Workflow Templates

. Read and store IOT sensor data with the MQTT Trigger and InfluxDB tonyduffy@protonmail.com This workflow is for users wanting a practical example of how to obtain data from remote IOT systems using the MQTT protocol in an n8n environment. The template provides typical n8n node implementation and configuration settings necessary to read and store IOT data. The workflow reads the temperature and humidity data from a remote IOT system in this case a DHT22 sensor connected to a ESP32 micro controller. The data is parsed into the correct JSON format and then ingested in an InfluxDB data bucket. From there the stored temperature and humidity values can be displayed in real time. The workflow can be easily modified to read any MQTT driven device data. Remote IOT Sensor Setup The ESP32 controller with the DHT22 sensor are running on a Wokwi simulator. The simulator uses micro python to publish a MQTT "wokwi-weather" topic with the temperature and humidity payloads to an online Mosquitto MQTT broker. The n8n MQTT trigger node subscribes to the topic on the broker and reads the payload values when any changes are published. The code node then prepares the payload for JSON format. The HTTP request node ingests the data in a InfluxDB bucket How to customise this workflow to your needs Wokwi IOT ESP32 simulator You will need to setup a free account at Wokwi.com Once created search for a project "Micro-Python MQTT Weather Logger (ESP32)" Then when the MQTT weather logger project is open change lines 28 and 29 to the following 28 MQTT_CLIENT_ID = "" 29 MQTT_BROKER = "test.mosquitto.org" You then can start the simulation by clicking on the green arrow and it will connect the mosquitto broker and the "wokwi-weather" topic will be published. By clicking on the DHT22 sensor the temperature and humidity bar will appear and you can change the values to send updated payload values to the broker. InfluxDB You will require access to functioning InfluxDB database to utilise this workflow Note : You will have to provide the following for the HTTP request node to connect to InfluxDB. The URL and port of the desired InfluxDB (In this case the InfluxDB is running locally on port 8086 ie. http://localhost:8086.) InfluxDB bucket for the data. ( In this case the created bucket name is "wokwi-data") The Organization ID of the InfluxDB. This can be obtained for the InfluxDB admin page A generated API token to read and write to the InfluxDB bucket. Created from the InfluxDB admin n8n workflow. The MQTT trigger node is configured to subscribe to the "wokwi-weather" topic on the test Mosquitto MQTT broker. It reads the temperature and humidity data sent by ESP32. The code node uses Javascript to move the temperature and humidity payloads to JSON format. This is flexible and can easily modified. The HTTP request node posts the JSON payloads to the InfluxDB bucket. When the above is configured the workflow should function correctly. Thanks to the many who have downloaded this template. Let me know on what you would like to build. Contact me at tonyduffy@protonmail.com

beginner

2 nodes762 views

Analyze Telegram Messages with OpenAI and Send Notifications via Gmail & Telegram

by Immanuel

AI-powered Telegram message analysis with multi-tool notifications (Gmail, Telegram) This workflow triggers on Telegram updates, analyzes messages with an AI Agent using MCP tools, and sends notifications via Gmail and Telegram. Detailed Description Who is this for? This template is for teams, businesses, or individuals using Telegram for communication who need automated, AI-driven insights and notifications. It’s ideal for customer support teams, project managers, or tech enthusiasts wanting to process Telegram messages intelligently and receive alerts via Gmail and Telegram. What problem is this workflow solving? Use case This workflow solves the challenge of manually monitoring Telegram messages by automating message analysis and notifications. For example, a support team can use it to analyze customer queries on Telegram with AI tools (OpenAI, Airbnb, Brave, FireCrawl) and get notified via Gmail and Telegram for quick responses. What this workflow does The workflow: Triggers on a Telegram update (e.g., a new message) using the Listen for Telegram Updates node. Processes the message with the Analyze Message with AI node, an AI Agent using MCP tools like OpenAI Chat, Airbnb search, Brave search, and FireCrawl. Sends notifications via the Send Gmail Notification and Send Telegram Alert nodes, including AI-generated insights. Setup Prerequisites: Telegram bot token for the trigger and notification nodes. Gmail API credentials for sending emails. API keys for OpenAI, Airbnb, Brave, and FireCrawl (used in the AI Agent). Steps: Configure the Listen for Telegram Updates node with your Telegram bot token. Set up the Analyze Message with AI node with your OpenAI API key and other tool credentials. Configure the Send Gmail Notification node with your Gmail credentials. Set up the Send Telegram Alert node with your Telegram bot token. Test by sending a Telegram message to trigger the workflow. Setup takes ~15-30 minutes. Detailed instructions are in sticky notes within the workflow. How to customize this workflow to your needs Add more AI tools (e.g., sentiment analysis) in the Analyze Message with AI node. Modify the notification message in the Send Gmail Notification and Send Telegram Alert nodes to include specific AI outputs. Add nodes for other channels like Slack or SMS after the AI Agent. Disclaimer This workflow uses Community nodes (e.g., Airbnb, Brave, FireCrawl), which are available only in self-hosted n8n instances. Ensure your n8n setup supports Community nodes before using this template.

