Workflow Templates

Who is this for? This template is designed for internal support teams, product specialists, and knowledge managers in technology companies who want to automate ingestion of product documentation and enable AI-driven, retrieval-augmented question answering via WhatsApp. What problem is this workflow solving? Support agents often spend too much time manually searching through lengthy documentation, leading to inconsistent or delayed answers. This solution automates importing, chunking, and indexing product manuals, then uses retrieval-augmented generation (RAG) to answer user queries accurately and quickly with AI via WhatsApp messaging. What these workflows do Workflow 1: Document Ingestion & Indexing Manually triggered to import product documentation from Google Docs. Automatically splits large documents into chunks for efficient searching. Generates vector embeddings for each chunk using OpenAI embeddings. Inserts the embedded chunks and metadata into a MongoDB Atlas vector store, enabling fast semantic search. Workflow 2: AI-Powered Query & Response via WhatsApp Listens for incoming WhatsApp user messages, supporting various types: Text messages: Plain text queries from users. Audio messages: Voice notes transcribed into text for processing. Image messages: Photos or screenshots analyzed to provide contextual answers. Document messages: PDFs, spreadsheets, or other files parsed for relevant content. Converts incoming queries to vector embeddings and performs similarity search on the MongoDB vector store. Uses OpenAI’s GPT-4o-mini model with retrieval-augmented generation to produce concise, context-aware answers. Maintains conversation context across multiple turns using a memory buffer node. Routes different message types to appropriate processing nodes to maximize answer quality. Setup Setting up vector embeddings Authenticate Google Docs and connect your Google Docs URL containing the product documentation you want to index. Authenticate MongoDB Atlas and connect the collection where you want to store the vector embeddings. Create a search index on this collection to support vector similarity queries. Ensure the index name matches the one configured in n8n (data_index). See the example MongoDB search index template below for reference. Setting up chat Authenticate the WhatsApp node with your Meta account credentials to enable message receiving and sending. Connect the MongoDB collection containing embedded product documentation to the MongoDB Vector Search node used for similarity queries. Set up the system prompt in the Knowledge Base Agent node to reflect your company’s tone, answering style, and any business rules, ensuring it references the connected MongoDB collection for context retrieval. Make sure Both MongoDB nodes (in ingestion and chat workflows) are connected to the same collection with: An embedding field storing vector data, Relevant metadata fields (e.g., document ID, source), and The same vector index name configured (e.g., data_index). Search Index Example: { "mappings": { "dynamic": false, "fields": { "_id": { "type": "string" }, "text": { "type": "string" }, "embedding": { "type": "knnVector", "dimensions": 1536, "similarity": "cosine" }, "source": { "type": "string" }, "doc_id": { "type": "string" } } } }

This n8n template takes a video and extracts frames from it which are used with a multimodal LLM to generate a script. The script is then passed to the same multimodal LLM to generate a voiceover clip. This template was inspired by Processing and narrating a video with GPT's visual capabilities and the TTS API How it works Video is downloaded using the HTTP node. Python code node is used to extract the frames using OpenCV. Loop node is used o batch the frames for the LLM to generate partial scripts. All partial scripts are combined to form the full script which is then sent to OpenAI to generate audio from it. The finished voiceover clip is uploaded to Google Drive. Sample the finished product here: https://drive.google.com/file/d/1-XCoii0leGB2MffBMPpCZoxboVyeyeIX/view?usp=sharing Requirements OpenAI for LLM Ideally, a mid-range (16GB RAM) machine for acceptable performance! Customising this workflow For larger videos, consider splitting into smaller clips for better performance Use a multimodal LLM which supports fully video such as Google's Gemini.

