Daily AI news digest with Perplexity Pro, GPT format & Gmail delivery
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. π§ AI News Update Every 24 Hours (with Perplexity + GPT Formatter) Description: This workflow automatically delivers a clean, AI-curated summary of the latest AI news headlines from the past 24 hours directly to your inbox β every morning at 9 AM. For step-by-step video tutorial for this build, watch here: https://youtu.be/O-DLvaMVLso π§° How It Works: π Schedule Trigger βRuns daily at 9 AM to start the workflow. π Perplexity AI Agent βSearches for AI-related headlines published in the last 24 hours, including: Headline 1-sentence summary Source Full URL π§ GPT Formatter AI Agent βUses an OpenAI language model (GPT-4.1-mini) to reformat raw news data into a clean, readable email update. π§· Memory Buffer (Optional) βGives the formatter context and continuity if you want to personalize formatting further over time. π§ Gmail Node βSends the formatted AI news digest to your inbox (or your teamβs) daily. π¦ Tools & APIs Required: β Perplexity AI API β OpenAI API β Gmail Account (OAuth2 credentials) π Use Cases: Daily AI trend monitoring for individuals or teams Automating internal market intelligence Research triggers for blog or content creation Email digests for newsletters or Slack updates π οΈ Customizable Ideas: Swap Gmail for Slack, Telegram, Discord, etc. Modify the topic (e.g., Climate Tech, Crypto News) Add sentiment analysis or AI-generated commentary Send summary to Google Docs or Notion instead
By Automate With MarcAutomated n8n workflow backup to GitHub with deletion tracking
Remixed Backup your workflows to GitHub from Solomon's work. Check out his templates. How it works This workflow will backup your workflows to GitHub. It uses the n8n API node to export all workflows. It then loops over the data, checks in GitHub to see if a file exists that uses the credential's ID. Once checked it will: update the file on GitHub if it exists; create a new file if it doesn't exist; ignore if it's the same. In addition, it also checks if any workflows have been deleted from n8n. If a workflow no longer exists in n8n, the corresponding file will be removed from the repository to keep everything in sync. Who is this for? People wanting to backup their workflows outside the server for safety purposes or to migrate to another server.
By Marcial AmbrizWebpage change detection & alerts with Google Suite and hash tracking
This n8n template can monitor and detect changes to a webpage's contents and notify you only when a change occurs. Great to keep an eye on and track publicly available documents such as company TOS, government policy or competitor pages. How it works A scheduled trigger is used so we can run everyday to automate this process. A website page is then fetched with the HTTP request node and the contents we want to track are extracted using the HTML node. To detect changes, we generate a hash on the contents with the cryptography node and compare it with previously seen hashes using the "remove duplicates" node. If the hash was seen before, the workflow stops here. Finally, when new changes are detected a copy of the contents are uploaded to Google Drive and a logged into a Google sheet. A notification email can also be sent if action is required. How to use Update the URL you want to track in the node named "variables" and ensure the HTML node has updated selectors to get the content you want. Ensure the timezone is set correctly when using the Scheduled Trigger node. Requirements Google Sheets, Drive and Gmail for storing and notifying about changes. Webpages should ideally be publicly accessible. If not, you may need to switch the HTTP request node with a webscraping service. Customising this workflow Not using Google? Easier swap to other Service providers such as Miscrosoft365. Need more URLs? Try modifing the variables node to accept multiple URLs though the HTML node will need to be customised.
