Agents & Automations

Summarize YouTube Videos & Chat About Content with GPT-4o-mini via Telegram 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 WorksInput: 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. 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: 1. Import the Workflow: Download the provided JSON template and import it into your n8n instance. 2. 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. 3. 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. 4. 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.

How it works Fetch all workflows from your n8n instance. Filter workflows that contain nodes with a modelId setting. Extract the node names, model IDs, model names, workflow names, and workflow URLs. Save the extracted information into a connected Google Sheet. Set up steps Connect your n8n API credentials. Connect your Google Sheets account. Replace "Your n8n domain" with your actual domain URL. Use this Google Sheet template to create a new sheet for results. Setup typically takes 5 minutes. Be cautious: if you have over 100 workflows, performance may be impacted. Notes Sticky notes inside the workflow provide extra guidance. This workflow clears old sheet data before writing new results. Make sure your n8n instance allows API access. Result Example Update: It didn't detect the AI model in the tool originally. Now it's fixed! Update 20250429: Support 1.91.0 with open node directly! Optimize the URL with node ID.

Primer workflow for OpenAI models: ChatGPT, DALLE-2, Whisper This workflow contains 5 examples on how to work with OpenAI API. 1. Transcribe voice into text via Whisper model (disabled, please put your own mp3 file with voice). 2. The old way of using OpenAI conversational model via text-davinci-003. 3. Examples 1.x: Simple ChatGPT calls. Text completion and text edit. 4. Example 2: Provide system and user content into ChatGPT. 5. Examples 3.x: Create system / user / assistance content via Code Node. Prompt chaining technique example. 6. Example 4: Generate code via ChatGPT. 7. Example 5: Return multiple answers. Useful for providing picking the most relevant reply. IMPORTANT! Do not run the whole workflow, it's rather slow. Better execute the last node of each branch or simply disconnect branches that are not needed.

Unlock AI-Driven Research with Jina AI (No API Key Needed!) Following the success of Open Deep Research 1.0, we are excited to introduce an improved and fully free version: AI-Powered Research with Jina AI Deep Search. This workflow leverages Jina AI’s Deep Search API, a free and powerful AI research tool that requires no API key. It automates querying, analyzing, and formatting research reports, making AI-driven research accessible to everyone. Key Features - No API Keys Required - Start researching instantly without setup hassle. - Automated Deep Search - Uses Jina AI to fetch relevant and high-quality information. - Structured AI Reports - Generates clear, well-formatted research documents in markdown. - Flexible and Customizable - Modify the workflow to fit your specific research needs. - Ideal for Researchers, Writers & Students - Speed up your research workflow. Use Cases This workflow is particularly useful for: - Researchers - Quickly gather and summarize academic papers, online sources, and deep web content. - Writers & Journalists - Automate background research for articles, essays, and investigative reports. - Students & Educators - Generate structured reports for assignments, literature reviews, or presentations. - Content Creators - Find reliable sources for blog posts, videos, or social media content. - Data Analysts - Retrieve contextual insights from various online sources for reports and analysis. How It Works 1. The user submits a research query via chat. 2. The workflow sends the query to Jina AI’s Deep Search API. 3. The AI processes and generates a well-structured research report. 4. A code node formats the response into clean markdown. 5. The final output is a structured, easy-to-read AI-generated report. Pre-Conditions & Requirements - An n8n instance (self-hosted or cloud). - No API keys needed – Jina AI Deep Search is completely free. - Basic knowledge of n8n workflow automation is recommended for customization. Customization Options This workflow is fully modular, allowing users to: - Modify the query prompt to refine the research focus. - Adjust the report formatting to match personal or professional needs. - Expand the workflow by adding additional AI tools or data sources. - Integrate it with other workflows in n8n to enhance automation. Users are free to connect it with other workflows, add custom nodes, or tweak existing configurations. Getting Started - Setup Time: Less than 5 minutes - Import the workflow into n8n. - Run the workflow and input a research topic. - Receive a fully formatted AI-generated research report. Start your AI-powered research with Jina AI Deep Search today!

