Workflow Templates

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. This workflow automates summarizing YouTube videos by accepting a YouTube URL via a form, fetching the video transcript using Apify, and then generating a concise summary with OpenAI GPT. Setup Instructions Prerequisites: Apify account with access to the YouTube Transcript actor. OpenAI API key (for GPT-4o-mini model). n8n instance with the Apify and OpenAI credentials configured. Configuration Steps Apify Setup: Configure Apify API credentials in the Apify node. Ensure the YouTube Transcript actor ID (1s7eXiaukVuOr4Ueg) is correct. OpenAI Setup: Add your OpenAI API key in the OpenAI Chat Model node. Confirm model selection is set to gpt-4o-mini. Customization Modify form field to accept additional inputs if needed. Adjust Apify actor input JSON in the Payload node for extra metadata extraction. Customize the summarization options to tweak summary length or style. Change OpenAI prompt or model parameters in the OpenAI Chat Model node for different output quality or tone. Steps 1. On Form Submission Node:** Form Trigger Purpose:** Collect the YouTube video URL from the user via a web form. 2. Prepare Payload Node:** Set Purpose:** Format the YouTube URL and options into the JSON payload for Apify input. 3. Fetch Transcript Node:** Apify Purpose:** Run the YouTube Transcript actor to retrieve video captions and metadata. 4. Extract Captions Purpose:** Isolate the captions field from the Apify response for processing. 5. Summarize Transcript Purpose:** Generate a concise summary of the video captions.

Search music and play to Spotify from Telegram This workflow is a simple demonstration on accessing a message model from Telegram and it makes searching for songs an easy task even if you can't remember the artist or song name. An OpenAI message model tries to figure out the song and sends it to an active Spotify device**. Use case Imagine an office where you play music in the background and the employees can control the music without having to login to the playing account. How it works You describe the song in Telegram. Telegram bot sends the text to n8n. An OpenAI message model tries to find the song. Spotify gets the search query string. First match is then added to queue. -- If there is no match a message is sent to Telegram and the process ends. We change to the next track in the list. We make sure the song starts playing by trying to resume. We fetch the currently playing track. We return "now playing" information to Telegram: Song Name - Artist Name - Album Name. Error handling Every Spotify step has it's on error handler under settings where we output the error. Message parser receives the error and sends it to Telegram. Requirements Active workflow* OpenAI API key Telegram bot Spotify account and Oauth2 API Spotify active on a device** .* The Telegram trigger is activated only if this workflow is active. You can however TEST the workflow in the editor by clicking "Test step" and then it waits for the Telegram event. When event is received, just step through all steps or just clicking "Test step" on the "Fetch Now Playing" node. .** You must have a Spotify device active when trying to communicate with a device. Open Spotify and play something - not it is active.

This workflow automatically syncs Shopify orders with your Zendesk tickets. Using this workflow, Shopify orders will be added or have their information updated straight to your Zendesk tickets. Prerequisites Shopify account and Shopify credentials Zendesk account and Zendesk credentials How it works Shopify Trigger starts the workflow whenever an order is updated. Zendesk node finds if the order already exists and has a ticket assigned. Set node keeps and passes only ticket ID. Merge by Key node combines the Shopify order data with the Zendesk ticket data. If node splits the workflow conditionally, checks if the ticket already exists or not. If order is new, Zendesk node creates a new ticket for the order.

Quickly transform any LinkedIn profile URL into a concise, AI‑generated professional summary — perfect for recruiters, sales teams, and hiring managers who need instant insights into prospects or candidates without manual research. How it works The workflow polls a Google Sheet for new or updated rows containing LinkedIn profile URLs. For each URL, the Real‑Time LinkedIn Scraper API (via RapidAPI) pulls experience and education sections. Extracted profile data is sent to OpenAI’s GPT model, which generates a clean, structured summary highlighting key strengths, career trajectory, and differentiators. The generated summary is written back into a new column in the same row of your Google Sheet for easy review and sharing. Set up steps Connect your Google account and select the spreadsheet + worksheet containing your list of LinkedIn URLs. Sign up for the Real‑Time LinkedIn Scraper API on RapidAPI, copy your API key, and add it to the workflow’s HTTP Request node. Insert your OpenAI API key credentials. Ensure your Google Sheet has one column for “linkedin_url” and create two empty columns named “full_name” and "summary" (or customize them based on your needs). Run a single row through the workflow to verify scraping accuracy and summary formatting, then turn on the workflow for continuous automation. With this template, eliminate hours of manual profile review — instantly gain actionable insights and focus on what really matters: building relationships and closing deals.

