Workflow Templates

Who’s it for This template is perfect for TikTok creators, content marketers, and social media teams who want to turn viral comments into engaging short-form videos without manually scripting, recording, or editing. If you want to keep up with trends and consistently publish high-quality avatar videos, this workflow automates the entire process from comment selection to enhanced final video. What it does The workflow takes TikTok video URLs and their top comments from a Data Table, extracts the transcript using Dumpling AI, and uses GPT-4 to write a natural and engaging TikTok script inspired by the comment. It then generates a full AI avatar video through Captions.ai, enhances it with subtitles and B-roll using Submagic, and finally saves all video details into Airtable for tracking. Here’s what happens step by step: Pulls TikTok videos and their top comments from a Data Table Sends video URLs to Dumpling AI to retrieve transcripts Feeds both transcript and comment into GPT-4 to generate a conversational TikTok script Cleans and formats the script using JavaScript Sends the script to Captions.ai to produce an AI avatar video Checks video status and retries if needed Enhances the final video with Submagic for captions and effects Receives the enhanced video via webhook and logs details into Airtable How it works Schedule Trigger: Runs automatically at set intervals to start the workflow Data Table: Retrieves TikTok video URLs and associated comments Dumpling AI: Extracts transcripts from the video URLs GPT-4: Generates a compelling TikTok script based on the comment JavaScript Node: Cleans up script formatting for a smooth avatar generation Captions.ai: Creates an AI avatar video from the cleaned script Wait & Check: Monitors video creation status and retries if necessary Submagic: Enhances the video with captions, zooms, and B-roll effects Webhook & Airtable: Receives final video data and saves URL and ID for future use Requirements ✅ Dumpling AI API key stored as HTTP header credentials ✅ OpenAI GPT-4 credentials ✅ Captions.ai API credentials ✅ Submagic API credentials ✅ Airtable base with fields for Video URL and Caption Video ID ✅ A properly structured Data Table containing TikTok Keywords or video URLs How to customize Adjust the GPT-4 system prompt to shape the tone, style, or format of the TikTok script Change the avatar or creator settings in Captions.ai to match your brand personality Modify Submagic settings to control subtitle styling or B-roll effects Integrate approval steps before final video generation if needed Extend the workflow to auto-publish videos to TikTok or store them in cloud drives > This workflow lets you transform TikTok comments into engaging AI avatar videos with captions and edits, completely on autopilot. It’s a powerful way to scale content output and stay ahead of trends without manual scripting or filming.