🎥 Analyze YouTube Video for Summaries, Transcripts & Content + Google GeminiWho is this for? This workflow is ideal for content creators, video marketers, and research professionals who need to extract actionable insights, detailed transcripts, or metadata from YouTube videos efficiently. It is particularly useful for those leveraging AI tools to analyze video content and optimize audience engagement. What problem does this workflow solve? / Use case Analyzing video content manually can be time-consuming and prone to errors. This workflow automates the process by extracting key metadata, generating summaries, and providing structured transcripts tailored to specific use cases. It helps users save time and ensures accurate data extraction for content optimization. What this workflow does - Extracts audience-specific metadata (e.g., video type, tone, key topics, engagement drivers). - Generates customized outputs based on six prompt types: - Default: Actionable insights and strategies. - Transcribe: Verbatim transcription. - Timestamps: Timestamped dialogue. - Summary: Concise bullet-point summary. - Scene: Visual descriptions of settings and techniques. - Clips: High-engagement video segments with timestamps. Saves extracted data as a text file in Google Drive. Sends analyzed outputs via Gmail or provides them in a completion form. Setup - Configure API keys: Add your Google API key as an environment variable. - Input requirements: Provide the YouTube video ID (e.g., wBuULAoJxok). Select a prompt type from the dropdown menu. - Connect credentials: Set up Google Drive and Gmail integrations in n8n. How to customize this workflow to your needs - Modify the metadata prompt to extract additional fields relevant to your use case. - Adjust the output format for summaries or transcripts based on your preferences (e.g., structured bullets or plain text). - Add nodes to integrate with other platforms like Slack or Notion for further collaboration. Example Usage - Input: YouTube video ID (wBuULAoJxok) and prompt type (summary). - Output: A concise summary highlighting actionable insights, tools, and resources mentioned in the video.

This n8n template showcases the new HTTP tool released in version 1.47.0. Overall, the tool helps simplify AI Agent workflows where custom sub-workflows were performing the same simple HTTP requests. Comparisons 1. AI agent that can scrape webpages Remake of AI Agent that can scrape webpagesChanges: - Replaces Execute Workflow Tool and Subworkflow - Replaces Response Formatting 2. Allow your AI to call an API to fetch data Remake of Allow your AI to call an API to fetch dataChanges: - Replaces Execute Workflow Tool and Subworkflow - Replaces Manual Query Params Definitions - Replaces Response Formatting

🎨 AI Graphic Design Team - Generate and Review AI Images with Ideogram and OpenAI Who is this for? This workflow is perfect for graphic designers, creative agencies, marketing teams, or freelancers who regularly use AI-generated images in their projects. It's specifically beneficial for teams that want to automate the generation, review, and management of AI-created graphics efficiently. What problem does this workflow solve? Design teams often face time-consuming manual reviews and inconsistent quality checks for AI-generated images. This workflow addresses these challenges by automating image generation and introducing a systematic, AI-driven vetting process. This ensures only high-quality, relevant images reach your team's assets, saving valuable time and enhancing workflow efficiency. What this workflow doesAI Image Generation: Integrates Ideogram via HTTP Request to automatically create AI-generated images based on creative briefs. Automated Image Review: Uses OpenAI to automatically evaluate and approve images, ensuring they meet your predefined quality standards. Efficient Asset Management: Automatically creates structured Google Drive folders and compiles key metadata (including creation dates, prompts, and image links) into a CSV file and Google Sheet. Immediate Email Notifications: Delivers a setup confirmation and provides easy access to Google Drive folders and assets via automated email notifications. Final Approved Images: Outputs vetted, ready-to-use images for your creative projects, removing the burden of manual reviews. Setup 1. Initial Email Configuration Update your email details in both the "Setup Gmail" node and the "Gmail" notification node. Run the initial setup workflow to automatically create the Google Drive folders "Graphic_Design_Team" and "Image_Generations," and upload your CSV file. 2. Review Email & Set Up Google Sheets Check your inbox for an automated email containing folder IDs and direct links. Create and set up a Google Sheet by importing the provided CSV data from your email. 3. Update Workflow Nodes Select your newly created Google Sheet in both Google Sheets nodes. Update your Creative Brief node with the Google Drive folder IDs provided in the email. 4. Run Workflow for AI Image Generation & Review Execute the workflow. Your generated images will be automatically vetted, organized, and ready for creative use. How to Customize This Workflow - Tailor Image Generation Prompts: Adjust prompts and settings in the Ideogram HTTP Request node to better fit your project's creative requirements. - Set Quality Standards: Modify the criteria used by the OpenAI node to reflect your specific standards and preferences for image approval. - Customize Asset Organization: Adapt Google Drive folder structures, CSV headers, or Google Sheets integrations to match your team's organizational preferences. Dependencies & Requirements - Nodes Used: - HTTP Request (Ideogram API integration) - OpenAI (Image review and quality assessment) - Gmail (Automated notifications) - Google Drive (File and asset management) - Google Sheets (Metadata organization) - Credentials: Ensure Gmail, Google Drive, Google Sheets, and OpenAI credentials are properly configured in your n8n account. No custom or community nodes are needed. Final Outcome Upon completion, your workflow efficiently provides vetted, high-quality AI-generated images, organized in Google Drive and accessible via easy-to-use metadata in Google Sheets, drastically reducing manual intervention and accelerating your creative processes.