By JimleukAutomatic news summarization & email digest with GPT-4, NewsAPI and Gmail
π° AI News Digest Agent: Auto News Summarizer & Email Newsletter Create an intelligent news curation system that automatically fetches breaking headlines, generates AI-powered summaries, and delivers personalized news digests to your subscriber list. Perfect for newsletter creators, team leaders, and content curators who want to keep their audience informed without the manual effort of news monitoring and summarization. π How It Works This streamlined 5-step automation delivers fresh news insights around the clock: Step 1: Automated News Collection The workflow runs on a configurable schedule (default: every 10 minutes) to fetch the latest headlines from NewsAPI, ensuring your content stays current with breaking developments. Step 2: Intelligent Content Curation The system pulls top headlines from reliable news sources, filtering by country, category, and relevance to deliver the most important stories of the day. Step 3: AI-Powered Summarization GPT-4 processes the collected headlines and creates: Concise 5-bullet point summaries Key insights and implications Easy-to-digest news overviews Professional formatting for email distribution Step 4: Subscriber Management The workflow accesses your Google Sheets subscriber list, retrieving names and email addresses for personalized delivery. Step 5: Automated Email Distribution Personalized news digests are automatically sent to each subscriber via Gmail, with custom greetings and professionally formatted content. βοΈ Setup Steps Prerequisites NewsAPI account (free tier available) OpenAI API access for content summarization Google Sheets for subscriber management Gmail account for email distribution n8n instance (cloud or self-hosted) Required Google Sheets Structure Create a simple subscriber database: | Name | Email | |---------------|--------------------------| | John Smith | john@example.com | | Sarah Johnson | sarah@company.com | | Mike Chen | mike.chen@startup.co | Configuration Steps Credential Setup NewsAPI Key: Sign up at newsapi.org for free headline access OpenAI API Key: Required for AI-powered news summarization Google Sheets OAuth2: Access your subscriber spreadsheet Gmail OAuth2: Enable automated email sending News Source Configuration Country Selection: Choose target region (US, UK, CA, AU, etc.) Category Filters: Focus on specific topics (technology, business, health) Source Selection: Prefer certain news outlets or avoid others Language Settings: Configure for international audiences AI Summarization Customization Default prompt creates 5-bullet summaries, but can be tailored for: Industry Focus: Technology, finance, healthcare, politics Audience Type: General public, professionals, executives Content Depth: Brief overviews vs detailed analysis Tone & Style: Formal, conversational, or technical Email Template Personalization Subject Line Formatting: Include date, breaking news indicators Greeting Customization: Use subscriber names for personal touch Content Layout: Professional formatting with clear sections Branding Elements: Add your organization's signature or logo Delivery Schedule Optimization Frequency Settings: Every 10 minutes, hourly, or daily Time Zone Considerations: Optimize for subscriber locations Breaking News Alerts: Immediate delivery for urgent stories Digest Compilation: Collect multiple stories for periodic summaries π Use Cases Newsletter Publishers Content Automation: Generate newsletter content without manual curation Consistent Publishing: Maintain regular delivery schedules automatically Audience Growth: Provide value that encourages subscriptions and shares Time Savings: Eliminate hours of daily news monitoring and writing Corporate Communications Employee Updates: Keep teams informed about industry developments Executive Briefings: Deliver curated news summaries to leadership Client Communications: Share relevant industry insights with customers Stakeholder Relations: Maintain informed investor and partner networks Educational Institutions Student Resources: Provide current events for academic discussions Faculty Updates: Keep educators informed about relevant developments Research Support: Deliver news related to specific academic fields Parent Communications: Share educational policy and school-related news Professional Services Client Value Addition: Provide industry-specific news as a service benefit Thought Leadership: Position your firm as an informed industry expert Business Development: Share insights that demonstrate market knowledge Team Knowledge Sharing: Keep entire organization current on industry trends Community Organizations Member Engagement: Keep community members informed and engaged Local News Focus: Customize for regional or local news coverage Event Planning: Stay informed about developments affecting your community Advocacy Support: Monitor news relevant to your organization's mission π§ Advanced Customization Options Multi-Source News Aggregation Expand beyond NewsAPI with additional sources: