by samxck
Quick overview This workflow turns Feishu bot messages into a human-in-the-loop short-video production pipeline, using Tavily for web search, DeepSeek for topic and script generation, Jimeng AI for text-to-video, and Blotato to publish the approved video to TikTok, Instagram, and YouTube Shorts. How it works Receives a Feishu bot event via webhook, immediately returns the Feishu challenge or an “ok” response, and continues processing asynchronously. Parses the incoming message to extract the user and chat identifiers, detects commands (for example “确认选题”, “通过”, “修改”, “满意”), and looks up the user’s current state in a Feishu Bitable table. For topic exploration messages, runs a Tavily web search, sends the search context plus conversation history to DeepSeek to generate topic options, replies in Feishu, and appends the dialog back to Bitable. When the user confirms a topic, calls DeepSeek to generate a structured short-video script, posts the script to Feishu for review, and saves the confirmed topic and script to Bitable with the state set to script review. When the user requests changes, uses DeepSeek to either revise the existing script based on feedback or fully rewrite it, then re-sends the updated script to Feishu and keeps the workflow in script review. When the user approves the script, converts the script into a Jimeng-friendly prompt with DeepSeek, submits a Jimeng text-to-video generation task, notifies the user in Feishu, waits, queries Jimeng for the video URL, and sends a preview card while saving the video URL and state to Bitable. When the user approves the video, uploads the video to Blotato and publishes it to TikTok, Instagram, and YouTube via Blotato, then sends a completion message in Feishu and marks the session as published in Bitable. Setup Create and configure a Feishu self-built app with a bot, enable event subscriptions for im.message.receive_v1, grant the required messaging permissions, and set the n8n production webhook URL as the event callback. Create a Feishu Bitable base and table with the required fields (user_id, state, topic, script, video_url, jimeng_task_id, updated_at) and copy the appToken and tableId into the workflow. Add API credentials in the global configuration: DeepSeek API key, Tavily API key, Jimeng API key, and Blotato API key, plus your Feishu app_id and app_secret. In Blotato, connect your TikTok, Instagram, and YouTube accounts, copy their Account IDs, and fill them into the workflow’s Blotato account ID configuration. Ensure n8n is reachable from the public internet (for example via a reverse proxy or ngrok) so Feishu can deliver webhook events.
by Liveblocks
Modify Liveblocks Storage with JSON Patch This example uses Liveblocks Storage, a sync engine created by Liveblocks that allows you to create collaborative applications like Figma, Pitch, and Spline. When we fetch the Storage value for a room, we're fetching the state of the multiplayer document which users are collaborating on. In this workflow example, our document holds a list of shapes, like a drawing tool. Here's a rectangle, for example: { "id": "rect-1", "type": "rectangle", "x": 100, "y": 150, "width": 200, "height": 100, "color": "#ff0000" } Picture this hooked up to a design tool like Figma, with the user asking AI to edit their document. In these nodes, to generates a JSON Patch operation from the user's request ("Add a blue circle, and make the square orange") and applies it to the collaborative document. As soon as the JSON Patch operation has run, each user's design tool in their web browser will update with the changes in real time. Additionally, we're setting presence in the room, which means that the AI will appear in the document's live avatar stacks while it works, before disappearing shortly after.