This n8n workflow is designed to work on the local network and assists with reconciling downloaded bank statements with internal tenant records to quickly highlight any issues with payments such as missed or late payments or those of incorrect amounts. This assistant can then generate a report to quickly flag attention to ensure remedial action is taken. How it works The workflow monitors a local network drive to watch for new bank statements that are added. This bank statement is then imported into the n8n workflow, its contents extracted, and sent to the AI Agent. The AI Agent analyzes the line items to identify the dates and any incoming payments from tenants. The AI agent then uses a locally-hosted Excel ("XLSX") spreadsheet to get both tenant records and property records. From this data, it can determine for each active tenant when payment is due, the amount, and the tenancy duration. Comparing to the bank statement, the AI Agent can now report on where tenants have missed their payments, made late payments, or are paying incorrect amounts. The final report is generated and logged in the same XLSX for a human to check and action. Requirements - A self-hosted version of n8n is required. - OpenAI account for the AI model. Customizing this workflow If your organization has a Slack or Teams account, consider sending reports to a channel for increased productivity. Email may be a good choice too. Want to go fully local? A version of this workflow is available which uses Ollama instead. You can download this template here.

This n8n demonstrates how to build your own Github MCP server to personalize it to your organisation's repositories, issues, and pull requests. This n8n implementation, though not as fully featured as the official MCP server offered by Github, allows you to control precisely what access and/or functionality is granted to users, which can make MCP use simpler and, in some cases, more secure. The use-case in this template is to simply view and comment on issues within a specific repository but can be extended to meet the needs of your team. This MCP example is based on an official MCP reference implementation. How it works A MCP server trigger is used and connected to 3 custom workflow tools. We're using custom workflow tools as there are quite a few nodes required for each task. Behind these tools are regular Github nodes, although preconfigured with credentials and targeted repository. The "Get Issue Comments" and "Create Issue Comment" tools depend on obtaining an Issue Number first. The agent should call the "Get Latest Issues" tool for this. How to use This Github MCP server allows any compatible MCP client to view and comment on Github Issues. You will need to have a Github account and repository access available before you can use this server. Connect your MCP client by following the n8n guidelines. Try the following queries in your MCP client: - "Can you get me the latest issues about MCP?" - "What is the current progress on Issue 12345?" - "Please can you add a comment to Issue 12345 that they should try installing the latest version and see if that works?" Requirements - Github for account and repository access. The repository need not be your own, but you'll still need to ensure you have the correct permissions. - MCP Client or Agent for usage, such as Claude Desktop. Customising this workflow Extend this template to interact with pull requests or workflows within your own company's Github repositories. Alternatively, pull in metrics and generate reports for programme managers. Remember to set the MCP server to require credentials before going to production and sharing this MCP server with others!

🚀 Local Multi-LLM Testing & Performance Tracker This workflow is perfect for developers, researchers, and data scientists benchmarking multiple LLMs with LM Studio. It dynamically fetches active models, tests prompts, and tracks metrics like word count, readability, and response time, logging results into Google Sheets. Easily adjust temperature 🔥 and top P 🎯 for flexible model testing. Level of Effort: 🟢 Easy – Minimal setup with customizable options. Setup Steps: - Install LM Studio and configure models. - Update IP to connect to LM Studio. - Create a Google Sheet for result tracking. Key Outcomes: - Benchmark LLM performance. - Automate results in Google Sheets for easy comparison.