RSS Feed Integration: Add specialized industry publications Social Media Monitoring: Include trending topics from Twitter/LinkedIn Government Sources: Official announcements and policy updates International Coverage: Global perspectives on major stories Intelligent Content Filtering Implement smart curation features: Sentiment Analysis: Filter positive, negative, or neutral news Relevance Scoring: Prioritize stories based on subscriber interests Duplicate Detection: Avoid sending repetitive story coverage Quality Assessment: Ensure content meets editorial standards Subscriber Segmentation Create targeted news experiences: Interest Categories: Technology, business, sports, entertainment Geographic Preferences: Local, national, or international focus Delivery Preferences: Frequency and format customization Engagement Tracking: Monitor opens, clicks, and subscriber behavior Enhanced Email Features Professional newsletter capabilities: HTML Templates: Rich formatting with images and links Call-to-Action Buttons: Drive engagement with your content or services Social Sharing: Enable easy sharing of newsletter content Analytics Integration: Track email performance and subscriber engagement π Content Generation Examples Sample Email Output: Subject: π° Your Daily News Digest - March 15, 2024 Hi John, Please find today's top news headlines summarized below: π BUSINESS & TECHNOLOGY Federal Reserve signals potential rate cuts following inflation data Major tech companies announce AI partnership for healthcare applications Renewable energy sector sees record investment levels in Q1 2024 Cryptocurrency markets stabilize after regulatory clarity announcement Supply chain disruptions ease as global shipping routes normalize π‘ These developments suggest growing economic optimism and continued technology sector innovation. The healthcare AI partnership particularly signals significant advances in medical technology accessibility. Stay informed and have a great day! --- Powered by AI News Digest Agent Unsubscribe | Update Preferences Breaking News Alert Format: Subject: π¨ Breaking News Alert - Major Development Hi Sarah, BREAKING: [Headline] Key Details: [Critical point 1] [Critical point 2] [Impact analysis] Full coverage in your next scheduled digest. --- AI News Digest Agent π οΈ Troubleshooting & Best Practices Common Issues & Solutions API Rate Limiting Monitor NewsAPI quota usage and upgrade plan if needed Implement intelligent caching to reduce redundant requests Stagger requests during high-traffic periods Set up alerts for approaching rate limits Email Delivery Challenges Monitor Gmail sending limits and implement delays if needed Use professional email authentication (SPF, DKIM) Maintain clean subscriber lists to avoid spam flags Implement unsubscribe functionality for compliance Content Quality Control Review AI summaries periodically for accuracy and bias Implement feedback loops for continuous prompt improvement Create editorial guidelines for consistent tone and style Monitor subscriber feedback and engagement metrics Optimization Strategies Performance Enhancement Use parallel processing for multiple news sources Implement intelligent caching for repeated content Optimize AI prompts for faster processing and better results Monitor workflow execution time and resource usage Subscriber Growth Create compelling value propositions for newsletter signups Implement referral systems for organic growth Share sample newsletters on social media and websites Collect feedback to continuously improve content quality Content Strategy A/B test different summary formats and lengths Analyze which news categories generate most engagement Experiment with sending times for optimal open rates Create themed newsletters for special events or topics π Success Metrics Engagement Indicators Open Rates: Percentage of subscribers reading newsletters Click-Through Rates: Engagement with linked news sources Subscriber Growth: New signups and retention rates Forward/Share Rates: Viral coefficient of your content Content Quality Measurements Relevance Scores: Subscriber feedback on content usefulness Timeliness: How quickly breaking news reaches subscribers Accuracy: Verification of AI-summarized content Completeness: Coverage of important stories in your focus areas π Questions & Support Need assistance with your AI News Digest Agent setup or optimization? π§ Technical Support Email: Yaron@nofluff.online Response Time: Within 24 hours on business days Specialization: NewsAPI integration, AI content optimization, email deliverability π₯ Educational Resources YouTube Channel: https://www.youtube.com/@YaronBeen/videos Complete setup and configuration tutorials Advanced customization techniques for different industries Email marketing best practices for automated newsletters Troubleshooting common integration issues Scaling strategies for growing subscriber lists π€ Professional Community LinkedIn: https://www.linkedin.com/in/yaronbeen/ Connect for ongoing newsletter automation support Share your news curation success stories Access exclusive templates and workflow variations Join discussions about content automation trends π¬ Support Request Best Practices Include in your support message: Your target audience and newsletter focus Current subscriber count and growth goals Specific news categories or geographic regions of interest Any technical errors or integration challenges Current content creation workflow and pain points