Stop manually searching for songs and let an AI DJ do the work for you. This template provides a complete, end-to-end system that transforms any text prompt into a ready-to-play Spotify playlist. It combines the creative understanding of a powerful AI Agent with the real-time web knowledge of Linkup to curate perfect, up-to-the-minute playlists for any occasion. The experience is seamless: simply describe the vibe you're looking for in a web form, and the workflow will automatically create the playlist in your Spotify account and redirect you straight to it. Whether you need "upbeat funk for a sunny afternoon" or "moody electronic tracks for late-night coding," your personal AI DJ is ready to deliver. Who is this for? Music lovers:** Create hyper-specific playlists for any mood, activity, or niche genre without the hassle of manual searching. DJs & event planners:** Quickly generate themed playlists for parties, weddings, or corporate events based on a simple brief. Content creators:** Easily create companion playlists for your podcasts, videos, or articles to share with your audience. n8n developers:** A powerful example of how to build an AI agent that uses an external web-search tool to accomplish a creative task. What problem does this solve? Creates up-to-date playlists:** A standard AI doesn't know about music released yesterday. By using Linkup's live web search, this workflow can find and include the very latest tracks. Automates the entire creation process:** It handles everything from understanding a vague prompt (like "songs that feel like a summer road trip") to creating a fully populated Spotify playlist. Saves time and effort:** It completely eliminates the tedious task of searching for individual tracks, checking for relevance, and manually adding them to a playlist one by one. Provides a seamless user experience:** The workflow begins with a simple form and ends by automatically opening the finished playlist in your browser. There are no intermediate steps for you to manage. How it works Submit your playlist idea: You describe the playlist you want and the desired number of tracks in a simple, Spotify-themed web form. The AI DJ plans the search: An AI Agent (acting as your personal DJ) analyzes your request. It then intelligently formulates a specific query to find the best music. Web research with Linkup: The agent uses its Linkup web-search tool to find artists and tracks from across the web that perfectly match your request, returning a list of high-quality suggestions. The AI DJ curates the list: The agent reviews the search results and finalizes the tracklist and a creative name for your playlist. Build the playlist in Spotify: The workflow takes the agent's final list, creates a new public playlist in your Spotify account, then searches for each individual track to get its ID and adds them all. Instant redirection: As soon as the last track is added, the workflow automatically redirects your browser to the newly created playlist on Spotify, ready to be played. Setup Connect your accounts: You will need to add your credentials for: Spotify: In the Spotify nodes. Linkup: In the Web query to find tracks (HTTP Request Tool) node. Linkup's free plan is very generous! Your AI provider (e.g., OpenAI): In the OpenAI Chat Model node. Activate the workflow: Toggle the workflow to "Active." Use the form: Open the URL from the On form submission trigger and start creating playlists! Taking it further Change the trigger:* Instead of a form, trigger the playlist creation from a *Telegram* message, a *Discord** bot command, or even a webhook from another application. Create collaborative playlists:** Set up a workflow where multiple people can submit song ideas. You could then have a final AI step consolidate all the requests into a single, cohesive prompt to generate the ultimate group playlist. Optimize for speed:* The *Web query to find tracks** node is set to deep search mode for the highest quality results. You can change this to standard mode for faster and cheaper (but potentially less thorough) playlist creation.

How it works This workflow automatically uploads YouTube Shorts from a Google Drive folder. It picks one video at each run, generates a YouTube-optimized title, description, and hashtags using an AI model, uploads the video through YouTube’s resumable upload API, and finally moves the processed video to a “Posted” folder. Key steps Run on a schedule (daily/hourly/custom CRON) Fetch one video from a selected Google Drive folder Generate title + description + hashtags using an LLM Prepare YouTube metadata Upload the video via resumable upload Move the file to a “posted” folder to avoid duplicates Setup instructions Connect your Google Drive credentials Connect your YouTube OAuth2 credentials Update the Drive folder IDs (input + posted folders) Edit the “Set variables” node to change store name, country, coupon code, and tone Review the prompt in the AI node if you want to customize content style All technical details are documented inside the sticky notes within the workflow.

🧠 AI Brainstorm Generator - Break Through Creative Blocks Instantly Transform any problem into innovative solutions using AI-powered brainstorming that combines mathematical randomness with intelligent synthesis. What This Workflow Does This workflow generates creative, actionable solutions to any problem by combining: Mersenne Twister algorithm** for high-entropy random seed generation AI-driven random word generation** to create unexpected semantic triggers Dual AI agents** that brainstorm and refine ideas into polished solutions Simply input your challenge via the chat interface, and within 2 minutes receive a professionally refined solution that combines the best elements from 5+ innovative ideas. Key Features ✨ Consistent Creativity - Works regardless of your mental state or time of day 🎲 True Randomness - MT19937 algorithm ensures no pattern repetition 🤖 Multi-Model Support - Works with OpenAI GPT-4 or Google Gemini ⚡ Fast Results - Complete solutions in under 2 minutes 🔄 Self-Cleaning - Redis data expires automatically after use Use Cases Product ideation and feature development Marketing campaign concepts Problem-solving for technical challenges Business strategy innovation Creative writing prompts Workshop facilitation Requirements Redis database (local or cloud) OpenAI API key (GPT-4) OR Google Gemini API key n8n instance (self-hosted or cloud) How It Works User inputs problem via chat trigger Mersenne Twister generates high-entropy random numbers AI generates 36+ random words as creative triggers Brainstorming Agent creates 5 innovative solutions Critic Agent synthesizes the best elements into one refined solution Perfect for teams facing innovation challenges, solo entrepreneurs seeking fresh perspectives, or anyone who needs to break through creative blocks reliably. Setup Time: ~10 minutes Difficulty: Intermediate Support: Full documentation included via sticky notes

