create_carousel
Generate carousel slides from content, URLs, or topics for LinkedIn, Instagram, and Threads by extracting key points and creating formatted PDFs or PNGs.
Instructions
Full pipeline: content → slides → PDF/PNG in one call. Supports three input modes:
Mode 1 (Content provided): Pass article text, markdown, or transcript in the content field. The tool extracts key points, generates slides, and produces output immediately.
Mode 2 (URL provided): Pass a sourceUrl. The tool fetches the page, extracts article content, and runs the full pipeline. If the page is JavaScript-rendered and extraction fails, the tool returns fallback instructions to use firecrawl_scrape or web_fetch instead.
Mode 3 (Topic only): Pass a topic without content or sourceUrl. The tool returns orchestration instructions with multiple research workflows: • Web Research: Use gemini_deep_research → pass result as content • YouTube Summary: Use supadata_transcript → summarize with gemini_chat → pass as content • Data-Driven: Use gemini_deep_research → preview_slides → generate_svg for charts → render_slides • Quick Draft: Use web_fetch to grab a page → pass as content
Common workflows the user might request:
"Make a carousel about [topic]" → Call with topic param, follow returned workflow
"Turn this article into a carousel: [url]" → Call with sourceUrl param
"Here's my content, make a carousel" → Call with content param
"Research [topic] and make a carousel with charts" → Call with topic, follow Data-Driven workflow
Platforms: linkedin (1080×1350 PDF), instagram (1080×1080 PNGs), threads (1080×1350 PNGs)
After rendering: Consider using analyze_image (Gemini MCP) to review the output quality.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| content | No | Article text, markdown, or transcript. Optional if sourceUrl is provided (content will be fetched). If neither content nor sourceUrl is provided, topic must be set. | |
| topic | No | Topic for the carousel. When set without content/sourceUrl, returns orchestration instructions for researching the topic first via available tools (Gemini, web fetch, Supadata). | |
| templateName | No | Template name (run list_templates to see options including user brand kits) | professional |
| brandName | No | Brand name shown in slide footers | |
| slideCount | No | Target number of slides (4-12) | |
| sourceUrl | No | URL to fetch article content from. The server scrapes and cleans HTML automatically. Also used for CTA slide link. | |
| outputDir | No | Output directory (default: ~/Documents/carousels/) | |
| platform | No | Target platform: linkedin (1080x1350 PDF), instagram (1080x1080 PNGs), threads (1080x1350 PNGs) |