By Yaron BeenTelegram bot inline keyboard with dynamic menus & rating system
π€ Telegram Bot with Dynamic Menus & Rating System What It Does This n8n workflow creates an interactive Telegram bot with: Dynamic inline keyboards that respond to user clicks 5-star rating system for collecting feedback Personalized responses using the user's actual name Multi-level menu navigation (Main β Settings β Profile, etc.) Real-time message updates when buttons are clicked How It Works Receives messages via Telegram webhook trigger node Extracts user data (name, ID, message type) Builds dynamic menus based on user actions Sends/updates messages with inline keyboards Handles button clicks without page refresh π Setup Instructions Get Your Bot Credentials Configure Workflow Open "Set Bot Token" node Replace token with yours Save and activate workflow (Active) Test Your Bot Message your bot on Telegram Click the buttons to navigate menus Try the rating system on Feature 1 π¨ Customization Guide Add New Menu Items In the "Prepare Response" Function node, add new cases: case 'your_feature': responseText = 'Your feature description'; keyboard = [ [{ text: 'π― Button 1', callback_data: 'action1' }], [{ text: 'π Back', callback_data: 'main' }] ]; break; Modify Rating Options Change star buttons to numbers or emojis: // Current: βββ // Alternative: 1οΈβ£ 2οΈβ£ 3οΈβ£ or π π Change Bot Responses Edit responseText for message content Modify keyboard arrays for button layout Add HTML formatting: <b>bold</b>, <i>italic</i> π‘ ++Key Features Demonstrated++ HTTP Request workaround for dynamic keyboards (n8n Telegram node limitation) Callback query handling to prevent loading animations Message editing vs sending new messages User data extraction from Telegram API Switch-case menu routing for scalable navigation β οΈ ++Important Notes++ Limitation: n8n's native Telegram node doesn't support dynamic inline keyboards, this is why need to use HTTP nodes. Solution demonstrated: Use HTTP Request node with Telegram Bot API directly
By Ruslan ElishevDetect hallucinations using specialised Ollama model bespoke-minicheck
Fact-Checking Workflow Documentation Overview This workflow is designed for automated fact-checking of texts. It uses AI models to compare a given text with a list of facts and identify potential discrepancies or hallucinations. Components Input The workflow can be initiated in two ways: a) Manually via the "When clicking 'Test workflow'" trigger b) By calling from another workflow via the "When Executed by Another Workflow" trigger Required inputs: facts: A list of verified facts text: The text to be checked Text Preparation The "Code" node splits the input text into individual sentences Takes into account date specifications and list elements Fact Checking Each sentence is individually compared with the given facts Uses the "bespoke-minicheck" Ollama model for verification The model responds with "Yes" or "No" for each sentence Filtering and Aggregation Sentences marked as "No" (not fact-based) are filtered The filtered results are aggregated Summary A larger language model (Qwen2.5) creates a summary of the results The summary contains: Number of incorrect factual statements List of incorrect statements Final assessment of the article's accuracy Usage Ensure the "bespoke-minicheck" model is installed in Ollama (ollama pull bespoke-minicheck) Prepare a list of verified facts Enter the text to be checked Start the workflow The results are output as a structured summary Notes The workflow ignores small talk and focuses on verifiable factual statements Accuracy depends on the quality of the provided facts and the performance of the AI models Customization Options The summarization function can be adjusted or removed to return only the raw data of the issues found The AI models used can be exchanged if needed This workflow provides an efficient method for automated fact-checking and can be easily integrated into larger systems or editorial workflows.
By Guido ZockollSend Telegram notification for new WooCommerce orders
π§ How it works: β’ The workflow triggers when a new order is created in WooCommerce. β’ It extracts order details including ID, status, total, and products list. β’ Sends a formatted message via Telegram to the store admin. β’ Includes a clickable button that links directly to the order view page. βοΈ Set up steps: β’ Estimated setup time: 5β10 minutes. β’ Requires active WooCommerce REST API credentials. β’ Requires a Telegram bot and your admin chat ID. β’ Replace the Telegram chatId and WooCommerce credentials in the workflow. β’ Make sure your WooCommerce site allows external API access.