by Sina
Complete SEO/GEO Blog Generation Pipeline: Research → Write 4000+ Words → Add Images → Publish (Wordpress + Other CMS) → Index on Google How it works This workflow runs two parallel flows that together create a fully hands-off SEO content pipeline, from topic selection to Google indexing. (Each blog typically takes around ~15 minutes to generate. The system runs multiple deep processing steps to ensure high-quality, human-like output instead of fast but low-quality AI content. It’s designed to reflect a production-grade SEO system, combining structured reasoning, multi-step validation, and quality control to match modern Google standards like E-E-A-T.) Flow 1 — Daily Scheduled Generation: Runs automatically every day on a schedule Fetches AI-suggested blog topics based on your website's niche and existing content Picks the best topic and sends it to the Siah AI Engine (18 specialized agents) Generates a 4000+ word, SEO-optimized article with keyword research, E-E-A-T compliance, AI images, internal links, slug, and metadata Publishes the finished post directly to your CMS (This approach focuses on depth, structure, and quality (not just text generation), making it one of the most complete blog automation systems currently aligned with modern SEO and Google ranking expectations.) Flow 2 — Webhook-Triggered Google Indexing: Fires automatically the moment a blog is published Submits the new URL to the Google Indexing API instantly No waiting for Googlebot to crawl, your post enters the index immediately Set up steps Setup takes under 5 minutes: Create a free account at seosiah.com and grab your API token from the dashboard Paste your token into the HTTP Request nodes (clearly labeled inside the workflow) In the "Add your website URL" node, enter your site URL Set your preferred publish time in the Schedule Trigger Activate — the workflow runs fully on its own from here
by Gloria
Premium n8n Workflow: SMART AI Keyword Categorization & Content Strategy This n8n workflow transforms raw keyword data into actionable content intelligence using advanced AI categorization and clustering. It creates a comprehensive content strategy with ready-to-use titles and descriptions for your blog posts. 🚀 Features 🧠 AI-Powered Categorization Automatically sorts keywords into strategic buckets — Quick Wins, Authority Builders, Emerging Topics, Intent Signals, and Semantic Topics — for targeted content creation 🎯. 🔗 Semantic Clustering Identifies meaningful relationships between keywords to create logically grouped content clusters 🕸️. 📑 Content Blueprint Generation Creates compelling titles and descriptions for each keyword and cluster to streamline your content creation process 📝. 🌐 Hub & Spoke Strategy Builder Develops a complete site architecture plan with main hub articles and supporting spoke content 🏗️. ⚡ Airtable Integration Organizes all outputs in a structured database for seamless integration with your content workflow. 🤖 n8n AI Agents Leverages advanced AI capabilities to analyze keyword intent and potential without manual intervention. 👥 This Workflow is Perfect For: Content strategists 📊 SEO professionals 🔍 Content marketing teams 👥 Blog managers 💻 Digital publishers 📰 Website owners (E-Commerce) 🏢 Anyone using the SMART AI Keyword Research Workflow 🔄 Stop struggling with manual keyword grouping and transform your raw keyword data into a comprehensive content strategy. 👉 Get this premium workflow today! 📝 What's Included? ⚙️ n8n Workflow Template Ready-to-use workflow with AI-powered nodes for keyword analysis and categorization. 📊 Airtable Database Structure Pre-configured tables for categorized keywords, content ideas, and hub-spoke relationships. 🧩 Keyword Categorization System Automated logic to sort keywords by opportunity, competition, and relevance. 📋 Content Titles and Descriptions AI prompts to create optimized titles and descriptions for each content piece. 🌐 Hub & Spoke Mapper Logic to identify main topics and supporting content opportunities. 📚 Documentation Step-by-step instructions for importing keyword data and running the workflow. 🏆 Why Choose This Workflow? ⏱️ Save Massive Time: Automate what would take days of manual analysis and planning. 📈 Improve Content ROI: Create content that targets the right keywords in the right way. 🔄 Seamless Integration: Works perfectly with the AI Keyword Research and Blog Writing workflows available on my profile. 🏗️ Build Site Authority: Create topically relevant content clusters that boost domain expertise. 🎯 Strategic Focus: Stop guessing which keywords to target and how to organize your content. 🛠️ How It Works 1️⃣ Import the provided n8n workflow into your n8n instance 📥. 2️⃣ Connect to your Airtable base containing keyword research data ⚙️. 3️⃣ Configure the AI agents with your preferred content parameters 🤖. 4️⃣ Run the workflow to automatically categorize, cluster, and create content briefs 🔄. 5️⃣ Use the generated content strategy to guide your blogging or feed directly into the Multi-Agent Blog Writing System available on my profile 📝. Additional detailed instructions are provided in the workflow. 🏁 What You Need to Get Started 🔹 Access to n8n (self-hosted or cloud) ☁️ 🔹 An Airtable account with keyword data (ideally from the AI Keyword Research Workflow on my profile) 📊 🔹 OpenAI API credentials for the AI categorization and title generation 🔑 🔹 Basic understanding of content strategy and n8n workflows 🧠 💡 You can also connect this workflow with my SEO Keyword Research Automation using DataForSEO and Airtable and my Multi-Agent SEO Optimized Blog Writing System with Hyperlinks for E-Commerce, both available on my profile, to build a fully automated, end-to-end SEO content machine.
