Loading page
How it works This template is an interactive, step-by-step tutorial designed to teach you the most important skill in n8n: using expressions to access and manipulate data. If you know what JSON is but aren't sure how to pull a specific piece of information from one node and use it in another, this workflow is for you. It starts with a single "Source Data" node that acts as our filing cabinet, and then walks you through a series of lessons, each demonstrating a new technique for retrieving and transforming that data. You will learn how to: 1. Access a simple value from a previous node. 2. Use n8n's built-in selectors like .last() and .first(). 3. Get a specific item from a list (Array). 4. Drill down into nested data (Objects). 5. Combine these techniques to access data in an array of objects. 6. Go beyond simple retrieval by using JavaScript functions to do math or change text. 7. Inspect data with utility functions like Object.keys() and JSON.stringify(). 8. Summarize data from multiple items using .all() and arrow functions. Set up steps Setup time: 0 minutes! This workflow is a self-contained tutorial and requires no setup or external credentials. 1. Click "Execute Workflow" to run the entire tutorial. 2. Follow the flow from the "Source Data" node to the "Final Exam" node. 3. For each lesson, click on the node to see how its expressions are configured in the parameters panel. 4. Read the detailed sticky note next to each lesson—it breaks down exactly how the expression works and why. By the end, you'll have the foundational knowledge to connect data and build powerful, dynamic workflows in n8n.
by Lucas PeyrinAutomate video ads with NanoBanana, Seedream 4, ChatGPT Image and Veo 3 Who is this for? This template is designed for marketers, content creators, and e-commerce brands who want to automate the creation of professional ad videos at scale. It’s ideal for teams looking to generate consistent, high-quality video ads for social media without spending hours on manual design, editing, or publishing. What problem is this workflow solving? / Use case Creating video ads usually requires multiple tools and a lot of time: writing scripts, designing product visuals, editing videos, and publishing them across platforms. This workflow automates the entire pipeline — from idea to ready-to-publish ad video — ensuring brands can quickly test campaigns and boost engagement without production delays. What this workflow does 1. Generates ad ideas from Telegram input (text + product image). 2. Creates product visuals using multiple AI image engines: Seedream 4.0 (realistic visuals) NanoBanana (image editing & enhancement) ChatGPT Image / GPT-4o (creative variations) 3. Produces cinematic video ads with Veo 3 based on AI-generated scripts. 4. Merges multiple short clips into a polished final ad. 5. Publishes automatically to multiple platforms (TikTok, Instagram, LinkedIn, X, Threads, Facebook, Pinterest, Bluesky, YouTube) via Blotato. 6. Stores metadata and results in Google Sheets & Google Drive for easy tracking. 7. Notifies you via Telegram with the video link and copy. Setup 1. Connect your accounts in n8n: Telegram API (for input and notifications) Google Drive + Google Sheets (storage & tracking) Kie AI API (Seedream + Veo 3) Fal.ai API (NanoBanana + video merging) OpenAI (for script and prompt generation) Blotato API (for social publishing) 2. Prepare a Google Sheet with brand info and settings (product name, category, features, offer, website URL). 3. Deploy the workflow and connect your Telegram bot to start sending ad ideas (photo + caption). 4. Run the workflow — it will automatically generate images, create videos, and publish to your chosen channels. How to customize this workflow to your needs Brand customization: Adjust the Google Sheet values to reflect your brand’s offers and product features. Platforms: Enable/disable specific Blotato nodes depending on which platforms you want to publish to. Video style: Edit the AI agent’s system prompt to control tone, format, and transitions (cinematic, playful, modern, etc.). Notifications: Adapt Telegram nodes to send updates to different team members or channels. Storage: Change the Google Drive folder IDs to store generated videos and images in your preferred location. This workflow lets you go from idea → images → cinematic ad video → auto-published content in minutes, fully automated. --- Watch This Tutorial: Step by Step --- Documentation: Notion Guide --- Need help customizing? Contact me for consulting and support : Linkedin / Youtube