By Mohammadreza azariFind high-intent sales leads by scraping Glassdoor with Bright Data & GPT
π Scrape Glassdoor with Bright Data Designed for sales teams, recruiters, and marketers aiming to automate job discovery and prospecting. This workflow scrapes Glassdoor job listings using Bright Data and automatically generates targeted pitches using AI, streamlining lead identification and outreach. --- 𧩠How It Works This automation leverages n8n, Bright Data, Google Sheets, and OpenAI: Trigger Starts with a custom form input (Location, Keyword, Country). Bright Data Job Scrape Triggers a Bright Data dataset snapshot via HTTP Request. Polls snapshot progress using a Wait node, ensuring data readiness. Retrieves full job listings dataset once ready. Google Sheets Integration Writes detailed job data (company, role, location, overview, metrics) into a Google Sheet. Uses a pre-built template for organized data storage. Automated Pitch Generation (AI) Splits listings into actionable parts: company name, title, and description. Sends data to OpenAI (via LangChain) to generate relevant pitches or icebreakers. Saves generated content back into the same sheet for easy access. --- β Requirements Ensure you have the following: Google Sheets Google account Template Sheet with columns for job details and AI-generated pitches Bright Data Active account with Dataset API access API key and dataset ID OpenAI Valid OpenAI API key for GPT models n8n Environment Nodes: HTTP Request, Wait, If, Google Sheets, Split Out, LangChain (OpenAI) Credentials: Google Sheets OAuth2 Bright Data API credentials OpenAI API key --- βοΈ Setup Instructions Step 1: Prepare Google Sheets Copy the provided Google Sheets template Do not change headers Step 2: Import & Configure Workflow in n8n Import the workflow JSON file Set Google Sheets node: Link to your copied sheet Confirm correct tab name Step 3: Configure Bright Data Replace <YOURBRIGHTDATAAPIKEY> with your real key Set your dataset ID in all HTTP Request nodes Step 4: Configure OpenAI (LangChain) Connect OpenAI API key to the LangChain node Customize prompt to match tone and outreach style Step 5: Testing & Scheduling Test via manual form trigger Schedule runs or leave form enabled for on-demand use --- π§ Tips & Best Practices Use specific keywords and locations for better results Adjust polling intervals based on dataset size Refine AI prompts regularly to improve pitch quality Clean unused columns from your sheet to boost performance --- π¬ Support & Feedback For help or customization: π§ Email: Yaron@nofluff.online πΊ YouTube: @YaronBeen π LinkedIn: linkedin.com/in/yaronbeen π Bright Data Docs: docs.brightdata.com/introduction
By Yaron BeenAutomatically collect & process Google News articles to Google Sheets
Overview This workflow automatically collects the latest articles from Google News RSS feeds, cleans and deduplicates them, and stores them neatly in a Google Sheet. It runs on a set schedule (every Monday at 09:00 by default) and helps you build a fresh pool of content ideas for newsletters, blogs, or social media. --- What you can do with it π Research faster β pull in fresh articles from multiple RSS sources without manual searching. π§Ό Clean & normalize β extract the real article URL (instead of Google redirects), keep only the title, summary, and date. π No duplicates β filter out empty or repeated entries before they ever reach your sheet. π Central storage β append all new, unique links into a Google Sheet for review or further automation. --- How it works Trigger β Cron starts the flow every Monday at 09:00 (you can change the schedule). RSS Read β Fetches articles from multiple Google News queries (e.g., βAIβ, βAI Automationβ). Merge β Combines all feed results into one list. Set (Clean URL) β Extracts the real URL, title, summary, and publication date. Filter β Ensures only items with a valid title and URL continue. Unique by URL β Removes duplicate articles across feeds. Google Sheets Append β Saves new links into your chosen Sheet for review and later use. --- Setup Instructions Import workflow into your n8n instance. Update RSS feeds: Replace the example Google News RSS URLs (AI, AI Automation) with your own queries. Format: https://news.google.com/rss/search?q=YOUR_QUERY&hl=de&gl=DE&ceid=DE:de Connect Google Sheets: Add your Google Sheets credentials. Select the documentId (the spreadsheet) and sheetName (the tab) in the Append new Links node. Recommended columns: date, title, url, summary. Adjust schedule: In the Trigger: Montag 09:00 node, change the cron expression to daily or multiple times per day if you want. Run test: Execute once manually. Check your sheet for the first rows. --- Tips & Extensions β Add more RSS Read nodes for additional sources (blogs, media outlets, niche topics). β Chain this workflow with an AI node (OpenAI/GPT) to automatically generate post ideas from the collected articles. β Notify yourself in Slack/Telegram when new articles are added. β Use a status column (Draft, Approved, Posted) to manage a simple content pipeline directly from the sheet. --- π With this template youβll never run out of content ideas β everything flows into one place, ready to inspire your next posts, newsletters, or campaigns.
