for pure-value content.

cta_platformsstring[]

What the CTA actually offers.

sales_bridgeboolean

Add pre-sale bridge slides before the offer.

series_partinteger

Part number for a recurring series.

voice_specstring

A reference voice spec to reproduce exactly.

render_imagesboolean

Start rendering images immediately after the script. Default false (review first).

Response

Tool executed successfully

okboolean required
toolstring required
resultobject required

Changes

No recorded changes to this operation across all 2 revisions of this API.