by Abrar Sami
Auto-generate product comparison pages that help users buy faster This workflow creates detailed "X vs Y" product comparison pages designed to help readers make faster, more confident purchase decisions β all with zero manual writing. How it works Triggered manually or via Google Sheets row Takes two product names as input (e.g. βNotion vs Evernoteβ) Uses AI to generate: β A compelling title and meta description π Clear feature-by-feature comparison π€ Use-case-based recommendations π¬ FAQ section tailored to user pain points Saves each section into a Google Sheet for review or publishing Final output can be exported to your CMS or website builder (like Dorik, Webflow, etc.) Set up steps Youβll need OpenAI and Google Sheets credentials Takes 10β15 minutes to plug in your keys and connect the sheet Adjust prompts to match your brand tone or SEO goals π You can easily expand this to generate pricing tables, testimonials, or even localized versions using the same structure. Ideal for SaaS companies, affiliate marketers, or content teams who want to scale up comparison content β without spending hours writing.
by Alfred Nutile
How it works This workflow provides a streamlined process for uploading files to Digital Ocean Spaces, making them publicly accessible. The process happens in three main steps: User submits the form with file, in this case I needed it to upload images I use in my seo tags. File is automatically uploaded to Digital Ocean Spaces using S3-compatible storage Form completion confirmation is provided Setup steps Initial setup typically takes 5-10 minutes Configure your Digital Ocean Spaces credentials and bucket settings Test the upload functionality with a small sample file Verify public access permissions are working as expected Important notes Credentials are tricky check the screenshot above for how I set the url, bucket etc. I am just using the S3 Node Set the ACL as seen below Troubleshooting Bucket name might be incorrect Region Wrong Check Space permissions if uploads fail Verify API credentials are correctly configured You can see a video here. (live in 24 hours) https://youtu.be/pYOpy3Ntt1o
by Cameron Wills
Who is this for? Content creators, digital marketers, and social media managers who want to automate the creation of short-form videos for platforms like TikTok, YouTube Shorts, and Instagram Reels without extensive video editing skills. What problem does this workflow solve? Creating engaging short-form videos consistently is time-consuming and requires multiple tools and skills. This workflow automates the entire process from ideation to publishing, significantly reducing the manual effort needed while maintaining content quality. What this workflow does This all-in-one solution transforms ideas into fully produced short-form videos through a 5-step process: Generate video captions from ideas stored in a Google Sheet Create AI-generated images using Flux and the OpenAI API Convert images to videos using Kling's API Add voice-overs to your content with Eleven Labs Complete the video production with Creatomate by adding templates, transitions, and combining all elements The workflow handles everything from sourcing content ideas to rendering the final video, and even notifies you on Discord when videos are ready. Setup (Est. time: 20-30 minutes) Before getting started, you'll need: n8n installation (tested on version 1.81.4) OpenAI API Key (free trial credits available) PiAPI (free trial credits available) Eleven Labs (free account) Creatomate API Key (free trial credits available) Google Sheets API enabled in Google Cloud Console Google Drive API enabled in Google Cloud Console OAuth 2.0 Client ID and Client Secret from your Google Cloud Console Credentials How to customize this workflow to your needs Adjust the Google Sheet structure to include additional data like video length, duration, style, etc. Modify the prompt templates for each AI service to match your brand voice and content style Update the Creatomate template to reflect your visual branding Configure notification preferences in Discord to manage your workflow This workflow combines multiple AI technologies to create a seamless content production pipeline, saving you hours of work per video and allowing you to focus on strategy rather than production.