By SuSReplicate line items on new deal in HubSpot and notify with Slack
Replicate Line Items on New Deal in HubSpot Workflow Use Case This workflow solves the problem of manually copying line items from one deal to another in HubSpot, reducing manual work and minimizing errors. What this workflow does Triggers upon receiving a webhook with deal IDs. Retrieves the IDs of the won and created deals. Fetches line items associated with the won deal. Extracts product SKUs from the retrieved line items. Fetches product details based on SKUs. Creates new line items for the created deal and associates them. Sends a Slack notification with success details. Step up steps Create a HubSpot Deal Workflow 1.1 Set up your trigger (ex: when deal stage = Won) 1.2 Add step : Create Record (deal) 1.3 Add Step : Send webhook. The webhook should be a Get to your n8n first trigger. Set two query parameter : dealidwon as the Record ID of the deal triggering the HubSpot Workflow dealidcreate as the Record ID of the deal created above. Click Insert Data -> The created object Set up your HubSpot App token in HubSpot -> Settings -> Integration -> Private Apps Set up your HubSpot Token integration using the predefined model. Set up your Slack connection Add an error Workflow to monitor errors
By Arnaud MARIEDocument Q&A system with OpenAI GPT, Pinecone Vector DB & Google Drive integration
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. π€ AI-Powered Document QA System using Webhook, Pinecone + OpenAI + n8n This project demonstrates how to build a Retrieval-Augmented Generation (RAG) system using n8n, and create a simple Question Answer system using Webhook to connect with User Interface (created using Lovable): π§Ύ Downloads the pdf file format documents from Google Drive (contract document, user manual, HR policy document etc...) π Converts them into vector embeddings using OpenAI π Stores and searches them in Pinecone Vector DB π¬ Allows natural language querying of contracts using AI Agents π Flow 1: Document Loading & RAG Setup This flow automates: Reading documents from a Google Drive folder Vectorizing using text-embedding-3-small Uploading vectors into Pinecone for later semantic search 𧱠Workflow Structure A [Manual Trigger] --> B[Google Drive Search] B --> C[Google Drive Download] C --> D[Pinecone Vector Store] D --> E[Default Data Loader] E --> F[Recursive Character Text Splitter] E --> G[OpenAI Embedding] πͺ Steps Manual Trigger: Kickstarts the workflow on demand for loading new documents. Google Drive Search & Download Node: Google Drive (Search: file/folder) Downloads PDF documents Apply Recursive Text Splitter: Breaks long documents into overlapping chunks Settings: Chunk Size: 1000 Chunk Overlap: 100 OpenAI Embedding Model: text-embedding-3-small Used for creating document vectors Pinecone Vector Store Host: url Index: index Batch Size: 200 Pinecone Settings: Type: Dense Region: us-east-1 Mode: Insert Documents π¬ Flow 2: Chat-Based Q&A Agent This flow enables chat-style querying of stored documents using OpenAI-powered agents with vector memory. 𧱠Workflow Diagram A[Webhook (chat message)] --> B[AI Agent] B --> C[OpenAI Chat Model] B --> D[Simple Memory] B --> E[Answer with Vector Store] E --> F[Pinecone Vector Store] F --> G[Embeddings OpenAI] πͺ Components Chat (Trigger): Receives incoming chat queries AI Agent Node Handles query flow using: Chat Model: OpenAI GPT Memory: Simple Memory Tool: Question Answer with Vector Store Pinecone Vector Store: Connected via same embedding index as Flow 1 Embeddings: Ensures document chunks are retrievable using vector similarity Response Node: Returns final AI response to user via webhook π Flow 3: UI-Based Query with Lovable This flow uses a web UI built using Lovable to query contracts directly from a form interface. π₯ Webhook Setup for Lovable Webhook Node Method: POST URL:url Response: Using 'Respond to Webhook' Node 𧱠Workflow Logic A[Webhook (Lovable Form)] --> B[AI Agent] B --> C[OpenAI Chat Model] B --> D[Simple Memory] B --> E[Answer with Vector Store] E --> F[Pinecone Vector Store] F --> G[Embeddings OpenAI] B --> H[Respond to Webhook] π‘ Lovable UI Users can submit: Full Name Email Department Freeform Query: User can enter any freeform query. Data is sent via webhook to n8n and responded with the answer from contract content. π Use Cases Contract Querying for Legal/HR teams Procurement & Vendor Agreement QA Customer Support Automation (based on terms) RAG Systems for private document knowledge βοΈ Tools & Tech Stack π Final Notes Pinecone Index: package1536 Dimension: 1536 Chunk Size: 1000, Overlap: 100 Embedding Model: text-embedding-3-small Feel free to fork the workflow or request the full JSON export. Looking forward to your suggestions and improvements!