🧾 What this workflow does This automation transforms a short text idea into a cinematic video by chaining together three powerful AI services: GPT-4.1 for scene creation, Dumpling AI’s FLUX.1 Pro model for visual generation, and KIE API (Veo 3) for cinematic video creation. The system fully automates the journey from raw concept to video output, returning the final video URL. 👤 Who is this for Content creators who want to test visual ideas quickly Agencies creating moodboards, ad scenes, or pitch visuals Solo marketers or founders without video editing skills AI automation builders creating content tools ⚙️ How to set up ✅ Requirements OpenAI GPT-4.1 API key** Dumpling AI (FLUX.1 Pro model)** API token KIE API* account with access to the *Veo 3 endpoint** Optional: Tool to store or share the final video link (e.g., Google Sheets, Slack) 🔧 Setup steps Start with a text idea Example: “A lion running through misty mountains at sunrise.” GPT-4.1 Node: Expands the idea into two parts: Cinematic Prompt: Describes the atmosphere, emotion, and camera movement. Image Prompt: A vivid single-frame visual to generate the base image. Dumpling AI Node (FLUX.1 Pro): Takes the image prompt and returns a cinematic-style image. You can customize dimensions, steps, seed, and guidance level. KIE API Node (Veo 3): Sends both the cinematic prompt and image to the Veo 3 model. The model returns a video URL (e.g., 3–6 seconds cinematic footage). Final Output: The video URL is returned by the HTTP node. You can connect this to Airtable, Slack, Telegram, or Google Sheets to log the result or share with your team. 🧠 How it works You input a text idea GPT-4.1 turns it into both a detailed cinematic prompt and a base image prompt Dumpling AI generates the image KIE API’s Veo 3 turns it into a cinematic video The final video URL is returned for download or embedding 💡 Customization Ideas Add a Telegram bot to trigger this workflow with an idea via message Route video links to a Notion database or content calendar Add a loop with rating logic to regenerate low-rated videos Use Google Drive to auto-save videos in brand folders Automate weekly video ideation for social media using a prompt list This workflow helps you turn raw imagination into cinematic motion using AI. From social content to storyboarding, you can generate compelling visuals in minutes — no design or video background needed.

Automated Crypto Forecast Pipeline using Decodo and Gmail Sign Up for Decodo HERE for discount This template scrapes CoinGecko pages for selected coins, converts metrics into clean JSON, stores them in an n8n Data Table, generates 24-hour direction forecasts with Gemini, and emails a concise report. Who’s it for? Crypto watchers who want automated snapshots, forecasts, and a daily email—without managing a full data stack. How it works 30-min schedule loops coins, scrapes CoinGecko (Decodo), parses metrics, and upserts to Data Table. 18:00 schedule loads last 48h data. Gemini estimates next-24h direction windows. Email is rendered (HTML + plain text) and sent. How to set up Add Decodo, Gmail, and Gemini credentials. Open Configure Coins to edit tickers. Set Data Table ID. Replace recipient email. (Self-host only) Community node Decodo required. @decodo/n8n-nodes-decodo (community)