by Marcelo Abreu
What this workflow does Runs automatically every Monday morning at 8 AM Collects your Google Search Console from the last month and the month before that for a given url (date range is configurable) Formats the data, aggregating it by date, query, page, device and country Generates AI-driven analysis and insights on your results, providing actionable recommendations Renders the report as a visually appealing PDF with charts and tables Sends the report via Slack (you can also add email or WhatsApp) A sample for the first page of the report: Setup Guide Create an account of pdforge and use the pre-made Meta Ads template. Connect Google OAuth2 (guide on the template), OpenAI and Slack to n8n Set your site url and date range (opcional) Customize the scheduling date and time Requirements Google OAuth2 (via Google Search Console): Documentation pdforge access: Create an account AI API access (e.g. via OpenAI, Anthropic, Google or Ollama) Slack acces (via OAuth2): Documentation Feel free to contact me via Linkedin, if you have any questions! ππ»
by VEED
Generate social videos with AI avatars using VEED and Claude Overview This n8n workflow automatically generates TikTok/Reels-ready talking head videos from scratch. You provide a topic and intention, and the workflow handles everything: scriptwriting, avatar generation, voiceover creation, and video rendering. Output: Vertical (9:16) AI-generated videos with lip-synced avatars, ready for social media posting. What It Does Topic + Intention β Claude writes script β OpenAI generates avatar β OpenAI creates voiceover β VEED renders video β Saved to Google Drive + logged to Sheets Pipeline Breakdown | Step | Tool | What Happens | |------|------|--------------| | 1. Script Generation | Claude Sonnet 4 | Creates hook, script (30-45 sec), caption, and image prompt based on your topic and intention | | 2. Avatar Generation | OpenAI gpt-image-1 | Generates photorealistic portrait image (1024Γ1536) | | 3. Voiceover | OpenAI TTS-1-HD | Converts script to natural speech (Nova voice) | | 4. Video Rendering | VEED Fabric 1.0 | Lip-syncs avatar to audio, creates final video | | 5. Storage | Google Drive | Uploads final MP4 | | 6. Logging | Google Sheets | Records all metadata (script, caption, URLs, timestamps) | Required Connections API Keys (entered in Configuration node) | Service | Key Type | Where to Get | |---------|----------|--------------| | Anthropic | API Key | https://console.anthropic.com/settings/keys | | OpenAI | API Key | https://platform.openai.com/api-keys | > β οΈ OpenAI Note: gpt-image-1 requires organization verification. Go to https://platform.openai.com/settings/organization/general to verify. n8n Credentials (connect in n8n) | Node | Credential Type | Purpose | |------|-----------------|---------| | οΏ½οΏ½ Generate Video (VEED) | FAL.ai API | VEED video rendering | | οΏ½οΏ½ Upload to Drive | Google Drive OAuth2 | Store final videos | | οΏ½οΏ½ Log to Sheets | Google Sheets OAuth2 | Track all generated content | Configuration Options Edit the βοΈ Workflow Configuration node to customize. The configuration uses a JSON format: { "topic": "AI video creation tools", "intention": "informative", "brand_name": "YOUR_BRAND_NAME", "target_audience": "content creators and marketers", "trending_hashtags": "#AIvideo #ContentCreation #VideoMarketing #AItools #TikTokTips", "num_videos": 1, "anthropic_api_key": "YOUR_ANTHROPIC_API_KEY", "openai_api_key": "YOUR_OPENAI_API_KEY", "video_resolution": "720p", "video_aspect_ratio": "9:16", "custom_avatar_description": "", "custom_script": "" } Configuration Fields Explained | Field | Required | Description | |-------|----------|-------------| | topic | β | The subject of your video (e.g., "AI productivity tools") | | intention | β | Content style: informative, lead_generation, or disruption | | brand_name | β | Your brand/product name to mention | | target_audience | β | Who you're creating content for | | trending_hashtags | β | Hashtags to include in the caption | | num_videos | β | How many videos to generate (1-5 recommended) | | anthropic_api_key | β | Your Anthropic API key | | openai_api_key | β | Your OpenAI API key | | video_resolution | β | Video quality: 720p or 