✍️🌄 WordPress + AI Content Creator This workflow automates the creation and publishing of multi-reading-level content for WordPress blogs. It leverages AI to generate optimized articles, automatically creates featured images, and provides versions of the content at different reading levels (Grade 2, 5, and 9). How It Works Content Generation & Processing 🎯 Starts with a manual trigger and a user-defined blog topic Uses AI to create a structured blog post with proper HTML formatting Separates and validates the title and content components Saves a draft version to Google Drive for backup Multi-Reading Level Versions 📚 Automatically rewrites the content for different reading levels: Grade 9: Sophisticated language with appropriate metaphors Grade 5: Simplified with light humor and age-appropriate examples Grade 2: Basic language with simple metaphors and child-friendly explanations WordPress Integration 🌐 Creates a draft post in WordPress with the Grade 9 version Generates a relevant featured image using Pollinations.ai Automatically uploads and sets the featured image Sends success/error notifications via Telegram Setup Steps Configure API Credentials 🔑 Set up WordPress API connection Configure OpenAI API access Set up Google Drive integration Add Telegram bot credentials for notifications Customize Content Parameters ⚙️ Adjust reading level prompts as needed Modify image generation settings Set WordPress post parameters Test and Deploy 🚀 Run a test with a sample topic Verify all reading level versions Check WordPress draft creation Confirm notification system This workflow is perfect for content creators who need to maintain a consistent blog presence while catering to different audience reading levels. It's especially useful for educational content, news sites, or any platform that needs to communicate complex topics to diverse audiences.

This template creates a Telegram AI Assistant that answers questions based on your documents, powered by Google Gemini and Supabase. Key features include Intelligent HTML Post-processing for rich formatting in Telegram and Adaptive Message Chunking to handle long text responses. 📹 Watch the Bot in Action ▶️ Click the image above to watch a live demo on YouTube. This video provides a live demonstration of the bot's core features and how it interacts. See a quick walkthrough of its capabilities and user flow. How it works: User uploads a PDF document to a Telegram bot. The workflow processes the PDF, creates embeddings using Google Gemini, and stores these embeddings in a Supabase vector table. Users then ask questions to the bot. The workflow performs a vector search in Supabase to find relevant document chunks based on the user's query. Google Gemini uses the retrieved relevant chunks to generate an intelligent answer. The bot sends the formatted answer back to the user on Telegram, utilizing HTML markup for enhanced presentation. Set up steps: Setup should take approximately 15-20 minutes. Import the workflow into your n8n instance. Configure credentials for Telegram, Google Gemini, and Supabase. Set up your Supabase vector table using the provided SQL script. Activate the workflow. Detailed setup instructions, including how to get API keys and configure nodes, are available in the sticky notes within the workflow itself.

Who is this for? This workflow is designed for travel bloggers, content creators, social media managers, and anyone who wants to transform their travel photos into engaging written narratives. It's perfect for travelers looking to create compelling stories from their photo collections without spending hours crafting content manually, families wanting to document memorable trips, and digital nomads who need to produce travel content efficiently. What problem is this workflow solving? Converting travel photos into engaging stories is time-consuming and requires both creative writing skills and the ability to analyze visual content meaningfully. This workflow solves the challenge of: Transforming visual memories into compelling written narratives Organizing photos chronologically to create logical story flow Generating professional-quality travel content without writing expertise Analyzing photo content to extract meaningful themes and emotions Creating day-by-day structured narratives from unorganized photo collections Reducing the time spent on manual content creation for travel documentation What this workflow does This AI-powered photo storyteller takes your travel photos and automatically generates immersive, first-person travel narratives. The workflow: Accepts multiple photos through a webhook endpoint Uses OpenAI Vision API (GPT-4o) to analyze each photo's content, emotions, and themes Automatically organizes photos chronologically by date and timestamp Groups photos by travel days and extracts daily themes Leverages GPT-4.1 (minimum required) to craft engaging, first-person travel stories with creative day titles Generates structured narratives with sensory details, cultural observations, and emotional insights Outputs JSON formatted content ready for formatting Creates day-by-day story structure with memorable moments and reflective conclusions Setup Required Credentials: OpenAI API key configured in n8n for both Vision Analysis and Story Generation nodes Ensure you have sufficient OpenAI credits for image analysis and text generation Webhook Configuration: The workflow creates a webhook endpoint at /tripteller-upload Configure your photo upload interface to POST photos array to this endpoint Photos should be sent as base64 encoded data with filename and metadata Photo Requirements: Supported formats: Standard image formats (JPEG, PNG, etc.) Photos should include timestamp metadata for chronological organization Caution Do not upload all photos at once. Start with a small number of photos, like 5 at a time. How to customize this workflow to your needs Story Style Customization: Modify the system prompt in the "Generate Travel Story" node to adjust writing tone (nostalgic, adventurous, poetic, etc.) Customize the story structure by editing the output format requirements Add specific cultural or geographical context prompts for location-specific storytelling Photo Analysis Enhancement: Adjust the Vision Analysis node prompt to focus on specific elements (architecture, food, people, landscapes) Modify the grouping logic in the "Group Photos by Day" node for different time-based organization Add location extraction from EXIF data for geographical context Output Format Adjustment: Customize the final response structure in the "Format Final Response" node Add integration with publishing platforms (blog APIs, social media, etc.) Include additional metadata like location tags, travel duration, or trip statistics Performance Optimization: Adjust the execution timeout based on your typical photo volume Modify the parallel processing approach for large photo collections Add progress tracking for longer processing workflows