Process multiple invoices automatically using Mistral's dedicated OCR model—at approximately $0.002 per page. Upload batches of PDF, PNG, or JPG invoices through a simple form, extract structured financial data with AI, validate results with confidence scoring, and save everything to Google Sheets. What this workflow does Accepts multiple invoice uploads via n8n Form Trigger Processes files in batch with rate limiting Converts each file to base64 and sends to Mistral OCR API Extracts 9 standard fields using GPT-4o-mini Information Extractor Validates data and assigns confidence scores (high/medium/low) Saves all results to Google Sheets with status tracking Fields extracted Invoice Number, Date, Vendor Name, Tax ID, Subtotal, Tax Rate, Tax Amount, Total Amount, Currency Use cases Accountants processing client invoices in bulk Small businesses digitizing paper receipts Bookkeepers automating repetitive data entry Finance teams building searchable invoice databases Setup requirements Mistral API Key (console.mistral.ai) — HTTP Header Auth credential OpenAI API Key (platform.openai.com) Google Sheets OAuth connection Google Sheet with 15 columns (template in workflow notes)

Pull a Dun & Bradstreet Business Information Report (PDF) by DUNS, convert the response into a binary PDF file, extract readable text, and use OpenAI to return a clean, flat JSON with only the key fields you care about (e.g., report date, Paydex, viability score, credit limit). Includes Sticky Notes for quick setup help and guidance. ✅ What this template does Requests a D&B report* (PDF) for a specific *DUNS** via HTTP Converts* the API response into a *binary PDF file** Extracts** the text from the PDF for analysis Uses OpenAI with a Structured Output Parser to return a flat JSON Designed to be extended to Sheets, databases, or CRMs 🧩 How it works (node-by-node) Manual Trigger — Runs the workflow on demand ("When clicking 'Execute workflow'"). D&B Report (HTTP Request) — Calls the D&B Reports API for a Business Information Report (PDF). Convert to PDF File (Convert to File) — Turns the D&B response payload into a binary PDF. Extract Binary (Extract from File) — Extracts text content from the PDF. OpenAI Chat Model — Provides the language model context for the analyzer. Analyze PDF (AI Agent) — Reads the extracted text and applies strict rules for a flat JSON output. Structured Output (AI Structured Output Parser) — Enforces a schema and validates/auto-fixes the JSON shape. (Optional) Get Bearer Token (HTTP Request) — Template guidance for OAuth token retrieval (shown as disabled; included for reference if you prefer Bearer flows). 🛠️ Setup instructions (from the JSON) 1) D&B Report (HTTP Request) Auth:* Header Auth (use an n8n *HTTP Header Auth** credential) URL:** https://plus.dnb.com/v1/reports/duns/804735132?productId=birstd&inLanguage=en-US&reportFormat=PDF&orderReason=6332&tradeUp=hq&customerReference=customer%20reference%20text Headers:** Accept: application/json Credential Example:** D&B (HTTP Header Auth) > Put your Authorization: Bearer <token> header inside this credential, not directly in the node. 2) Convert to PDF File (Convert to File) Operation:** toBinary Source Property:** contents[0].contentObject > This takes the PDF content from the D&B API response and converts it to a binary file for downstream nodes. 3) Extract Binary (Extract from File) Operation:** pdf > Produces a text field with the extracted PDF content, ready for AI analysis. 4) OpenAI Model(s) OpenAI Chat Model** Model:** gpt-4o (as configured in the JSON) Credential:* Your stored *OpenAI API* credential (do *not** hardcode keys) Wiring:** Connect OpenAI Chat Model as ai_languageModel to Analyze PDF Connect another OpenAI Chat Model (also gpt-4o) as ai_languageModel to Structured Output 5) Analyze PDF (AI Agent) Prompt Type:** define Text:** ={{ $json.text }} System Message (rules):** You are a precision extractor. Read the provided business report PDF and return only a single flat JSON object with the fields below. No arrays/lists. No prose. If a value is missing, output null. Dates: YYYY-MM-DD. Numbers: plain numerics (no commas or $). Prefer most recent or highest-level overall values if multiple are shown. Never include arrays, nested structures, or text outside of the JSON object. 6) Structured Output (AI Structured Output Parser) JSON Schema Example:** { "report_date": "", "company_name": "", "duns": "", "dnb_rating_overall": "", "composite_credit_appraisal": "", "viability_score": "", "portfolio_comparison_score": "", "paydex_3mo": "", "paydex_24mo": "", "credit_limit_conservative": "" } Auto Fix:** enabled Wiring:* Connect as ai_outputParser to *Analyze PDF** 7) (Optional) Get Bearer Token (HTTP Request) — Disabled example If you prefer fetching tokens dynamically: Auth:** Basic Auth (D&B username/password) Method:** POST URL:** https://plus.dnb.com/v3/token Body Parameters:** grant_type = client_credentials Headers:** Accept: application/json Downstream usage:** Set header Authorization: Bearer {{$json["access_token"]}} in subsequent calls. > In this template, the D&B Report node uses Header Auth credential instead. Use one strategy consistently (credentials are recommended for security). 🧠 Output schema (flat JSON) The analyzer + parser return a single flat object like: { "report_date": "2024-12-31", "company_name": "Example Corp", "duns": "123456789", "dnb_rating_overall": "5A2", "composite_credit_appraisal": "Fair", "viability_score": "3", "portfolio_comparison_score": "2", "paydex_3mo": "80", "paydex_24mo": "78", "credit_limit_conservative": "25000" } 🧪 Test flow Click Execute workflow (Manual Trigger). Confirm D&B Report returns the PDF response. Check Convert to PDF File for a binary file. Verify Extract from File produces a text field. Inspect Analyze PDF → Structured Output for valid JSON. 🔐 Security notes Do not hardcode tokens in nodes; use Credentials (HTTP Header Auth or Basic Auth). Restrict who can execute the workflow if it's accessible from outside your network. Avoid storing sensitive payloads in logs; mask tokens/headers. 🧩 Customize Map the structured JSON to Google Sheets, Postgres/BigQuery, or a CRM. Extend the schema with additional fields (e.g., number of employees, HQ address) — keep it flat. Add validation (Set/IF nodes) to ensure required fields exist before writing downstream. 🩹 Troubleshooting Missing PDF text?* Ensure *Convert to File** source property is contents[0].contentObject. Unauthorized from D&B?** Refresh/verify token; confirm Header Auth credential contains Authorization: Bearer <token>. Parser errors?** Keep the agent output short and flat; the Structured Output node will auto-fix minor issues. Different DUNS/product?** Update the D&B Report URL query params (duns, productId, etc.). 🗒️ Sticky Notes (included) Overview:** "Fetch D&B Company Report (PDF) → Convert → Extract → Summarize to Structured JSON (n8n)" Setup snippets for Data Blocks (optional) and Auth flow 📬 Contact Need help customizing this (e.g., routing the PDF to Drive, mapping JSON to your CRM, or expanding the schema)? 📧 robert@ynteractive.com 🔗 https://www.linkedin.com/in/robert-breen-29429625/ 🌐 https://ynteractive.com