by Harshil Agrawal
This workflow allows you to create a group, add members to the group, and get the members of the group. Bitwarden node: This node will create a new group called documentation in Bitwarden. Bitwarden1 node: This node will get all the members from Bitwarden. Bitwarden2 node: This node will update all the members in the group that we created earlier. Bitwarden3 node: This node will get all the members in the group that we created earlier.
by PDF Vector
Overview Conducting comprehensive literature reviews is one of the most time-consuming aspects of academic research. This workflow revolutionizes the process by automating literature search, paper analysis, and review generation across multiple academic databases. It handles both digital papers and scanned documents (PDFs, JPGs, PNGs), using OCR technology for older publications or image-based content. What You Can Do Automate searches across multiple academic databases simultaneously Analyze and rank papers by relevance, citations, and impact Generate comprehensive literature reviews with proper citations Process both digital and scanned documents with OCR Identify research gaps and emerging trends systematically Who It's For Researchers, graduate students, academic institutions, literature review teams, and academic writers who need to conduct comprehensive literature reviews efficiently while maintaining high quality and thoroughness. The Problem It Solves Manual literature reviews are extremely time-consuming and often miss relevant papers across different databases. Researchers struggle to synthesize large volumes of academic papers, track citations properly, and identify research gaps systematically. This template automates the entire process from search to synthesis, ensuring comprehensive coverage and proper citation management. Setup Instructions: Configure PDF Vector API credentials with academic search access Set up search parameters including databases and date ranges Define inclusion and exclusion criteria for paper selection Choose citation style (APA, MLA, Chicago, etc.) Configure output format preferences Set up reference management software integration if needed Define research topic and keywords for search Key Features: Simultaneous search across PubMed, arXiv, Semantic Scholar, and other databases Intelligent paper ranking based on citation count, recency, and relevance OCR support for scanned documents and older publications Automatic extraction of methodologies, findings, and limitations Citation network analysis to identify seminal works Automatic theme organization and research gap identification Multiple citation format support (APA, MLA, Chicago) Quality scoring based on journal impact factors Customization Options: Configure search parameters for specific research domains Set up automated searches for ongoing literature monitoring Integrate with reference management software (Zotero, Mendeley) Customize output format and structure Add collaborative review features for research teams Set up quality filters based on journal rankings Configure notification systems for new relevant papers Implementation Details: The workflow uses advanced algorithms to search multiple academic databases simultaneously, ranking papers by relevance and impact. It processes full-text PDFs when available and uses OCR for scanned documents. The system automatically extracts key information, organizes findings by themes, and generates structured literature reviews with proper citations and reference management. Note: This workflow uses the PDF Vector community node. Make sure to install it from the n8n community nodes collection before using this template.