Summarize YouTube Videos & Chat About Content with GPT-4o-mini via Telegram Description This n8n workflow automates the process of summarizing YouTube video transcripts and enables users to interact with the content through AI-powered question answering via Telegram. It leverages the GPT-4o-mini model to generate summaries and provide insights based on the video’s transcript. How It Works Input: The workflow starts by receiving a YouTube video URL. This can be submitted through: A Telegram chat message. A webhook (e.g., triggered by a shortcut on Apple devices). Transcript Extraction: The URL is processed to extract the video transcript using the custom youtubeTranscripter community node (available here). The transcript is concatenated into a single text and stored in a Google Docs document. Summarization: The GPT-4o-mini AI model analyzes the transcript and generates a structured summary, including: A general overview. Key moments. Instructions (if applicable). The summary is then sent back to the user via Telegram. Interactive Q&A: Users can ask questions about the video content via Telegram. The AI retrieves the stored transcript from Google Docs and provides accurate, context-based answers, which are sent back through Telegram. Setup Instructions To configure this workflow, follow these steps: Import the Workflow: Download the provided JSON template and import it into your n8n instance. Install the Community Node: Install the youtubeTranscripter community node via npm: npm install n8n-nodes-youtube-transcription-kasha Important: This node requires a self-hosted n8n instance due to its external dependencies. Configure Nodes: Webhook: Set up the webhook to receive YouTube URLs. Alternatively, configure the Telegram node if using Telegram as the input method. Google Docs: Provide valid credentials to enable writing the transcript to a Google Docs document. AI Model: Set up the GPT-4o-mini model for summarization and Q&A functionality. Test the Workflow: Send a YouTube URL via your chosen input method (Telegram or webhook) and confirm that the summary is generated and delivered correctly. Customization Language**: Adjust the AI prompts to generate summaries and answers in any desired language. Output Format**: Modify the summary structure by editing the prompt in the summarization node. Input Methods**: Replace the Telegram node with another messaging or input node to adapt the workflow to different platforms. Who Can Benefit? This template is perfect for: Content Creators**: Quickly summarize video content for repurposing or review. Students and Researchers**: Extract key insights from educational or informational videos efficiently. General Users**: Interact with video content via AI without needing to watch the full video. Problem Solved This workflow simplifies video content consumption by: Automating the extraction and summarization of key points. Enabling interactive Q&A to address specific questions without rewatching the video. Additional Notes Disclaimer**: The youtubeTranscripter community node is required and only works on self-hosted n8n instances due to its reliance on external services. Apple Users**: Enhance your experience with a custom shortcut to share YouTube videos directly to the workflow. Download the shortcut here.