1080p | | video_aspect_ratio | β | Aspect ratio: 9:16 (vertical) or 16:9 (horizontal) | | custom_avatar_description | β | Optional: Describe your avatar (leave empty for AI-generated) | | custom_script | β | Optional: Your own script (leave empty for AI-generated) | Intention Types | Intention | Content Style | Best For | |-----------|---------------|----------| | informative | Educational, value-driven, builds trust | Thought leadership, tutorials | | lead_generation | Creates curiosity, soft CTA | Product awareness, funnels | | disruption | Bold, provocative, scroll-stopping | Viral potential, brand awareness | Custom Avatar & Script Options The workflow supports flexible content generation - you can let Claude generate everything, or provide your own inputs. Custom Avatar Description Leave custom_avatar_description empty to let Claude decide, or provide your own: "custom_avatar_description": "a female influencer in her 30s, with a coworking space in the background, attractive but charismatic" Examples: "a woman in her 20s with gym clothes" "a bearded man in his 30s wearing a hoodie" "a professional woman with glasses in business casual" Custom Script Leave custom_script empty to let Claude write it, or provide your own: "custom_script": "This is my custom script. VEED is a great platform for creating videos like this. You can try it too!" Guidelines for custom scripts: Keep it 30-45 seconds when read aloud Maximum ~450 characters Avoid special characters for TTS compatibility Write naturally, as if speaking Behavior Matrix | custom_avatar_description | custom_script | What Claude Generates | |---------------------------|---------------|----------------------| | Empty | Empty | Avatar + Script + Caption | | Provided | Empty | Script + Caption | | Empty | Provided | Avatar + Caption | | Provided | Provided | Caption only | Content Angles (auto-rotated) When generating multiple videos, the workflow automatically varies the approach: | # | Angle | Hook Style | |---|-------|------------| | 1 | Problem-solution | Opens with a question | | 2 | Myth-busting | Opens with controversial statement | | 3 | Quick-tip | Opens with a number/statistic | | 4 | Before-after | Opens with transformation | | 5 | Trend-commentary | Opens with news/timely angle | Output Per Video Generated | Asset | Format | Location | |-------|--------|----------| | Final Video | MP4 (720p, 9:16) | Google Drive folder | | Avatar Image | PNG (1024Γ1536) | tmpfiles.org (temporary) | | Voiceover | MP3 | tmpfiles.org (temporary) | | Metadata | Row entry | Google Sheets | Google Sheets Columns | Column | Description | |--------|-------------| | topic | Video topic | | intention | Content intention used | | brand_name | Brand mentioned | | content_theme | 2-3 word theme summary | | script_audio | Full voiceover script | | script_image | Image generation prompt | | caption | Ready-to-post TikTok caption with hashtags | | image_url | Temporary avatar image URL | | audio_url | Temporary audio URL | | video_url | Google Drive link to final video | | status | done/error | | created_at | Timestamp | Estimated Costs Per Video | Service | Usage | Approximate Cost | |---------|-------|------------------| | Claude Sonnet 4 | 2K tokens | $0.01 | | OpenAI gpt-image-1 | 1 image (1024Γ1536) | ~$0.04-0.08 | | OpenAI TTS-1-HD | 450 characters | $0.01 | | VEED/FAL.ai | 1 video render | ~$0.10-0.20 | | Total | | ~$0.15-0.30 per video | > Costs vary based on script length and current API pricing. Setup Checklist Step 1: Import Workflow [ ] Import generate-social-videos-with-ai-avatars-using-veed-and-claude.json into n8n Step 2: Configure API Keys [ ] Open the βοΈ Workflow Configuration node [ ] Replace YOUR_ANTHROPIC_API_KEY with your actual Anthropic API key [ ] Replace YOUR_OPENAI_API_KEY with your actual OpenAI API key [ ] Verify your OpenAI organization at https://platform.openai.com/settings/organization/general (required for gpt-image-1) Step 3: Connect n8n Credentials [ ] Click on οΏ½οΏ½ Generate Video (VEED) node β Add FAL.ai credential [ ] Click on οΏ½οΏ½ Upload to Drive node β Add Google Drive OAuth2 credential [ ] Click on οΏ½οΏ½ Log to Sheets node β Add Google Sheets OAuth2 credential Step 4: Configure Storage [ ] Update the οΏ½οΏ½ Upload to Drive node with your Google Drive folder URL [ ] Update the οΏ½οΏ½ Log to Sheets node with your Google Sheets URL [ ] Create column headers in your Google Sheet: topic, intention, brand_name, content_theme, script_audio, script_image, caption, image_url, audio_url, video_url, status, created_at Step 5: Customize Content [ ] Update topic, brand_name, target_audience, and trending_hashtags [ ] Optionally add custom_avatar_description and/or custom_script Step 6: Test [ ] Set num_videos: 1 for initial testing [ ] Execute the workflow [ ] Check Google Drive for the output video [ ] Verify metadata was logged to Google Sheets MCP Integration (Optional) This workflow can also be exposed to Claude Desktop via n8n's Model Context Protocol (MCP) integration, allowing you to generate videos through natural language prompts. To enable MCP: Add a Webhook Trigger node to the workflow (in addition to the Manual Trigger) Connect it to the same βοΈ Workflow Configuration node Go to Settings β Instance-level MCP β Enable the workflow Configure Claude Desktop with your n8n MCP server URL Claude Desktop Configuration (Windows): { "mcpServers": { "n8n-mcp": { "command": "supergateway", "args": [ "--streamableHttp", "https://YOUR_N8N_INSTANCE.app.n8n.cloud/mcp-server/http", "--header", "authorization:Bearer YOUR_MCP_ACCESS_TOKEN" ] } } } > Note: Install supergateway globally first: npm install -g supergateway Limitations & Notes Technical Limitations tmpfiles.org**: Temporary file URLs expire after ~1 hour. Final videos are safe in Google Drive. VEED processing**: Takes 2-5 minutes per video depending on length. n8n Cloud network**: Some external domains are blocked; workflow uses base64 for images to avoid this. Content Considerations Scripts are optimized for 30-45 seconds (TTS-friendly) Avatar images are AI-generated (not real people) Captions include hashtags automatically Each video in a batch gets a different content angle Best Practices Start small: Test with 1 video before scaling to 5 Review scripts: Claude generates good content but review before posting Monitor costs: Check API usage dashboards weekly Backup sheets: The Google Sheet serves as your content database Troubleshooting | Issue | Solution | |-------|----------| | "Organization must be verified" | Verify at platform.openai.com/settings/organization/general | | VEED authentication error | Re-add FAL.ai credential to VEED node | | Google Drive "no binary field" | Ensure Download Video outputs to field named data | | JSON parse error from Claude | Workflow has fallback content; check Claude node output | | Image URL blocked | Workflow uses base64 to avoid this; ensure gpt-image-1 model | | MCP "Server disconnected" (Windows) | Install supergateway globally: npm install -g supergateway | | MCP path error on Windows | Use supergateway directly instead of npx | Version History | Version | Date | Changes | |---------|------|---------| | 2.0 | Jan 2026 | Added custom avatar/script options, MCP integration support, improved configuration | | 1.0 | Jan 2026 | Initial release with portrait mode, gpt-image-1, native VEED node | Credits Built with: n8n** - Workflow automation Anthropic Claude** - Script generation OpenAI** - Image & audio generation VEED Fabric** - AI video rendering Google Workspace** - Storage & logging
by Usman Liaqat
Description: This n8n workflow helps you capture Slack messages via a webhook and download attached media files (like images, documents, or videos) directly from those messages. How it works: Slack Trigger (Webhook) β Listens for new messages in a Slack channel where the app is added. HTTP Request β Uses the file's private download URL to retrieve the media securely. Use cases: Download files shared by team members in a Slack channel. Capture and process media from specific project or support channels. Prepare media for later processing, archiving, or review. Requirements: Slack app with appropriate permissions (files:read, channels:history, etc.). Slack webhook set up to listen to channel messages. - Authenticated HTTP request to handle private Slack file URLs. This template is ideal for users who want full control over file handling triggered by real-time Slack messages.