By Mohan GopalGenerate short-form clips from YouTube videos with GPT-4o, Grok & Airtable
This n8n template demonstrates how to automate YouTube content repurposing using AI. Upload a video to Google Drive and automatically generate transcriptions, A/B testable titles, AI thumbnails, short-form clips with captions, and YouTube descriptions with chapter timestamps. Use cases include: Content creators who publish 1-2 long-form videos per week and need to extract 5-10 short-form clips, YouTube agencies managing multiple channels, or automation consultants building content systems for clients. Good to know Processing time is approximately 10-15 minutes per video depending on length Cost per video is roughly $1.00 (transcription $0.65, AI generation $0.35) YouTube captions take 10-60 minutes to generate after upload - the workflow includes automatic polling to check when captions are ready Manual steps still required: video clipping (using provided timestamps), social media posting, and YouTube A/B test setup How it works When a video is uploaded to Google Drive, the workflow automatically triggers and creates an Airtable record The video URL is sent to AssemblyAI (via Apify) for transcription with H:MM:SS.mmm timestamps GPT-4o-mini analyzes the transcript and generates 3 title variations optimized for A/B testing When you click "Generate thumbnail" in Airtable, your prompt is optimized and sent to Kie.ai's Nano Banana Pro model with 2 reference images for consistent branding After uploading to YouTube, the workflow polls YouTube's API every 5 minutes to check if auto-generated captions are ready Once captions are available, click "Generate clips" and Grok 4.1 Fast analyzes the transcript to identify 3-8 elite clips (45+ seconds each) with proper start/end boundaries and action-oriented captions GPT-4o-mini generates a YouTube description with chapter timestamps based on the transcript All outputs are saved to Airtable: titles, thumbnail, clip timestamps with captions, and description How to use Duplicate the provided Airtable base template and connect it to your n8n instance Create a Google Drive folder for uploading edited videos After activating the workflow, copy webhook URLs and paste them into Airtable button formulas and automations Upload your edited video to the designated Google Drive folder to trigger the system The workflow automatically generates titles and begins transcription Add your thumbnail prompt and 2 reference images to Airtable, then click "Generate thumbnail" Upload the video to YouTube as unlisted, paste the video ID into Airtable, and check the box to trigger clip generation Use the provided timestamps to manually clip videos in your editor Copy titles, thumbnail, clips, and description from Airtable to publish across platforms Requirements Airtable account (Pro plan recommended for automations) Google Drive for video upload monitoring Apify account for video transcription via AssemblyAI actor OpenAI API key for title and description generation (GPT-4o-mini) OpenRouter API key for clip identification (Grok 4.1 Fast) Kie.ai account for AI thumbnail generation (Nano Banana Pro model) YouTube Data API credentials for caption polling Customising this workflow Tailor the system prompts to your content niche by asking Claude to adjust them without changing the core structure Modify the clip identification criteria (length, caption style, number of clips) in the Grok prompt Adjust thumbnail generation style by updating the image prompt optimizer Add custom fields to Airtable for tracking performance metrics or additional metadata Integrate with additional platforms like TikTok or Instagram APIs for automated posting
By Jordan