Workflow Templates

🧾 Image Extraction Pipeline (Google Drive + VLM Run + n8n) ⚙️ What This Workflow Does This workflow automates the process of extracting images from uploaded documents in Google Drive using the VLM Run Execute Agent, then downloads and saves those extracted images into a designated Drive folder. 🧩 Requirements Google Drive OAuth2 credentials** VLM Run API credentials** with Execute Agent access A reachable n8n Webhook URL (e.g., /image-extract-via-agent) ⚡Quick Setup Configure Google Drive OAuth2 and create upload folder and folder for saving extracted images. Install the verified VLM Run node by searching for VLM Run in the node list, then click Install. Once installed, you can start using it in your workflows. Add VLM Run API credentials for document parsing. ⚙️ How It Works Monitor Uploads – The workflow watches a specific Google Drive folder for new file uploads (e.g., receipts, reports, or PDFs). Download File – When a file is created, it’s automatically downloaded in binary form. Extract Images (VLM Run) – The file is sent to the VLM Run Execute Agent, which analyzes the document and extracts image URLs via its callback. Receive Image Links (Webhook) – The workflow’s Webhook node listens for the agent’s response containing extracted image URLs. Split & Download – The Split Out node processes each extracted link, and the HTTP Request node downloads each image. Save Image – Finally, each image is uploaded to your chosen Google Drive folder for storage or further processing. 💡Why Use This Workflow Manual image extraction from PDFs and scanned files is repetitive and error-prone. This pipeline automates it using VLM Run, a vision-language AI service that: Understands document layout and structure Handles multi-page and mixed-content files Extracts accurate image data with minimal setup. For example- the output contains URLs to extracted images { "image_urls": [ "https://vlm.run/api/files/img1.jpg", "https://vlm.run/api/files/img2.jpg" ] } Works with both images and PDFs 🧠 Perfect For Extracting photos or receipts from multi-page PDFs Archiving embedded images from reports or invoices Preparing image datasets for labeling or ML model training 🛠️ How to Customize You can extend this workflow by: Adding naming conventions or folder structures based on upload type Integrating Slack/Email notifications when extraction completes Including metadata logging (file name, timestamp, source) into Google Sheets or a database Chaining with classification or OCR workflows using VLM Run’s other agents ⚠️ Community Node Disclaimer This workflow uses community nodes (VLM Run) that may need additional permissions and custom setup.

This n8n workflow automates the end-to-end proof-of-delivery process for logistics operations. It ingests POD data via webhook—including driver signatures, delivery photos, and GPS coordinates—performs AI-driven verification for package integrity and authenticity, updates ERP systems with delivery status, triggers automated invoicing for verified cases, and handles disputes by creating evidence-backed tickets and alerting teams. Designed for seamless integration, it minimizes errors in billing and reconciliation while accelerating resolution for mismatches. Benefits Reduced Manual Effort:** Automates verification and status updates, cutting processing time from hours to minutes. Enhanced Accuracy:** AI analysis detects damages, location discrepancies, and signature fraud with high confidence scores, preventing billing disputes. Faster Revenue Cycle:** Instant invoicing for verified deliveries improves cash flow and reduces DSO (Days Sales Outstanding). Proactive Dispute Management:** Generates high-priority tickets with linked evidence, enabling quicker resolutions and lower escalation costs. Audit-Ready Traceability:** Logs all decisions, AI outputs, and actions for compliance with logistics standards like ISO 9001. Scalability:** Handles high-volume deliveries without proportional staff increases, supporting growth in e-commerce fulfillment. Useful for Which Industry Logistics & Supply Chain:** Ideal for 3PL providers, freight forwarders, and courier services managing last-mile deliveries. E-Commerce & Retail:** Supports platforms like Amazon or Shopify sellers verifying customer receipts and automating returns. Manufacturing & Distribution:** Streamlines B2B shipments with ERP integrations for just-in-time inventory. Pharmaceuticals & Healthcare:** Ensures tamper-evident deliveries with photo verification for cold-chain compliance. Food & Beverage:** Tracks perishable goods with damage detection to maintain quality assurance. Workflow Process Webhook Intake:** Receives POD submission (driver ID, signature image, delivery photo, recipient, GPS) via POST/GET. Input Validation:** Checks for required fields; branches to error if incomplete. Parallel AI Verification:** AI Vision (OpenAI GPT-4): Analyzes photo for package condition, location match, and damage. Signature Validation: AI checks legitimacy, handwritten authenticity, and completeness. Merge & Decide:** Consolidates results with confidence scoring; routes to verified (true) or dispute (false). Verified Path:** Update ERP: POSTs status, timestamps, and coordinates to delivery system. Trigger Invoicing: Generates billable invoice with POD reference via billing API. Success Response: Returns confirmation to caller. Dispute Path:** Create Ticket: POSTs high-priority support ticket with evidence (images, scores). Alert Team: Notifies dispute team via email/Slack with issue summary and ticket link. Dispute Response: Returns status and next steps to caller. Error Handling:** Returns detailed feedback for invalid inputs. Setup Instructions Import Workflow: Paste JSON into n8n Workflows → Import from Clipboard. Configure Webhook: Set URL for POD submissions (e.g., from mobile apps); test with sample POST data. AI Setup: Add OpenAI API key to vision/signature nodes; specify GPT-4 model. Integrate Systems: Update ERP/billing URLs and auth in update/trigger nodes (e.g., https://your-erp.com/api). Dispute Config: Link support API (e.g., Zendesk) and notification service (e.g., Slack webhook). Threshold Tuning: Adjust confidence scores in decision node (e.g., >85% for auto-approve). Test Run: Execute manually with valid/invalid POD samples; verify ERP updates and ticket creation. Prerequisites n8n instance (v1.50+) with webhook and HTTP request nodes enabled. OpenAI API access for GPT-4 vision (image analysis credits required). ERP/billing APIs with POST endpoints and authentication (e.g., OAuth tokens). Support ticketing system (e.g., Zendesk, Jira) for dispute creation. Secure image storage (e.g., AWS S3) for POD uploads. Basic API testing tools (e.g., Postman) for endpoint validation. Modification Options Add OCR for recipient name extraction from photos in validation step. Integrate geofencing APIs for automated location alerts in AI vision. Support multi-signature PODs for group deliveries by expanding parallel branches. Add partial invoicing logic for mixed verified/disputed items. Incorporate blockchain for immutable POD records in high-value shipments. Extend alerts to SMS via Twilio for on-the-road driver notifications. Build analytics export to Google Sheets for delivery success rates.