by Juan Carlos Cavero Gracia
Description This n8n automation template provides an end-to-end solution for generating a series of themed images for Instagram and TikTok carousels using OpenAI's GPT Image (via the image generation API) and automatically publishing them to both platforms. It uses a sequence of prompts to create a narrative or themed carousel, generating each image based on the previous one, and then posts them with an AI-generated caption. Who Is This For? Social Media Managers:** Quickly create and schedule engaging image carousels for Instagram and TikTok. Content Creators:** Automate the visual content creation process for thematic posts or storytelling carousels. Digital Marketers:** Efficiently produce visual assets for campaigns that require sequential imagery. Small Businesses:** Generate unique promotional content for social media without needing advanced design skills. What Problem Does This Workflow Solve? Manually creating a series of related images for a carousel and then publishing them across multiple platforms can be repetitive and time-consuming. This workflow addresses these issues by: Automating Image Generation:** Uses OpenAI to generate a sequence of 5 images, where each new image is an evolution based on the previous one and a new prompt. Automating Caption Generation:** Leverages OpenAI (GPT) to create a suitable description/caption for the carousel based on the image prompts. Streamlining Multi-Platform Publishing:** Automatically uploads the generated image carousel and caption to both Instagram and TikTok. Reducing Manual Effort:** Significantly cuts down the time spent on designing individual images and manually uploading them. Ensuring Visual Cohesion:** The sequential image generation method (editing the previous image) helps maintain a consistent style or narrative across the carousel. How It Works Trigger: The workflow is initiated manually (can be adapted to a schedule or webhook). Define Prompts: Five distinct prompts are pre-set within the workflow to guide the generation of each image in the carousel. AI Caption Generation: OpenAI (GPT-4.1) generates a concise (β€ 90 characters for TikTok) description for the social media posts based on all five image prompts. Sequential AI Image Generation: Image 1: OpenAI's image generation API (specified as gpt-image-1) creates the first image based on prompt1. Image 2-5: For each subsequent image, the workflow uses the OpenAI image edits API. It takes the previously generated image and a new prompt (prompt2 for image 2, prompt3 for image 3, and so on) to create the next image in the sequence. Images are converted from base64 JSON to binary format. Content Aggregation: The five generated binary image files (named photo1 through photo5) are merged. Multi-Platform Distribution: The merged images and the AI-generated description are sent to api.upload-post.com for publishing as a carousel to Instagram. The same content is sent to api.upload-post.com for publishing as a carousel to TikTok, with an option to automatically add music. The TikTok description is truncated if it exceeds 90 characters. Setup Accounts & API Keys: You will need: An n8n instance. An OpenAI API key. An API key for upload-post.com. Configure Credentials: Add your OpenAI API key to the "OpenAI" credentials in n8n. This will be used by the "Generate Description for Tiktok and Instagram" node and the HTTP Request nodes calling the OpenAI image generation/edit APIs. In the "POST TO INSTAGRAM" and "POST TO TIKTOK" nodes, replace "Apikey add_api_key_here" with your actual upload-post.com API key. Update the user field in the "POST TO INSTAGRAM" and "POST TO TIKTOK" nodes if "upload_post" is not your user identifier for that service. Customize Prompts: Modify the five prompts (prompt1 to prompt5) in the "Set All Prompts" node to define the story or theme of your image carousel. Review Image Generation Parameters: In the "Set API Variables" node, you can adjust: size_of_image (e.g., "1024x1536" for vertical carousels). openai_image_model (ensure this matches a valid OpenAI model identifier for image generation/edits, like dall-e-2 or dall-e-3 if gpt-image-1 is a placeholder). response_format_image (should generally remain b64_json for this workflow). (Optional) TikTok Auto Music: The "POST TO TIKTOK" node has an auto_add_music parameter set to true. Change this to false if you prefer to add music manually or not at all. Requirements Accounts:** n8n, OpenAI, upload-post.com. API Keys & Credentials:** API Keys for OpenAI and https://upload-post.com. (Potentially) Paid Plans:** OpenAI and upload-post.com usage may incur costs depending on your volume and their respective pricing models. This template empowers you to automate the creation and distribution of visually consistent image carousels, saving time and enhancing your social media presence.