📄 What this workflow does This workflow helps you analyze Google reviews of any business to generate powerful marketing insights. By simply submitting a business name and its Google Place ID, it fetches the top 30 reviews and uses GPT-4 (via LangChain Agent) to extract valuable customer insights such as marketing angles, customer motivations, product pain points, and voice of customer (VOC) quotes. The output is stored automatically in a connected Google Sheet. 👤 Who is this for Marketing teams looking for messaging inspiration Founders or product managers exploring customer feedback Brand strategists gathering real-world insights Agencies running VOC or sentiment analysis 🛠️ Requirements Dumpling AI API key** OpenAI GPT-4 or GPT-4o access** Google Sheets connection** A form or manual input with: Business Name Google Place ID ⚙️ How to set up Connect Credentials Dumpling AI (via HTTP Header Auth) OpenAI (GPT-4) Google Sheets (OAuth2) Prepare your Google Sheet Create columns: Business Name, Place ID, Marketing Angles, Customer Motivations, Frictions and Barriers, Product Opportunities, VOC Snippets Update Nodes Replace the Google Sheets Document ID and Tab Name with yours Check that the Dumpling API node is linked to your credential Optional: tweak the prompt in the LangChain Agent node to fit your tone or goals 🤖 How it works (Workflow Steps) User submits business name + Google Place ID Dumpling AI fetches top 30 reviews Workflow aggregates review text GPT-4 via LangChain analyzes the reviews Insights are parsed and logged to Google Sheets 💡 Customization Ideas Push output to Notion, Airtable, or Slack Add sentiment scoring to prioritize themes Create summaries for each insight category Schedule insights to be emailed weekly This is a plug-and-play VOC research workflow — great for founders, marketers, and product teams who want actionable data from real customers without doing manual review scraping or summarizing.

How it works This workflow changes the file name, and therefore the extension and MIME type, of any binary file passed to it. This is perfect for converting file formats on the fly, like turning a Telegram voice message (.oga) into an MP3 for an AI transcription service. Set New File Name: The SET OUTPUT FILE NAME node is where you define the desired output file name and extension (e.g., audio.mp3). It also dynamically captures the property name of the incoming binary (e.g., data). Extract Binary Data: The workflow temporarily converts the binary file into a Base64 text string to make it accessible in the next step. Rebuild Binary with New Name: A Code node takes the Base64 data and reconstructs it as a binary file, but this time, it assigns the new file name you specified. n8n automatically sets the MIME type based on the new file extension. Set up steps Setup time: < 1 minute This workflow is designed to be used as a sub-workflow. In your main workflow, add an Execute Sub-Workflow node where you need to change a file's type. In the Workflow parameter, select this "Change Binary MimeType/Extension" workflow. Open this workflow and go to the SET OUTPUT FILE NAME node. Modify the output_file_name value to your desired file name (e.g., voice_message.mp3 or document.pdf). Save this workflow. Now, any binary file you send to it from your main workflow will be returned with the new fileName and mimeType.

🤖 AI Customer Support Agent with Google Docs Knowledge (Telegram + OpenAI) This no-code workflow turns your Telegram bot into an intelligent, always-on AI support agent that references your business documentation in Google Docs to respond to customer queries—instantly and accurately. Watch full step-by-step video tutorial of the build here: https://youtu.be/Mlv7CjGO7wI 🔧 How it works: Telegram Trigger – Captures incoming messages from users on your Telegram bot Langchain AI Agent (OpenAI GPT) – Interprets the message and uses RAG (retrieval-augmented generation) techniques to craft an answer Google Docs Tool – Connects to and retrieves context from your specified Google Doc (e.g. FAQ, SOPs, policies) Memory Buffer – Keeps track of recent chat history for more human-like conversations Telegram Reply Node – Sends the AI-generated response back to the user 💡 Use Cases: E-commerce customer service SaaS product onboarding Internal helpdesk bot for teams WhatsApp-style support for digital businesses 🧠 What makes this powerful: Supports complex questions by referencing a live Google Doc knowledge base Works in plain conversational language (no buttons or forms needed) Runs 24/7 with zero code Easily extendable to Slack, WhatsApp, or email support 🛠️ Tools used: Telegram Node (trigger + send) Langchain Agent with OpenAI GPT Google Docs Tool Memory Buffer Sticky Notes for easy understanding