by PDF Vector
Overview HR departments and recruiters spend countless hours manually reviewing resumes, often missing qualified candidates due to time constraints. This workflow automates the entire resume screening process by extracting structured data from resumes in any format (PDF, Word documents, or even photographed/scanned resume images), calculating experience scores, and creating comprehensive candidate profiles ready for your ATS system. What You Can Do This workflow automatically retrieves resumes from Google Drive and uses AI to extract all relevant candidate information including personal details, work experience with dates, education, skills, and certifications. It intelligently handles various resume formats including PDFs, Word documents, and even scanned or photographed resumes using OCR. The workflow calculates total years of experience, tracks skill-specific experience, generates proficiency scores for each skill, and provides an AI-powered assessment of candidate strengths and suitability for different roles. Who It's For Perfect for HR departments processing high volumes of applications, recruitment agencies managing multiple clients, talent acquisition teams seeking to improve candidate quality, and hiring managers who want data-driven insights for decision making. Ideal for organizations that need to maintain consistent evaluation standards across different reviewers and want to reduce time-to-hire while improving candidate match quality. The Problem It Solves Manual resume screening is inefficient and inconsistent. Different reviewers may evaluate the same resume differently, leading to missed opportunities and bias. This workflow standardizes the extraction process, automatically calculates years of experience for each skill, and provides objective scoring metrics to help identify the best candidates faster while reducing human bias in the initial screening process. Setup Instructions Configure Google Drive credentials in n8n Install the PDF Vector community node from the n8n marketplace Configure your PDF Vector API credentials Set up your preferred data storage (database or spreadsheet) Customize the skill categories for your industry Configure the scoring algorithm based on your requirements Connect to your existing ATS system if needed Key Features Automatic Resume Retrieval**: Pull resumes from Google Drive folders automatically Universal Format Support**: Process PDFs, Word documents, and photographed resumes OCR Capabilities**: Extract text from scanned or photographed documents Experience Calculation**: Automatically compute total and skill-specific experience Proficiency Scoring**: Generate objective skill proficiency ratings AI Assessment**: Get intelligent insights on candidate fit and strengths Multi-Language Support**: Handle resumes in various languages ATS Integration**: Output structured data compatible with major ATS systems Customization Options Define custom skill categories relevant to your industry, adjust scoring weights for different experience types, add specific extraction fields for your organization, implement keyword matching for job requirements, set up automated candidate ranking systems, create role-specific evaluation criteria, and integrate with LinkedIn or other professional networks for enhanced candidate insights. Note: This workflow uses the PDF Vector community node. Make sure to install it from the n8n community nodes collection before using this template.
by Paul Roussel
Automated workflow to remove video backgrounds and composite foreground video on static image backgrounds. Perfect for creating branded content, professional presentations, and consistent visual branding across your videos. How it works • Upload inputs: Provide foreground video URL and background image URL (both must be publicly accessible) • Remove background: API automatically removes video background with AI-powered segmentation • Composite on image: Video is centered on custom image background with aspect ratio preserved • Save to Drive: Final composed video is automatically uploaded to Google Drive with shareable link Set up steps ⏱️ Total setup time: ~7 minutes • Get VideoBGRemover API Key (~2 min): Visit https://videobgremover.com/api-management, sign up, and copy your API key • Add API key to n8n (~2 min): Go to Settings → Variables, add VIDEOBGREMOVER_KEY with your API key as value. Find the api key -> https://videobgremover.com/n8n • Connect Google Drive (~2 min): Click "Upload to Google Drive" node, click "Connect", and authorize n8n • Test workflow (~1 min): Use manual trigger with sample URLs provided in the "Sample URLs (Edit Here)" node Use cases: Branded content with company backgrounds and logos Product demos with custom imagery or brand colors AI avatars on professional office/studio backgrounds Social media content requiring consistent visual branding Profile videos with custom scenes or patterns Presentation videos with company branding Pricing: VideoBGRemover API charges $0.50-$2.00 per minute of video processed. Free trial credits available. Triggers: Webhook (for automation) or Manual (for testing) Processing time: Typically 3-5 minutes per minute of video