This n8n workflow streamlines the onboarding process for new customers by automating personalized email communication, calendar scheduling, and contact assignment in HubSpot. It is perfect for businesses looking to ensure a smooth and personalized onboarding experience for new clients. Who is this for? - Customer success teams who need to onboard new clients efficiently. - Sales teams who want to ensure smooth transitions from prospect to customer. - Small businesses that want to automate customer onboarding without complex systems. What problem is this workflow solving? This workflow reduces the manual effort involved in onboarding new customers by: - Automatically sending personalized welcome emails. - Scheduling a welcome meeting using a calendar tool. - Assigning the customer to a Customer Success Manager (CSM) in HubSpot. What this workflow does:Trigger via Webhook or HubSpot: The workflow can be triggered either by a webhook (direct API call) or a HubSpot trigger (e.g., when a new contact is created). HubSpot Connection: - Retrieves the list of HubSpot owners (users with contact access). - Identifies the owner of the new contact. Calendar Management: Utilizes a Calendar Agent to schedule a welcome meeting with the new customer. The Calendar Agent can create, update, or delete events as needed. Personalized Email Creation: Uses an AI-powered Email Writer (OpenAI) to generate a personalized welcome email. Transforms the email text into HTML for a polished format. Email Sending via Gmail: Sends the personalized email to the customer using Gmail. Sets the new contact’s owner in HubSpot for further communication tracking. Setup:Webhook Setup in n8n: - Create a new workflow and add a Webhook node. - Set the Webhook URL path (e.g., /webhook-customer-onboarding). - Make sure the workflow is active. Webhook Setup in HubSpot: - Go to HubSpot Developer Account. - Navigate to Settings > Integrations > Webhooks. - Create a new webhook and set the URL as the n8n Webhook URL. - Choose POST as the request method. - Test the webhook to ensure it triggers the workflow in n8n. Calendar Agent Configuration: The Calendar Agent can be configured to create, update, or delete events. Connect it to your calendar tool (Google Calendar, Outlook, etc.). Customize the calendar event details (title, description, time). Email Writer Setup: Customize the AI prompt in the Email Writer node to match your brand’s voice. Adjust the email text format for your specific needs. Gmail Integration: Connect your Gmail account in n8n. Set the recipient email to the new customer’s email address. How to customize this workflow to your needs:Modify the AI-Powered Email: - Adjust the email prompt for the AI model to create a different welcome message. - Change the email format or add custom variables (e.g., customer name, service details). Customize Calendar Settings: - Set default time slots for welcome meetings. - Specify which calendar to use for scheduling. Add Additional Steps: - Extend the workflow to automatically assign the customer to a specific HubSpot list. - Add a follow-up email or survey after the welcome meeting. This workflow is perfect for businesses seeking an efficient and personalized onboarding process, ensuring new customers feel welcomed and supported from day one.

Stay on top of the latest crypto news and market sentiment instantly, all inside Telegram! This workflow aggregates articles from the top crypto news sources, filters for your topic of interest, and summarizes key news and market sentiment using GPT-4o AI. Ideal for crypto traders, investors, analysts, and market watchers needing fast, intelligent news briefings. 💬 Just type a coin name (e.g., "Bitcoin", "Solana", "DeFi") into your Telegram AI Agent—and get a smart news digest. How It Works 1. Telegram Bot Trigger User sends a keyword (e.g., "Ethereum") of questions to the Telegram AI Agent. 2. Keyword Extraction (AI-Powered) An AI agent identifies the main topic for better targeting. 3. News Aggregation Pulls articles from 9 major crypto news RSS feeds: - Cointelegraph - Bitcoin Magazine - CoinDesk - Bitcoinist - NewsBTC - CryptoPotato - 99Bitcoins - CryptoBriefing - Crypto.news 4. Filtering Finds and merges articles relevant to the user's keyword. 5. AI SummarizationGPT-4o generates a 3-part summary: - News Summary - Market Sentiment Analysis - List of Article Links 6. Telegram Response Sends a structured, easy-to-read digest back to the user. 🔍 What You Can Do with This Workflow - Summarize breaking news for any crypto project or keyword - Monitor real-time market sentiment on Bitcoin, DeFi, NFTs, and more - Stay ahead of FUD, bullish trends, and major news events - Quickly brief yourself or your team via Telegram - Use it as a foundation for more advanced crypto alert bots ✅ Example User Inputs - "Bitcoin" → Latest Bitcoin news and sentiment summary - "Solana" → Updates on Solana projects, price movements, and community trends - "NFT" → Aggregated news about NFT markets and launches - "Layer 2" → Insights on Optimism, Arbitrum, and other L2s 🛠️ Setup Instructions 1. Create a Telegram Bot Use @BotFather and obtain the Bot Token. 2. Configure Telegram Credentials in n8n Add your bot token under Telegram API Credentials. 3. Configure OpenAI API Add your OpenAI credentials for GPT-4o access. 4. Update Telegram Send Node In the Telegram Send node, replace the placeholder chatId with your real Telegram user or group chat ID. 5. Deploy and Test Start chatting with your bot: e.g., "Ethereum" or "DeFi". 📌 Workflow Highlights - 9 major crypto news sources combined - Smart keyword matching with AI query parsing - Summarized insights in human-readable format - Reference links included for deeper reading - Instant delivery via Telegram 🚀 Get ahead of the crypto market—automate your news and sentiment monitoring with AI inside Telegram!

Automatically extract new articles from RSS feeds, convert HTML to text, summarize with OpenAI, and save to Google Sheets for easy access.