by phil
How it works π£οΈ> π I set up this workflow to convert any audio or video file into structured text using the new ElevenLabs Scribe model, one of the best Speech-to-Text AIs, available in 99+ languages. This workflow integrates seamlessly with n8n and leverages the ElevenLabs Scribe API to: This workflow seamlessly integrates with n8n to: β Upload audio/video files automatically β Transcribe them with industry-leading accuracy in any language β Export the text for further processing (summaries, subtitles, SEO content, etc.) π Try the new ElevenLabs Scribe model now: Convert speech to text instantly Business Cases πΉ Podcast Transcriptions β Convert podcast episodes into blog posts for SEO and accessibility πΉ YouTube Subtitles β Generate captions automatically for increased engagement πΉ Legal & Compliance β Accurately transcribe meetings, interviews, or customer calls πΉ E-learning β Turn lectures and webinars into structured course notes πΉ SEO & Content Marketing β Repurpose videos into articles, quotes, and social media content π‘ Boost your productivity with the new Scribe model β Start with ElevenLabs Scribe Set up steps π Quick & simple setup in n8n β Upload your file, select the model (scribe_v1), and let the AI handle the rest via the ElevenLabs API. βΈ» π’ Why I Chose the New ElevenLabs Scribe Model? I wanted the most accurate and reliable transcription tool for my workflow. After testing different options, Scribe outperformed Google Gemini & OpenAI Whisper in independent benchmarks. It delivers high-quality transcriptions, even in underserved languages like Serbian, Mongolian, and many more. β Transcribes in 99+ languages β Fast, accurate, and easy to integrate β Suitable for content creators, businesses, and professionals π Get started now and revolutionize your workflow with the new Scribe model β Try Scribe AI today π Phil | Inforeole
by Gede Suparsa
This template demonstrates how to provide an interactive chatbot for your work history based off your CV. Unanswered questions and follow-up email contacts are sent to you via Telegram. Use case: link on your profile to not only show off you AI workflow skills but also to provide an interactive chatbot about your work history for prospective employers. Good to Know It will require access to an OpenAI API Key (free for low usage) and setting up a bot in Telegram (free). How it Works The n8n inbuilt chat node will be hosted on n8n services to provide the chat interface. You will upload your CV either exported from LinkedIn or exported yourself to Microsoft OneDrive along with a simple text file explaining some other information about you. On each chat interaction the PDF and text file are used as tools to get context information for the chatbot to respond. If a question cannot be answered reliably, a subworkflow will be called to capture that question and send it to you as a telegram message. If the person chatting supplies their email address, this will be sent to you via a Telegram message along with other information the user provides. How to use After importing the template, create the subworkflows so that they can be used a Tools by the AI Node. Don't forget to add the Execute sub-workflow trigger. Setup credentials for Open AI, OneDrive and telegram. Upload your CV & text file summary to OneDrive and replace the document IDs in the get_documents sub-workflow. Activate the workflow so that publicly available chat will get generated on n8n.
by Madame AI
Generate visual resumes from Telegram inputs using Google Gemini This workflow transforms text-based resume data into visually stunning images by leveraging Google Gemini's reasoning and vision capabilities. It autonomously analyzes the candidate's profile, selects an appropriate design template based on their industry, and renders a high-quality resume image directly in Telegram. Target Audience Job seekers, career coaches, resume writers, and recruitment agencies looking to automate design generation. How it works Classify Input: The workflow starts with a Telegram trigger. A Google Gemini agent analyzes the incoming message to determine if it is a casual chat or a resume generation request. Fetch Context: If it is a resume request, a BrowserAct node triggers a workflow (using the "AI Resume Replicant" template) to fetch necessary external context or data. Ingest Designs (Optional): If a reference image is provided, CloudConvert standardizes the file, and Google Gemini Vision reverse-engineers the layout and style, saving the "Visual DNA" to Google Sheets. Draft Blueprint: The "Resume Writer" AI agent selects a stored design template that matches the candidate's industry (e.g., "Corporate" for Finance, "Creative" for Design) and maps the text content to the layout. Generate Prompt: A "Visualizer" AI agent converts the structured blueprint into a highly detailed natural language prompt for image generation. Render & Deliver: Google Gemini generates the final resume image, which is then sent back to the user via Telegram. How to set up Configure Credentials: Connect your Telegram, Google Gemini, Google Sheets, CloudConvert, and BrowserAct accounts in n8n. Prepare BrowserAct: Ensure the AI Resume Replicant template is saved in your BrowserAct account. Setup Google Sheet: Create a new Google Sheet with the required header (listed below). Connect Sheet: Open the Google Sheets nodes (Clear, Get, Append) and select your new spreadsheet. Configure Telegram: Ensure your Telegram Bot is connected to the Trigger and Message nodes. Google Sheet