Auto-Categorize Outlook Emails with AI in n8n How It Works Trigger: The workflow starts with the Microsoft Outlook Trigger node, polling your inbox every minute for new emails. Extract & Clean Email Content: The email’s key fields (from, subject, isRead, body) are extracted. The body is converted from HTML to Markdown, then sanitized to plain text for reliable AI processing. Node Setup Details: Microsoft Outlook Trigger Resource: Message Operation: Trigger on new email Fields to Output: from, subject, isRead(optional), body Folders to Include: (Set to your Inbox or specific folder IDs) Markdown Node Input: {{$json"body"}} (HTML email body) Output Key: Email Body Markdown Purpose: Converts HTML to Markdown for easier downstream processing. Sanitize Node (Code Node) Input: Email Body Markdown from previous node Purpose: Cleans up Markdown, strips images, links, HTML tags, table formatting, and truncates to 4000 characters. Sample JS Code: // Get the markdown content from the previous node const markdownContent = $input.item.json["Email Body Markdown"]; Setup AI tools Move message and Get Folders Outlook tools are required, get contacts is optional. Set each field in the tools to "defined automatically by the model" and describe each field so the model understands how to use it. OpenRouter or other LLM models tool: You can use any client for this, but make sure to use a model that does well with tool calls (Claude, GPT-4.1, Gemini 2.5 Pro, etc.). Best Practices & Notes AI Prompt Engineering:** The AI is instructed to be conservative—never move emails from real people or saved contacts, and always explain its reasoning if it doesn’t move a message. This automation only works for NEW incoming messages. Inbox Zero:** This system is designed to help you achieve and maintain Inbox Zero by keeping only actionable items in your main inbox. Customization:** You can adjust the folder logic, add more categories, or tweak the AI prompt for your specific needs. Privacy:** All processing happens within your n8n instance; no email data is stored outside your environment except for the AI call (which only receives sanitized, minimal content).

Overview This release introduces a Voice-Enabled Tour Recommendation System that leverages n8n, ElevenLabs Voice Agent, OpenAI GPT-4o, and Pinecone Vector DB to deliver personalized travel itineraries based on spoken input. Users speak their preferences to the ElevenLabs voice agent, which then triggers an n8n workflow that returns a tailored tour plan. Features Voice interaction with AI-powered travel agent via ElevenLabs Uses ChatGPT-4o for contextual understanding and generation Dynamic query handling with vector-based search using Pinecone Fast response generation using n8n webhook Modular agent memory and role design for scalable enhancement Pre-requisites n8n account with workflow creation access ElevenLabs account with agent and webhook setup OpenAI API key (GPT-4o access) Pinecone account for vector database A list of vectorized tour packages using this n8n embedder (https://creators.n8n.io/workflows/5085) Setup Instructions Step 1: Configure the Voice Agent Webhook in ElevenLabs Use POST method Webhook URL: https://... Breakdown voice input into: Destination Type of tour Number of days Number of passengers Step 2: Set Up the AI Agent Prompt in ElevenLabs Use a conversational style with summaries, clarifying questions, and affirmations. Example Prompt: “You use a natural speech style and periodically summarize... Your goal is to help callers create a personalized tour plan.” Step 3: Select LLM LLM: GPT-4o Mini Memory window: Up to 5 contexts Step 4: Integrate Tools Use Custom Tool: n8n ID: tool_xxxxxx Tool Description: “Generates travel plan once the details are collected” Step 5: Build n8n Workflow Trigger: Webhook (POST) Process user input: Tour Recommendation AI Agent Use OpenAI Chat Model (GPT-4o) for reasoning Query Pinecone Vector Store using Tour Builder Q&A node Respond with structured Itinerary Plan via webhook response How to use: Execute the n8n workflow (the webhook waits for the voice trigger from elevenlabs) Start the Elevenlabs Voice Agent Request for a tour plan to any destination giving the details of your tour preferences. Wait for the Voice Agent to respond back with tour package suggestions after fetching the tour details from the n8n workflow. Close the conversation. | Area | Improvement | | ------------------ | ----------------------------------------------------- | | 🔉 Voice UX | Natural-sounding travel agent using ElevenLabs | | 💡 Personalization | ChatGPT-4o adapts based on travel style & preferences | | 📚 Knowledge Base | Pinecone-powered vector retrieval of real tour data | | 🔁 Reusability | Modular workflow with reusable embedding tools | | ⚙️ System Design | Separation of memory, logic, and data layers | Who is this for? Travel Agencies & DMCs Offer ultra-personalized packages based on customer queries. Let AI do the matching. Tour Package Aggregators Auto-curate and send matching packages from your catalog — no manual searching needed. Content & Marketing Teams Craft customized tour recommendations for email campaigns and newsletters. Tech-enabled Travel Startups Embed this intelligence in your workflows, CRMs, or chatbots to delight customers.