Automatically generate new articles using Perplexity AI and add them to Google Sheets whenever a new article is detected via RSS feed.

This n8n workflow demonstrates creating a recipe recommendation chatbot using the Qdrant vector store recommendation API. Use this example to build recommendation features in your AI Agents for your users. How it works For our recipes, we'll use HelloFresh's weekly course and recipes for data. We'll scrape the website for this data. Each recipe is split, vectorized, and inserted into a Qdrant Collection using Mistral Embeddings. Additionally, the whole recipe is stored in a SQLite database for later retrieval. Our AI Agent is set up to recommend recipes from our Qdrant vector store. However, instead of the default similarity search, we'll use the Recommendation API instead. Qdrant's Recommendation API allows you to provide a negative prompt; in our case, the user can specify recipes or ingredients to avoid. The AI Agent is now able to suggest a recipe recommendation better suited for the user and increase customer satisfaction. Customizing the workflow This workflow can work for a variety of different audiences. Try different sets of data such as clothes, sports shoes, vehicles, or even holidays.

This workflow template demonstrates how to create an AI-powered agent that provides users with current weather information and Wikipedia summaries. By integrating n8n with Ollama's local Large Language Models (LLMs), this template offers a seamless and privacy-conscious solution for real-time data retrieval and summarization. Who is this for? - Developers and Enthusiasts: Individuals interested in building AI-driven workflows without relying on external APIs. - Privacy-Conscious Users: Those who prefer processing data locally to maintain control over their information. - Educators and Students: Learners seeking hands-on experience with AI integrations and workflow automation. What problem does this workflow solve? Accessing up-to-date weather information and concise Wikipedia summaries typically requires multiple API calls to external services, which can raise privacy concerns and incur costs. This workflow addresses these issues by utilizing Ollama's self-hosted LLMs within n8n, enabling users to retrieve and process information locally. What this workflow does: - User Input Capture: Begins with a chat interface where users can input queries. - AI Processing: The input is sent to an AI Agent node configured with Ollama's LLMs, which interprets the query and determines the required actions. - Weather Retrieval: For weather-related queries, the workflow fetches current weather data from a specified source. - Wikipedia Summarization: For queries seeking information, it retrieves relevant Wikipedia content and generates concise summaries. How to customize this workflow to your needs: - Automate Triggers: Set up scheduled triggers to provide users with regular updates, such as daily weather forecasts or featured Wikipedia articles.

This n8n workflow simplifies the process of removing backgrounds from images stored in Google Drive. By leveraging the PhotoRoom API, this template enables automatic background removal, padding adjustments, and output formatting, all while storing the updated images back in a designated Google Drive folder. This workflow is very useful for companies or individuals that are spending a lot of time on removing the background from product images. How it Works The workflow begins with a Google Drive Trigger node that monitors a specific folder for new image uploads. Upon detecting a new image, the workflow downloads the file and extracts essential metadata, such as the file size. Configurations are set for background color, padding, output size, and more, which are all customizable to match specific requirements. The PhotoRoom API is called to process the image by removing its background and adding padding based on the settings. The processed image is saved back to Google Drive in the specified output folder with an updated name indicating the background has been removed. Requirements - PhotoRoom API Key - Google Drive API Access Customizing the Workflow Easily adjust the background color, padding, and output size using the configuration node. Modify the output folder path in Google Drive or replace Google Drive with another storage service if needed. For advanced use cases, integrate further image processing steps, such as adding captions or analyzing content using AI.

This automation generates engaging WordPress blog posts by analyzing every new Google Sheets row employing insights from Perplexity AI and ChatGPT. It then publishes them directly to your site and updates the sheet.

Instantly manage Instagram comments by responding to new comments and updating media using Zaia for streamlined social media engagement.

What this workflow does? This workflow converts orthographic three-view drawings into 360° rotation videos through PiAPI's GPT-4o-Image and Kling APIs (unofficial). The workflow could be set with our 3D Figurine Orthographic Views workflow for generation. Who is the workflow for? - Designers: Generate inspiration into 3D designs and make them spin to gain concrete details in an efficient way. - Online shoppers: Show potential products from all angles in videos and preview the overall texture of models. - Content Creators (including toy bloggers): Make fun videos of collectible models. Step-by-step Instructions 1. Fill in basic parameters with your X-API-Key of your PiAPI account and 3-View image URL. 2. Click test workflow. 3. Get the final video in the last node. Use Case - Input Image - Output Video

Automatically convert Google Sheets data into text-to-speech audio using OpenAI and Eleven Labs, then send via email with Google Email.