by Zvid
Quick overview This workflow runs manually or on an optional daily schedule, finds active Shopify products without usable video, creates branded vertical videos with Zvid, and either returns editor or render review links or uploads completed MP4s to the matching products through Shopify’s staged-upload flow. How it works Starts manually or, after the workflow is activated, every day at 6:00 AM in the workflow’s configured n8n timezone. Queries the Shopify Admin GraphQL API using shopifyProductQuery, scans up to scanLimit products, and selects up to maxProducts products that have a public image, a priced variant, and no non-failed Shopify video. Builds a Zvid bulk render project by mapping Shopify product titles, prices, images, descriptions, sizes, and brand styling into a shared video template. Validates the first item against Zvid’s API to confirm the template resolves correctly and to calculate the credit cost for the batch. If dry-run mode is enabled, saves the first resolved video as a draft in the Zvid editor and outputs a summary with an editor link and the full credit quote. With dryRun disabled, submits a Zvid bulk render and checks the batch every pollSeconds until completion or timeoutMinutes. If n8n times out, the render continues in Zvid and should be checked before rerunning. If publishing is enabled, stages each MP4 upload to Shopify, uploads the file, attaches the staged video to the product via Shopify GraphQL, and tags the product as processed; otherwise it outputs the rendered video URLs for review. Setup In Shopify’s Dev Dashboard, create and install an app for your store. Create an app version with read_products, write_products, and write_files, release the version, then copy the Client ID and Client secret from Settings. Exchange them at POST https://{shop}.myshopify.com/admin/oauth/access_token using grant_type=client_credentials. Store the returned access_token—not the Client ID or secret—in an n8n Header Auth credential named X-Shopify-Access-Token, then assign it to the four Shopify HTTP Request nodes. Create a Zvid API key at https://app.zvid.io/api-keys. Store it in an n8n Header Auth credential with the header name x-api-key, then assign it to Validate project (free), Save draft to editor, Submit bulk render, and Get batch status. Update the Config values for shopDomain, shopifyApiVersion, shopifyProductQuery, processedTag, maxProducts/scanLimit, and your brand copy and styling (colors, fonts, timings, and resolution). Run once with dryRun set to true to review the editor draft and credit quote, then set dryRun to false to render. Keep publishToShopify set to false until you are ready for the workflow to upload and attach videos to Shopify products and add the processed tag. Requirements A Shopify store where you can create and install a Dev Dashboard app. Shopify Admin API scopes: read_products, write_products, and write_files. Active Shopify products with at least one public image and one priced variant. A Zvid account and API key; render credits are required only after disabling dry-run mode. n8n Cloud or self-hosted n8n. No community nodes are required. Customization Change shopifyProductQuery, scanLimit, maxProducts, and processedTag to control product selection. Customize the brand name, website, copy, colors, fonts, music, scene durations, frame rate, and video resolution in Config. Adjust the Schedule Trigger and n8n workflow timezone. Adapt the product copy and visual mapping for categories other than apparel. Keep publishToShopify disabled to return review links without modifying Shopify. Additional info Start with dryRun: true. Validation, the credit quote, and the editor preview do not start a render. Set dryRun: false only after reviewing the draft and expected credit cost. Keep publishToShopify: false until the rendered videos are approved. Shopify Dev Dashboard access tokens obtained with client credentials expire after approximately 24 hours. Refresh the n8n Header Auth token before scheduled runs or add an automatic token-refresh step. HTTP Request nodes are used because the standard n8n Shopify node does not expose the complete GraphQL staged-upload and product-media association sequence required by this workflow. Products are tagged only after Shopify accepts their video association.