Headers To use this workflow, create a Google Sheet with the following header: Resume Details Requirements BrowserAct* account (Template: *AI Resume Replicant**). Google Gemini** account. Telegram** account (Bot Token). CloudConvert** account. Google Sheets** account. How to customize the workflow Refine Design Logic: Modify the system prompt in the "Resume Writer" agent to change how the AI matches industries to design styles (e.g., force specific colors for specific roles). Change Output Format: Replace the Telegram response node with a Google Drive node to save the generated images as PDF or PNG files instead of sending them. Switch Image Model: Update the "Generate an image" node to use a different image generation model if preferred (e.g., OpenAI DALL-E). Need Help? How to Find Your BrowserAct API Key & Workflow ID How to Connect n8n to BrowserAct How to Use & Customize BrowserAct Templates Workflow Guidance and Showcase Video I Built a Resume Bot that CLONES Any Template! π€ (BrowserAct + n8n + Gemini Tutorial)
by Dr. Firas
Quick overview This workflow pulls blog topic ideas from Google Sheets, researches each topic with Perplexity, generates an SEO-ready HTML article plus metadata with OpenAI GPT-5, then creates a WordPress draft and attaches a DALLΒ·E cover image as the featured image. How it works Starts when you manually run the workflow. Reads a content idea (from the PROMPT column) from a Google Sheets content plan. Uses Perplexity to research the topic with a defined recency window and returns bullet-point findings. Uses OpenAI GPT-5 to write a structured output containing an SEO title, meta description, slug, and the full article body formatted as HTML. Creates a new WordPress post using the generated title, slug, and HTML content with the configured post status. Generates a photorealistic cover image with OpenAI DALLΒ·E, uploads it to the WordPress media library, and sets it as the postβs featured image. Updates the original Google Sheets row to record publishing details such as the WordPress post ID. Setup Create a Google Sheet (for example with columns like PROMPT, TITLE, and ID POST) and select the target spreadsheet and sheet/tab in both Google Sheets nodes. Add credentials for Google Sheets OAuth2, Perplexity, OpenAI (for GPT-5 text and DALLΒ·E image generation), and WordPress (REST API access, typically via an application password). Update the Configuration values, especially wordpress_site_url, wordpress_post_status, language, word-count limits, and the Perplexity search recency. Ensure your WordPress site allows REST API media uploads and that the WordPress credential has permission to create posts and upload media. Additional info Generate SEO content with Perplexity and GPT-5 for WordPress π₯ Open full documentation on Notion Need help customizing? Contact me for consulting and support : Linkedin MY NEW YOUTUBE CHANNEL π Subscribe to my new YouTube channel. Here I'll share videos and Shorts with practical tutorials and FREE templates for n8n.
by Bilel Aroua
Quick Overview This workflow turns a single car photo sent to a Telegram bot into an AI-directed campaign, generating hero frames with OpenAI GPT Image 2, optionally animating them into a short film with fal.ai LTX 2.3, and publishing or scheduling the result via Postoria while logging sessions and posts in n8n Data Tables. How it works Triggers when a Telegram message arrives, asks for a photo if none is attached, and pre-fills a creative brief from the photo caption or the last saved session. Collects the campaign objective, aspect ratio, film length, tone, and language via a Telegram form, then uploads the source image to ImgBB to get a public URL. Compiles a production spec (including render sizes, beat plan, negative prompt, and cost estimate), opens a session row in an n8n Data Table, and uses an OpenAI (LangChain) multi-agent director to generate a structured campaign blueprint. Sends the blueprint to Telegram for approval, optionally captures adjustment notes, and then generates one OpenAI GPT Image 2 edited hero frame per beat and presents them for review. If frames are approved, renders one 5-second beat video per frame with fal.ai LTX 2.3 (with native audio), stitches successful beats into a single film using fal.ai FFmpeg Compose, and sends the finished video back to Telegram. Opens a Telegram distribution console, imports the chosen asset (film or a selected still) into Postoria, publishes immediately or schedules it, and records session and post outcomes in n8n Data Tables. Runs daily on a schedule to pull recent Postoria posts plus session logs, has OpenAI summarize throughput and bottlenecks, and sends an ops digest to a configured Telegram chat. Setup Create the n8n Data Tables named car_os_sessions and car_os_posts with the expected columns so the session and post logging steps can read and update rows. Add credentials for Telegram (bot token), OpenAI (API key for the GPT-5.x chat models used by the agents), Postoria (API key), ImgBB (API key via query auth), and fal.ai (HTTP Custom Auth header with your key). In the configuration nodes, set your studio details (e.g. studio_name, brand_link, quality/pricing fields), and set ops_chat_id for the daily report destination. Connect your social accounts inside Postoria and (if your Postoria API key has multiple workspaces) set the preferred workspace name in both workspace-picking code steps. Ensure your n8n instance is reachable over public HTTPS so Telegram βsend and waitβ approvals can resume via webhook callbacks.