This workflow is an experiment to integrate charts in AI Agents, using the new Structured Output from OpenAI and Quickchart.io. How it works Users chat with an AI Agent. Anytime the AI Agent considers a chart is needed, it calls a tool to generate a chart OpenAI generates a chart using the Quickchart definition This object is added at the end of a Quickchart.io URL (see documentation) The url is added in the conversation via the AI Agent as markdown. Set up steps Create an OpenAI API Key Create the OpenAI credentials Use the credentials for the HTTP Request node (as Predefined Credential type) Activate your workflow Start chatting For example, you can ask the AI Agent to generate a chart about the top 5 movies at the box office Start exploring the limits Shout-out Quickchart.io is an amazing open source project that provides a free API to test. Go check them out! Example of chart

Unlock a new level of sophistication for your AI agents with this template. While the native n8n Think Tool is great for giving an agent an internal monologue, it's limited to one instance. This workflow provides a clever solution using a sub-workflow to create multiple, custom thinking tools, each with its own specific purpose. This template provides the foundation for building agents that can plan, act, and then reflect on their actions before proceeding. Instead of just reacting, your agent can now follow a structured, multi-step reasoning process that you design, leading to more reliable and powerful automations. Who is this for? AI and automation developers:** Anyone looking to build complex, multi-tool agents that require robust logic and planning capabilities. LangChain enthusiasts:** Users familiar with advanced agent concepts like ReAct (Reason-Act) will find this a practical way to implement similar frameworks in n8n. Problem solvers:** If your current agent struggles with complex tasks, giving it distinct steps for planning and reflection can dramatically improve its performance. What problem does this solve? Bypasses the single "Think Tool" limit:** The core of this template is a technique that allows you to add as many distinct thinking steps to your agent as you need. Enables complex reasoning:** You can design a structured thought process for your agent, such as "Plan the entire process," "Execute Step 1," and "Reflect on the result," making it behave more intelligently. Improves agent reliability and debugging:** By forcing the agent to write down its thoughts at different stages, you can easily see its line of reasoning, making it less prone to errors and much easier to debug when things go wrong. Provides a blueprint for sophisticated AI:** This is not just a simple tool; it's a foundational framework for building state-of-the-art AI agents that can handle more nuanced and multi-step tasks. How it works The re-usable "Thinking Space": The magic of this template is a simple sub-workflow that does nothing but receive text. This workflow acts as a reusable "scratchpad." Creating custom thinking tools: In the main workflow, we use the Tool (Workflow) node to call this "scratchpad" sub-workflow multiple times. We give each of these tools a unique name (e.g., Initial thoughts, Additional thoughts). The power of descriptions: The key is the description you give each of these tool nodes. This description tells the agent when and how it should use that specific thinking step. For example, the Initial thoughts tool is described as the place to create a plan at the start of a task. Orchestration via system prompt: The main AI Agent's system prompt acts as the conductor, instructing the agent on the overall process and telling it about its new thinking abilities (e.g., "Always start by using the Initial thoughts tool to make a plan..."). A practical example: This template includes two thinking tools to demonstrate a "Plan and Reflect" cycle, but you can add many more to fit your needs. Setup Add your own "action" tools: This template provides the thinking framework. To make it useful, you need to give the agent something to do. Add your own tools to the AI Agent, such as a web search tool, a database lookup, or an API call. Customize the thinking tools: Edit the description of the existing Initial thoughts and Additional thoughts tools. Make them relevant to the new action tools you've added. For example, "Plan which of the web search or database tools to use." Update the agent's brain: Modify the system prompt in the main AI Agent node. Tell it about the new action tools you've added and how it should use your customized thinking tools to complete its tasks. Connect your AI model: Select the OpenAI Chat Model node and add your credentials. Taking it further Create more granular thinking steps:** Add more thinking tools for different stages of a process, like a "Hypothesize a solution" tool, a "Verify assumptions" tool, or a "Final answer check" tool. Customize the thought process:* You can change *how the agent thinks by editing the prompt inside the fromAI('Thoughts', ...) field within each tool. You could ask for thoughts in a specific format, like bullet points or a JSON object. Change the workflow trigger:** Switch the chat trigger for a Telegram trigger, email, Slack, whatever you need for your use case! Integrate with memory:** For even more power, combine this framework with a long-term memory solution, allowing the agent to reflect on its thoughts from past conversations.

How it works creates a new page in Confluence based on a page template also defined in Confluence replaces any number of placeholders with data from your workflow generic implementation for maximum flexibility Set up steps All parameters you need to change are defined in the Set node Set your Atlassian-domain Set the template id you want to use as the basis for new pages Set the target space and parent page for new pages added based on that template. 🎥 Explainer video has all the details. =) Feedback Any feedback is welcome. If you have ideas for improvements, let me know.