This workflow serves a Question and Answer chat experience to an end user. It uses an AI Agent with a tool to fetch Question and Answer pairs stored in a Data Table (to serve the user answers grounded on knowledge base). This template is part of the official n8n quick start tutorial (2026). Watch it here.

This workflow connects JotForm submissions to Vapi AI, triggering a personalized outbound call via an AI voice assistant immediately after a user submits your form. Requirements JotForm A JotForm account JotForm API credentials** enabled in n8n A published JotForm form with a phone number field Vapi A Vapi account with credit A connected phone number for making calls An assistant created and ready for outbound calls Your Vapi API key Workflow Steps 1. JotForm Trigger Starts the workflow when a new form submission is received. 2. Information Extractor Formats the phone number** with a +, country code, and full number (e.g., +391234567890) for compatibility with Vapi. 4. Set Fields for Vapi Configure these fields: phone_number_id: ID of the Vapi number used for the call assistant_id: ID of the Vapi assistant api_key: Your Vapi API key 5. Start Outbound Vapi Call Sends a POST request to https://api.vapi.ai/call with: The formatted phone number All required Vapi fields Any additional info mapped from the form, for personalization Customization Add more form fields:** Include extra data (such as name, appointment time) and add to the Vapi payload. Conditional logic:** Use n8n filter nodes to control if/when calls are made. Dynamic assistant selection:** Route submissions to different assistants or numbers based on user responses. Notes Ensure phone numbers are formatted correctly in the extractor node to prevent call errors. Any field from your form can be passed in the API payload and used in the assistant's script. Need Help? For additional resources or help, visit 1 Node.

How it works: • Receives WhatsApp messages via webhook from Whapi.Cloud • Routes commands: AI chat (/ai), numeric commands (1-9), or help menu • Sends responses: text, images, documents, videos, contacts, product info • Manages WhatsApp groups: create, send messages, list groups • Integrates with OpenAI ChatGPT for AI-powered conversations Set up steps: Setup takes ~5-10 minutes. Import the workflow, configure Whapi.Cloud credentials (token from dashboard), set up webhook URL in Whapi.Cloud settings, and optionally add OpenAI API key for AI chat. Activate the workflow and start receiving messages. Key features: • No Meta restrictions or approval • Visual no-code workflow - easy to customize • Production-ready with error handling • Well-documented with sticky notes inside the workflow Perfect for businesses, developers, and automation enthusiasts who want WhatsApp automation without coding.