Use Case Automate image replacement in Google Docs: You need to update document images dynamically You want to create multiple versions of a template with different images You need to batch process document images from a URL database You want to generate shareable documents with custom images What this Workflow Does The workflow automates image replacement in Google Docs: Accepts image URLs from your database Finds and replaces images in template documents Creates new document copies with updated images Optionally converts to PDF and makes documents shareable Setup Connect your image URL database (column name must be "url") Set up Google Docs OAuth 2 API credentials Optional: Create a template document in Google Drive with placeholder images Optional: Configure Google Drive authentication for additional features How to Adjust it to Your Needs Remove template copying for single document processing Adjust image ID selection for documents with multiple images Configure sharing settings and download formats Customize file naming and storage location More templates and n8n workflows >>> @simonscrapes

This n8n workflow shows an easy way to automate the creation of social media assets using AI and a service like BannerBear. Designed for the busy marketer, leveraging AI image generation capabilities can help cut down production times and allow reinvesting into higher quality content. How it works This workflow generates social media banners for online events. Using a form trigger, a user can define the banner text and suggest an image to be generated. This request is passed to OpenAI's Dalle-3 image generation service to produce a relevant graphic for the event banner. This generated image is uploaded and sent to BannerBear where a template will use it and the rest of the form data to produce the banner. BannerBear returns the final banner which can now be used in an assortment of posts and publications. Requirements A BannerBear.com account and template is required An OpenAI account to use the Dalle-3 service. Customising the workflow We've only shown a small section of what BannerBear has to offer. With experimentation and other asset generating services such as AI audio and video, you should be able to generate more than just static banners!

📽️ What this workflow does This workflow turns a user-submitted form with country or animal names into a cinematic video with animated scenes and immersive ambient audio. Using GPT-4 for prompt generation, Dumpling AI for visual creation,& Replicate for motion animation, ElevenLabs for sound generation, and Creatomate for video stitching, it fully automates video production — from raw idea to rendered file. 🎯 What problem is this solving? Creating engaging multimedia content can take hours. This workflow automates the entire process of ideation, design, and rendering of high-quality cinematic clips, eliminating the need for manual video editing or audio production. 👥 Who is this for? Content creators and educators Digital artists and storytellers Marketers or YouTubers creating short-form visual content No-code/AI automation enthusiasts ⚙️ Setup Instructions ✅ Step 1: Google Sheet Create a Google Sheet with two columns: Title Generated videos Update the Sheet ID and tab name in the final node. ✅ Step 2: Google Drive Create two folders: One for ambient audio tracks One for final generated videos Update the folder IDs in both Google Drive nodes. ✅ Step 3: Credentials Setup Make sure all your API tokens are saved as credentials in n8n. This workflow uses the following integrations: OpenAI (GPT-4) Dumpling AI (via HTTP header) Replicate.com ElevenLabs Google Drive Google Sheets Creatomate ✅ Step 4: Form Fields Ensure your trigger form includes these fields: Title Country 1, Country 2, Country 3, Country 4 Style (e.g., cinematic, epic, fantasy, noir, etc.) 🧩 How it works User Form Submission Kicks off the workflow with the required inputs. Format Inputs Combines all 4 countries/animals into a single array. GPT-4: Generate Visual Prompts Uses GPT-4 to create rich cinematic descriptions per animal/country. Dumpling AI: Create Images Each description becomes a high-quality visual. GPT-4: Create Motion Prompts Each image prompt is rewritten into motion-based video prompts. Replicate: Animate Prompts and images are sent to Replicate’s model for animation. GPT-4: Generate Sound Prompt Based on the style, GPT-4 creates an ambient sound idea. ElevenLabs: Create Ambient Audio Audio is generated and uploaded to Google Drive. Creatomate: Stitch All Media All 4 motion videos and the audio track are stitched into one cinematic output. Upload to Google Drive + Log to Sheet Final video is saved in Drive and logged in Sheets with its title and link. 🛠️ How to Customize 🎨 Modify GPT prompts for different themes (e.g., horror, fantasy, sci-fi). 🧠 Swap animals for characters, objects, or locations. 🎧 Replace ambient sound with ElevenLabs voiceovers or music. 📂 Add metadata logging (generation time, duration, tags). 🧪 Try using alternative video tools like Pika Labs or Runway ML. ✅ Requirements n8n self-hosted or cloud instance Active accounts for: OpenAI, Dumpling AI, Replicate, ElevenLabs, Creatomate Google credentials set up for Drive + Sheets This is a perfect end-to-end automation that showcases the power of AI + automation for video storytelling.