by Bilel Aroua
Sora 2 Video Generator - No Watermark (Minimal Setup) This n8n workflow enables you to generate professional AI videos using OpenAI's Sora 2 without watermarks. Create videos from text descriptions or animate your images with a simple web form interface - ready to use in just 5 minutes! Generate cinematic AI videos for social media, marketing campaigns, product demos, or creative projects. The workflow handles both text-to-video and image-to-video generation with automatic status polling until your video is ready. Good to know: • Kie.AI charges per video generation. Check their pricing page for current rates • Videos typically take 30-60 seconds for standard quality, 60-120 seconds for HD • The workflow automatically retries status checks every 30 seconds until completion • No watermarks on output videos How it works • Users submit video requests via a beautiful web form with description, aspect ratio, and quality options • The workflow detects if an image was uploaded and routes to either text-to-video or image-to-video • For image uploads, the file is automatically uploaded to ImgBB to generate a public URL • The request is sent to Sora 2 API via Kie.AI with your specifications (prompt, quality, aspect ratio) • The workflow waits 30 seconds, then checks if video generation is complete • If not ready, it automatically loops back and checks again every 30 seconds • Once complete, the video is downloaded and optionally sent via Telegram notification • Clean, watermark-free MP4 video output ready for use Set up steps Step 1: Get Kie.AI API Key • Sign up at kie.ai and navigate to your dashboard • Go to API Keys section and generate a new key • Copy the API key for the next step Step 2: Configure n8n Credentials • In n8n, go to Credentials → New Credential • Select "HTTP Header Auth" • Name: Kie Ai(Veo and more) (exact name required) • Header Name: Authorization • Header Value: Bearer YOUR_API_KEY • Save the credential Step 3: ImgBB Setup (for Image-to-Video) • Get a free API key from api.imgbb.com • Open the "Upload to ImgBB" node in the workflow • Replace the YOUR_ImgBB_API_KEY parameter with your ImgBB API key Step 4: (Optional) Telegram Notifications • Create a bot with @BotFather on Telegram • Get your Chat ID from @get_id_bot • Update YOUR_CHAT_ID in both Telegram nodes • Or delete Telegram nodes entirely if not needed Requirements • Kie.AI account with API access for Sora 2 • ImgBB account for image hosting (free tier available) • (Optional) Telegram bot for video delivery notifications Customising this workflow • Adjust wait times in the Wait nodes if generation takes longer in your region • Add email notifications instead of/in addition to Telegram • Modify the form to collect additional metadata (user info, project names, etc.) • Add error handling nodes for production deployments • Connect to cloud storage (Google Drive, Dropbox) instead of Telegram for video delivery • Integrate with your existing CMS or content management system For assistance and support: contact@bilsimaging.com
by Ops Department
Quick overview This workflow exposes an OpenAI-compatible /v1/chat/completions endpoint in n8n that forwards requests (including optional file attachments) to a configurable LLM HTTP provider, supporting both synchronous replies and asynchronous processing via a callback URL. How it works Receives a POST request on /v1/chat/completions via a webhook, accepting JSON or multipart form-data with optional binary file uploads. Converts any uploaded files into OpenAI-style message content (images as image_url data URLs and other files as text entries) and merges them into the last user message. Prepares a job ID, extracts optional callback and provider override settings (URL and headers), and keeps the original request body for later use. If a callback URL is provided, immediately returns HTTP 202 with the job ID, then sends the request (without callback/provider fields) to the configured LLM provider endpoint. Formats the provider response (or error) into a completion payload with a status code and posts the result to the callback URL with job metadata. If no callback URL is provided, sends the request to the LLM provider synchronously and returns the provider response (or error) to the original caller with the same HTTP status code. Setup Deploy this workflow and copy the production webhook URL for /v1/chat/completions to use as your OpenAI-compatible endpoint in your client or application. Configure the upstream LLM provider URL and any required authorization headers (either by sending them in the request body under provider.url/provider.headers or by using the default Google Generative Language OpenAI-compatible endpoint and supplying its auth header). If you want asynchronous mode, provide a reachable callback.url (and optional callback.method and callback.headers) that can accept the completion payload posted by this workflow. If you plan to send attachments, ensure your client can send multipart form-data with a JSON body field plus additional file fields so the workflow can convert them into message content.
by Harshil Agrawal
This workflow allows you to create an invoice with the information received via Typeform submission. Typeform node: This node triggers the workflow. Whenever the form is submitted, the node triggers the workflow. We will use the information received in this node to generate the invoice. APITemplate.io node: This node generates the invoice using the information from the previous node.