This n8n workflow is an end-to-end AI-powered video generation pipeline that takes a dataset of sci-fi book, generates reviews with GenAI, dynamically injects assets into After Effects via Nexrender, and automatically produces fully rendered videos — ready for publishing. It demonstrates: • AI content generation inside render jobs • Dynamic After Effects templating • Adaptive composition logic • Fully automated creative production at scale Built as a demo for the Nexrender n8n integration, it shows how to turn raw ideas into finished video content with zero manual editing. Requirements: Nexrender Trial - https://www.nexrender.com/get-trial, N8N - https://n8n.io/, Fal.ai - https://fal.ai/, After Effects Project file - https://drive.google.com/file/d/1XmDcBMM34IFQ2Cv28pzumDmk2OwW2_9q/view?usp=share_link, Nexrender Integration - https://n8n.io/integrations/nexrender/ How It Works: • Imports a sci-fi books dataset into n8n • Uses GenAI (ChatGPT) to generate book reviews and narrative content • Cleans and structures the AI output for video rendering • Dynamically injects text and assets into an After Effects template via n8n Nexrender Integration • Submits the job to Nexrender for rendering • Generates AI-powered visuals inside the render job • Automatically adjusts composition length based on each review • Outputs a fully produced video — no manual editing required

This workflow automatically notifies the team in a Slack channel when code in a GitHub repository gets a new release. Prerequisites A GitHub account and credentials A Slack account and credentials Nodes GitHub Trigger node triggers the workflow when a release event takes place in the specified repository. Slack node posts a message in a specified channel with the text "New release is available in {repository name}", along with further details and a link to the release.

This workflow allows you to register your audience to an event on Demio via a Typeform submission. Typeform Trigger node: This node will trigger the workflow when a form response is submitted. Based on your use-case, you may use a different platform. Replace the Typeform Trigger node with a node of that platform. Demio node: This node registers a user for an event. It gets the details of the users from the Typeform response.

Who is this for? Content creators who want a consistent on-screen avatar without filming themselves Marketing teams producing personalized video messages at scale Educators building video lessons with a virtual presenter Anyone who wants to turn text into a talking avatar video using a cloned voice What problem does this solve? Creating a talking-head video normally requires a camera, lighting, and a person on screen. Voice cloning adds another layer of complexity. This workflow handles everything — provide a short voice sample and an image, type what you want the avatar to say, and get a lip-synced talking avatar video. What this workflow does Reads a short reference audio clip and a first frame image in parallel Clones the voice from the reference audio using deAPI (Qwen3 TTS VoiceClone) and generates new speech from the provided text Merges the cloned audio and the first frame image into a single item AI Agent crafts a talking-avatar-optimized video prompt — focusing on lip sync, facial expressions, and natural movement — then boosts it with the deAPI Video Prompt Booster tool using the first frame image for visual context Generates a talking avatar video synced to the cloned speech using deAPI (LTX-2.3 22B), with the image as the opening frame and the AI-crafted prompt guiding the scene Setup Requirements n8n instance** (self-hosted or n8n Cloud) deAPI account for voice cloning, prompt boosting, and video generation Anthropic account for the AI Agent A short reference audio file (3-10 seconds, MP3/WAV/FLAC/OGG/M4A) A first frame image for the avatar (PNG/JPG) Installing the deAPI Node n8n Cloud: Go to **Settings → Community Nodes and toggle the “Verified Community Nodes” option Self-hosted: Go to **Settings → Community Nodes and install n8n-nodes-deapi Configuration Add your deAPI credentials (API key + webhook secret) Add your Anthropic credentials (API key) Update the File Path in the "Read Reference Audio" node to point to your voice sample Update the File Path in the "Read First Frame Image" node to point to your avatar image Edit the Set Fields node with your desired text, video prompt, and language Ensure your n8n instance is on HTTPS How to customize this workflow Change the AI model**: Swap Anthropic for OpenAI, Google Gemini, or any other LLM provider Adjust the avatar style**: Modify the AI Agent system message to target different visual styles (cartoon, realistic, professional, casual) Add audio transcription**: Insert a deAPI Transcribe Audio node before voice cloning and pass the transcript as refText for improved cloning accuracy Change the aspect ratio**: Switch from landscape to portrait for mobile-first content or square for social media Add a last frame image**: Use the optional lastFrame parameter in Generate From Audio to control how the video ends Change the trigger**: Replace the Manual Trigger with a Form Trigger, webhook, or Airtable trigger for batch avatar generation Add delivery**: Append a Gmail, Slack, or Google Drive node to automatically deliver the generated video