by Dr. FirasWorking with Large Documents In Your VLM OCR Workflow Document workflows are popular ways to use AI but what happens when your document is too large for your app or your AI to handle? Whether its context window or application memory that's grinding to a halt, Subworkflow.ai is one approach to keep you going. > Subworkflow.ai is a third party API service to help AI developers work with documents too large for context windows and runtime memory. Prequisites 1. You'll need a Subworkflow.ai API key to use the Subworkflow.ai service. 2. Add the API key as a header auth credential. More details in the official docs https://docs.subworkflow.ai/category/api-reference How it Works 1. Import your document into your n8n workflow 2. Upload it to the Subworkflow.ai service via the Extract API using the HTTP node. This endpoint takes files up to 100mb. 3. Once uploaded, this will trigger an Extract job on the service's side and the response is a "job" record to track progress. 4. Poll Subworkflow.ai's Jobs endpoint and keep polling until the job is finished. You can use the "IF" node looping back unto itself to achieve this in n8n. 5. Once the job is done, the Dataset of the uploaded document is ready for retrieval. Use the Datasets and DatasetItems API to retrieve whatever you need to complete your AI task. 6. In this example, all pages are retrieved and run through a multimodal LLM to parse into markdown. A well-known process when parsing data tables or graphics are required. How to use Integrate Subworkflow's Extract API seemlessly into your existing document workflows to support larger documents from 100mb+ to up to 5000 pages. Customising the workflow Sometimes you don't want the entire document back especially if the document is quite large (think 500+ pages!), instead, use query parameters on the DatasetItems API to pick individual pages or a range of pages to reduce the load. Need Help? Official API documentation: https://docs.subworkflow.ai/category/api-reference Join the discord: https://discord.gg/RCHeCPJnYw
by JimleukThis workflow pulls news articles from NewsAPI, Mediastack, and CurrentsAPI on a scheduled basis. Each provider’s results are normalized into a consistent schema, then written into your database (NocoDB by default). Use case: automated aggregation of categorized news for content pipelines, research agents, or editorial queues. What You Must Update Before Running 1. API Keys Replace all placeholder keys: call newsapi.org - Top Headlines → update API_KEY in URL call newsapi.org - categories → update API_KEY call mediastack → update "ACCESS_KEY" in JSON call currentsapi → update "API_KEY" param 2. Database Connection Workflow uses NocoDB to store results. You must: Update the NocoDB API Token credential to your own Ensure your table includes the fields used in the create operations (source_category, title, summary, author, sources, content, images, publisher_date, etc.) If you prefer Google Sheets, Airtable, or another DB: Replace each NocoDB node with your equivalent “create row” operation The Set nodes already provide all normalized fields you need 3. Scheduling All schedulers are disabled by default. Enable the following so the workflow runs automatically: NewsAPI – Top Headlines NewsAPI – Categories Mediastack CurrentsAPI You may change the run times, but all four must be scheduled for the workflow to function as designed. What You Can Configure 1. Categories Defined in: newsapi.org categories mediastack categories Edit these arrays to pull only the categories you care about or to match your API plan limits. 2. Article Limits Adjust article_limit in: newsapi.org categories mediastack categories currentsapi config
by Joel GambleHow it works Customer submits your Typeform → instant personalised welcome SMS fires via Twilio Submission logged to Google Sheets with name, phone, timestamp, and nudge tracking Twilio listens 24/7 for replies → marks customer as responded, stops all future nudges Scheduler runs every 6 hours → finds non-responders and sends up to 2 follow-up nudges System stops contacting anyone who replies or hits the 2-nudge limit The three branches | Branch | Trigger | What it does | |--------|---------|--------------| | New Submission | Typeform form submit | Welcome SMS + log to Sheets | | Reply Handler | Incoming Twilio SMS | Mark replied, stop nudges | | Nudge Engine | Schedule every 6hrs | Nudge 1 at 24h, Nudge 2 at 48h | Why this matters | Metric | Manual | This workflow | |--------|--------|---------------| | Speed to lead | Hours or days | Under 10 seconds | | Follow-up consistency | Whoever remembers | 100% automated | | Lead drop-off | High — people go cold fast | Nudges catch non-responders | | Staff time per lead | 5–15 min | Zero | | Revenue at risk | Every ignored inquiry | Recovered automatically | Studies show leads contacted within 5 minutes are 9x more likely to convert. This workflow makes that the default — not the exception. What you need | Tool | Cost | Why | |------|------|-----| | Typeform | Free tier works | Intake/booking form | | Twilio | ~$1/mo + $0.0075/SMS | Send and receive SMS | | Google Sheets | Free | Track submissions and nudge state | A2P 10DLC notice: Twilio requires business registration for production SMS in the US. Allow 2-4 weeks. Your signup form needs opt-in language, terms, and a privacy policy. Set up steps Takes about 15 minutes Create a Google Sheet with columns: customerName · customerPhone · submittedAt · repliedAt · nudgeCount · lastNudgeAt Branch 1 — connect Typeform, select your form, connect Twilio + Google Sheets Branch 2 — connect Twilio trigger for inbound SMS, connect Google Sheets to mark replied Branch 3 — connect Google Sheets to read non-responders, connect Twilio to send nudges Verify Typeform field names match the Extract node exactly (case-sensitive) Submit a test entry with your own phone, reply to it, confirm Sheets updates correctly Toggle workflow Active Learn more at SMB Excel
by David Schreiber