5 nodes461 views

Automated Upwork Job Alerts with Airtable & Slack

by Artur

Overview This automated workflow fetches Upwork job postings using Apify, removes duplicate job listings via Airtable, and sends new job opportunities to Slack. Key Features: Automated job retrieval** from Upwork via Apify API Duplicate filtering** using Airtable to store only unique jobs Slack notifications** for new job postings Runs every 30 minutes** during working hours (9 AM - 5 PM) This workflow requires an active Apify subscription to function, as it uses the Apify Upwork API to fetch job listings. Who is This For? This workflow is ideal for: Freelancers looking to track Upwork jobs in real time Recruiters automating job collection for analytics Developers who want to integrate Upwork job data into their applications What Problem Does This Solve? Manually checking Upwork for jobs is time-consuming and inefficient. This workflow: Automates job discovery based on your keywords Filters out duplicate listings, ensuring only new jobs are stored Notifies you on Slack when new jobs appear How the Workflow Works 1. Schedule Trigger (Every 20 Minutes) Triggers the workflow at 20-minute intervals Ensures job searches are only executed during working hours (9 AM - 5 PM) 2. Query Upwork for Jobs Uses Apify API to scrape Upwork job posts for specific keywords (e.g., "n8n", "Python") 3. Find Existing Jobs in Airtable Searches Airtable to check if a job (based on title and link) already exists 4. Filter Out Duplicate Jobs The Merge Node compares Upwork jobs with Airtable data The IF Node filters out jobs that are already stored in the database 5. Save Only New Jobs in Airtable The Insert Node adds only new job listings to the Airtable collection 6. Send a Slack Notification If a new job is found, a Slack message is sent with job details Setup Guide Required API Keys Upwork Scraper (Apify Token) – Get your token from Apify Airtable Credentials Slack API Token – Connect Slack to n8n and set the channel ID (default: #general) Configuration Steps Modify search keywords in the 'Assign Parameters' node (startUrls) Adjust the Working Hours in the 'If Working Hours' node Set your Slack channel in the Slack node Ensure Airtable is connected properly - you'll need to create a table with 'title' and 'link' columns. Adjust the 'If Working Hours' node to match your timezone and hours, or remove it altogether to receive notifications and updates constantly. How to Customize the Workflow Change keywords: update the startUrls in the 'Assign Parameters' node to track different job categories Change 'If Working Hours': Modify conditions in the IF Node to filter times based on your needs Modify Slack Notifications: Adjust the Slack message format to include additional job details Why Use This Workflow? Automated job tracking without manual searches Prevents duplicate entries in Airtable Instant Slack notifications for new job opportunities Customizable – adapt the workflow to different job categories Next Steps Run the workflow and test with a small set of keywords Expand job categories for better coverage Enhance notifications by integrating Telegram, Email, or a dashboard This workflow ensures real-time job tracking, prevents duplicates, and keeps you updated effortlessly.