For Who? Content Creators Youtube Automation Marketing Team How it works? 1 - Every week, retrieve the keywords you want to track 2 - Thanks to Apify, scrape videos from YouTube Search related to these keywords, filtered by relevance 3 - Wait until the dataset is completed 4 - Get the information contained in the dataset 5 - For each video, clean and summarize the script 6 - Upload everything to your Airtable database 📺 YouTube Video Tutorial: Setup (~5min) Scheduled Trigger: Select the frequency you want. If you change it, update the data accordingly in the "Create Videos Dataset" HTTP Request node in Body ➡️ JSON ➡️ dateFilter. Setup Keywords: Enter keywords related to the niche you want. If you change the number of keywords, update the data accordingly in the "Create Videos Dataset" HTTP Request node in Body ➡️ JSON ➡️ searchQueries. Create Videos Dataset: Refer to the Apify documentation for more: https://docs.apify.com/api/v2/getting-started APIs: For all HTTP Request nodes in the URL field, replace [YOUR_API_TOKEN] with your API token. 👨‍💻 More Workflows : https://n8n.io/creators/nasser/

What this workflow does This (set of) workflow(s) shows how to start multiple sub-workflows, asynchronously, in parallel, and then wait for all of them to complete. Normally sub-workflows would need to be run synchronously, in series, or, if they are executed asynchronously (to run concurrently, in parallel), there is no easy way to merge/wait for an arbitrary number of them to complete. This is a "design pattern" template to show one approach for running multiple, data-driven instances of a sub-workflow "asynchronously," in parallel (instead of running them one at a time in series), but still prevent the later steps in the workflow from continuing until all of the sub-workflows have reported back that they are finished, via callback URL. There are other techniques involving messaging services, database tables, or other external "flow manager" helpers, but this technique accomplishes the goal fully within n8n. Setup To implement this pattern, examine the nodes in the template and modify the incoming data leading to: A split-out loop to acynchronously execute a sub-workflow multiple times, in parallel. For instance, each sub-workflow might process one of a list of incoming documents. The resumeUrl for the main/parent workflow is provided to all of the sub-workflow executions, along with a unique identifier that can be counted later (e.g. a document file-name). A "wait-for-all" loop that checks whether all sub-workflows have reported back (if node) and builds a unique list of identifiers from the callbacks received from each execution of the sub-workflow. The sub-workflow should be designed to respond immediately (async) and later send a callback request when it has finished processing. The callback request should include the unique identifier value received when the sub-workflow it was started. This is meant to be a possible answer to questions like this one about running things in parallel, maybe this one about waiting for things to finish, this one about managing sub-batches of things by waiting for each batch, or this one about running things in parallel. The topic of how to do this comes up A LOT, and this is one of the only techniques that (so far) seems to work.

How it works This template uses a slack app to connect with your google calendar, generate an instant google meet link and post it as a message in a slack channel Setup steps Firstly, you'll need to create a slack app Authenticate and connect your slack account Connect and choose the Google calendar you want to generate Google meet links for Customize your slack message Then using a /meet command in slack, you can instantly generate and post your Google meet links