🎬 Create UGC-style Instagram Reels from product URLs with OpenAI, Sisif, and Slack

⚡ 56 views · 🎬 Content Creation & Video

💡 Pro Tip — Heads up — if this workflow’s Instagram scraping breaks (it happens whenever Meta updates their frontend), ScraperNode is a community node that handles profiles, posts, reels, and comments without any HTML parsing.

View All Scrapers

Description

Quick overview

Paste a product page URL and get three UGC-style 9:16 video ad variants rendered by Sisif (https://sisif.ai/product-ads/), plus a hook, script and caption. Reviewers pick the winner in Slack, and the approved video is published as an Instagram Reel.

How it works

  1. Receives a product URL from an n8n form trigger or a POST webhook request.
  2. Fetches the product page HTML and extracts the title, description, and cleaned page text.
  3. Uses OpenAI to generate a UGC-style hook, short script, Instagram caption, and three distinct visual prompts.
  4. Sends each prompt to Sisif to generate a 5-second 720×1280 video, polling Sisif for completion up to 40 times.
  5. Posts the available video variant links to Slack and waits for a reviewer to choose a variant or reject.
  6. If a variant is approved, creates an Instagram Reels media container via the Facebook Graph API, polls until processing is finished, and then publishes the Reel.

Setup

  1. Create a Sisif API key at https://sisif.ai/users/api-keys/ and save it in n8n as an HTTP Bearer Auth credential for the Sisif generate and status-check requests.
  2. Add an OpenAI API credential (or replace the chat model) for the ad hook, script and caption generation.
  3. Connect Slack OAuth credentials and select the channel where the approval message is posted.
  4. Add Facebook Graph API credentials with permissions to publish Reels (including instagram_basic and instagram_content_publish) for an Instagram Business/Creator account linked to a Facebook Page.
  5. Replace YOUR_IG_USER_ID in the workflow settings with your Instagram User ID (and adjust the Graph API version if needed), then test by submitting the form or calling the webhook.

Requirements

🔗 Nodes Used

HTTP Request, Slack, Webhook, Stop and Error, Basic LLM Chain, OpenAI Chat Model

📥 Import

Download workflow.json and import into n8n: Workflow menu → Import from File

📖 Importing guide · 🔑 Credential setup