Who is this for? Marketing teams localizing video content for international markets E-commerce brands creating product videos for multiple regions Agencies producing multilingual ad campaigns for global clients Educators and trainers adapting video courses for different language audiences Anyone who wants to localize a spokesperson video without re-filming What problem does this solve? Localizing a video for a new market usually means hiring a local presenter, re-filming the entire video, or settling for subtitles that nobody reads. This workflow takes an existing spokesperson video, transcribes it, translates the speech into a target language, generates dubbed audio, and produces a lip-synced talking-head video with a locally-relevant face — all without a camera or a casting call. What this workflow does Reads the original spokesperson video and a reference image of the local presenter in parallel Transcribes the video's audio to text using deAPI (Whisper Large V3) Extracts the raw transcript text from the transcription result AI Agent translates the transcript into the target language, preserving tone and pacing Generates dubbed speech in the target language using deAPI text-to-speech (Qwen3 TTS Custom Voice) Generates a lip-synced talking-head video from the dubbed audio using deAPI audio-to-video generation (LTX-2.3 22B), with the local presenter image as the first frame Setup Requirements deAPI account for transcription, TTS, and video generation Anthropic account for the AI Agent (translation) A spokesperson video A reference image of the local presenter (JPG, JPEG, PNG, GIF, BMP, WebP — max 10 MB) Installing the deAPI Node n8n Cloud: Go to **Settings → Community Nodes and install n8n-nodes-deapi Self-hosted: Go to **Settings → Community Nodes and install n8n-nodes-deapi Configuration Add your deAPI credentials (API key + webhook secret) Add your Anthropic credentials (API key) Update the File Path in the "Read Source Video" node to point to your spokesperson video Update the File Path in the "Read Local Presenter Image" node to point to the reference image Edit the Set Fields node to set the target language (e.g., "Spanish", "Japanese", "French") Ensure your n8n instance is on HTTPS How to customize this workflow Change the AI model**: Swap Anthropic for OpenAI, Google Gemini, or any other LLM provider for translation Change the TTS model**: Switch Qwen3 TTS Custom Voice for Kokoro or Chatterbox for different voice characteristics Use voice cloning**: Replace the Generate Speech node with Clone a Voice to preserve the original speaker's voice in the target language Batch processing**: Replace the Manual Trigger with a Google Sheets or Airtable trigger containing rows for each target language and local presenter image Add delivery**: Append a Gmail, Slack, or Google Drive node to automatically deliver the localized video

Automatically organise your Gmail inbox using AI. This workflow categorises every incoming email and applies Gmail labels, keeping only important emails in your inbox while filing everything else automatically. Who is this for? Anyone overwhelmed by email clutter who wants inbox zero without manual sorting. How it works Gmail Trigger polls your inbox for new emails every minute AI Categorisation (GPT-4o) analyses each email and assigns a category such as Action Required, Newsletters, Sales Pitches, Client Communication, Receipts, and more Filter checks if the email requires your attention or can be auto-filed Label Management removes non-actionable emails from inbox and applies the appropriate Gmail label Prerequisites Gmail account with OAuth2 access OpenAI API key Gmail labels created for each category you want to use Setup steps Import the workflow and connect your Gmail OAuth2 credentials Add your OpenAI API key Create Gmail labels matching your categories such as Action Required, Newsletters, People Selling Me Stuff, Admin/Receipts Run the Get many labels node manually to retrieve your label IDs Update the Add to folder node with your label ID mapping using the example in the pink sticky note Customise the AI prompt categories to match your workflow needs Test with a few emails before activating

This workflow automatically generates realistic comments for your WordPress articles using AI. It makes your blog look more active, improves engagement, and can even support SEO by adding keyword-relevant comments. How It Works Fetches all published blog posts from your WordPress site via the REST API. Builds a tailored AI prompt using the article’s title, excerpt, and content. Uses OpenAI to generate a short, natural-sounding comment (some positive, some neutral, some longer, some shorter). Assigns a random commenter name and email. Posts the generated comment back to WordPress. Requirements n8n version: 1.49.0 or later (recommended). Active OpenAI API key. WordPress site with REST API enabled. WordPress API credentials (username + application password). Setup Instructions Import this workflow into n8n. Add your credentials in n8n > Credentials: OpenAI API (API key). WordPress API (username + application password). Replace the sample URL https://example.com with your own WordPress site URL. Execute manually or schedule it to run periodically. Categories AI & Machine Learning WordPress Content Marketing Engagement Tags ai, openai, wordpress, comments, automation, engagement, n8n