🚀 AI-Powered Email to Purchase Order Workflow Automatically scan your inbox for new purchase order requests, extract order details using Gemini AI, and log them into Google Sheets — all without manual effort. ✨ Core Capabilities ⏱ Runs every minute to check unread emails 📧 Filters emails by subject 🤖 Uses Gemini AI to summarize email content & extract structured order details 📅 Formats dates into ISO calendar weeks 📊 Adds product data from Google Sheets to complete order info ✅ Appends final purchase order records into a Google Sheet (without replacing previous ones) 🛠 Setup Essentials 📩 Gmail account for fetching unread emails 🔑 Google Gemini (PaLM) API credentials 📒 Google Sheet with predefined purchase order headers 📖 Activation Guide ⚙️ Configure Gmail & Google Sheets credentials in n8n 🎯 Adjust the subject filter to match your email rules 🔌 Connect Gemini AI with your API credentials 📑 Create a Google Sheet with the required headers ▶️ Activate the workflow and let it run in the background 🎨 Customizing the Workflow 🔍 Email Filters → Change keywords in the filter node to match your purchase order email subjects 🏷 Order Fields → Modify Set and Append to Google Sheet nodes if your schema differs ✍️ AI Instructions → Adjust the AI Agent’s prompt to fit your company’s email style or product details ⏲ Frequency → Update the Cron node if you want to scan emails less often 📂 Target Google Sheet → Point to a different sheet or tab depending on your department or customer

What it does This template automatically generates a professional, structured title for newly-ingested Paperless-ngx documents using AI (OpenAI GPT), then removes a processing tag to mark the document as handled. How it works A webhook fires when a document needs titling (e.g., from a Paperless post-consumption script) The document URL is validated, then the OCR text is fetched from the Paperless API All PII is scrubbed from the text using n8n's Guardrails node before sending to AI GPT generates a title using the format: [YYYY-MM-DD] - [Document Type] - [Subject] The specified processing tag is looked up and removed, then the document is updated Requirements An AI provider account, such as OpenAI, Anthropic, Gemini. As configured the template uses OpenAI, but any model should work. A running Paperless-ngx instance that has network accessibility to your n8n server How to use Needs to be set up in conjunction with a running Paperless-ngx instance. See Paperless-ngx instructions here Customization Edit the system message in the AI Agent node (Generate Document Name) to change the document naming convention and other guidelines Change the workflows on your Paperless-ngx instance to suit different needs.

Analyze crypto markets with interactive graphs using CoinGecko and C1 by Thesys This n8n template can answer questions about real-time prices, market moves, trending coins, and token details with interactive UI in real time (cards, charts, buttons) instead of plain text using C1 by Thesys. Data is fetched through the CoinGecko Free MCP tool. Check out a working demo of this template here. What this workflow does A user sends a message in the n8n Chat UI (public chat trigger). The AI Agent interprets the request. The agent calls CoinGecko Free MCP to fetch market data (prices, coins, trending, etc.). The model responds through C1 by Thesys with a streaming, UI answer. Example prompts you can try right away Copy/paste any of these into the chat: “What’s the current price of Bitcoin and Ethereum?” “Give me today’s market summary: total market cap, BTC dominance, top gainers/losers.” “Compare ETH vs SOL over 30 days with a chart.” > Note: This template is for information and visualization, not financial advice. How it works User sends a prompt C1 model based on prompt will use CoinGecko MCP to fetch live data C1 Model generates a UI Schema Response Schema is rendered as UI using Thesys GenUI SDK on the frontend Setup Make sure you have the following: 1️⃣ Thesys API Key You’ll need an API key to authenticate and use Thesys services. 👉 Get your key here What is C1 by Thesys? C1 by Thesys is an API middleware that augments LLMs to respond with interactive UI (charts, buttons, forms) in real time instead of text. Facing setup issues? If you get stuck or have questions: 💬 Join the Thesys Community 📧 Email support: support@thesys.dev

Overview This workflow processes passport images submitted through a form, extracts structured data using OpenAI OCR, and generates QR codes with the extracted information. Results are displayed on the form completion page and sent via email. The workflow reduces manual data entry and speeds up document processing workflows where passport information needs to be captured consistently. It works best with clear, front-facing passport images. How it works User submits a form with one or more passport images Files are split and processed individually Each file is validated as an image and resized for OCR accuracy Image is converted to base64 and sent to OpenAI for data extraction Extracted fields are cleaned, standardized, and validated QR payload is generated from standardized data and converted to QR code image URL Results are aggregated into HTML summary Summary is displayed on form completion page and sent via email Setup steps Add OpenAI API credentials to the OCR request node Connect your Gmail account for email delivery Replace YOUR_EMAIL placeholder with recipient address Test with 1–3 clear passport images Customization Modify OCR prompt to support other document types Adjust QR payload format to match your system requirements