4 nodes5 views

Extract and Structure Invoice Data with DocSumo and Export to Excel

by Anurag

Description This workflow automates the extraction of structured data from invoices or similar documents using Docsumo's API. Users can upload a PDF via an n8n form trigger, which is then sent to Docsumo for processing and structured parsing. The workflow fetches key document metadata and all line items, reconstructs each invoice row with combined header and item details, and finally exports all results as an Excel file. Ideal for automating invoice data entry, reporting, or integrating with accounting systems. How It Works A user uploads a PDF document using the integrated n8n form trigger. The workflow securely sends the document to Docsumo via REST API. After uploading, it checks and retrieves the parsed document results. Header information and table line items are extracted and mapped into structured records. The complete result is exported as an Excel (.xls) file. Setup Steps Docsumo Account: Register and obtain your API key from Docsumo. n8n Credentials Manager: Add your Docsumo API key as an HTTP header credential (never hardcode the key in the workflow). Workflow Configuration: In the HTTP Request nodes, set the authentication to your saved Docsumo credentials. Update the file type or document type in the request (e.g., "type": "invoice") as needed for your use case. Testing: Enable the workflow and use the built-in form to upload a sample invoice for extraction. Features Supports PDF uploads via n8n’s built-in form or via API/webhook extension. Sends files directly to Docsumo for document data extraction using secure credentials. Extracts invoice-level metadata (number, date, vendor, totals) and full line item tables. Consolidates all data in easy-to-use Excel format for download or integration. Modular node structure, easily extensible for further automation. Prerequisites Docsumo account with API access enabled. n8n instance with form, HTTP Request, Code, and Excel/Convert to File nodes. Working Docsumo API Key stored securely in n8n’s credential manager. Example Use Cases | Scenario | Benefit | |---------------------|-----------------------------------------| | Invoice Automation | Extract line items and metadata rapidly | | Receipts Processing | Parse and digitize business receipts | | Bulk Bill Imports | Batch process bills for analytics | Notes Credentials Security:** Do not store your API key directly in HTTP Request nodes; always use n8n credentials manager. Sticky Notes:** The workflow includes sticky notes for setup, input, API call, extraction, and output steps to assist template users. Custom Columns:** You can customize header or line item extraction by editing the Code node as needed.

AI Audio Transcription & Google Docs Report Generator with VLM Run

by Shahrear

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Automatically transform audio files into professional transcription reports with AI-powered speech recognition, timestamp generation, and formatted Google Docs output. What this workflow does Monitors Gmail for incoming audio attachments Downloads and processes audio files using VLM Run AI transcription Generates accurate transcriptions with precise timestamps and segmentation Creates professional reports in Google Docs with formatted output Handles asynchronous processing for long audio files without timeouts Setup Prerequisites: Gmail account, VLM Run API credentials, Google Docs access, self-hosted n8n. You need to install VLM Run community node Quick Setup: Configure Gmail OAuth2 for email monitoring Add VLM Run API credentials for audio transcription Set up Google Docs OAuth2 for report generation Create target Google Doc for transcription reports Update document URL in workflow nodes Test with sample audio file and activate Perfect for Meeting recordings and conference calls Voice memos and dictation workflows Interview transcriptions and journalism Podcast episode documentation Accessibility compliance and documentation Legal proceedings and court recordings Educational content and lecture notes Customer service call analysis Key Benefits Human-level accuracy** - Advanced AI speech recognition with automatic punctuation Timestamp precision** - Segmented transcriptions with exact time markers Multi-format support** - Handles MP3, WAV, M4A, AAC, OGG, FLAC files Asynchronous processing** - No timeouts for long audio files Professional formatting** - Beautifully structured Google Docs reports Automatic workflow** - Zero manual intervention required Saves hours per recording** - Transforms manual transcription into instant results Searchable documentation** - Google Docs integration enables easy content discovery How to customize Extend by adding: Speaker identification and diarization Integration with project management tools (Notion, Asana, Trello) Automatic summary generation from transcripts Translation to multiple languages Slack notifications for completed transcriptions Integration with CRM systems for call logging Audio quality enhancement preprocessing Custom formatting templates for different use cases Automatic keyword extraction and tagging Integration with calendar systems for meeting context This workflow revolutionizes audio documentation by combining cutting-edge AI transcription with professional report generation, making spoken content instantly accessible, searchable, and shareable across your organization.

🤖AI & Machine Learning

beginner

1 nodes346 views

Create a Slack AI Chatbot with Threads & Thinking UI using OpenRouter & Postgres

by James Francis

Overview Slack quietly released an update to their API that allows developers to build "AI Apps & Agents", which is a special classification of apps that have access to several special capabilities including: Multiple simultaneous chat threads with one user Loading "three dots" UI while your agent is thinking Option for users to pin your app to their top bar for quick chat access This workflow demonstrates how to build a Slack agent that takes advantage of all of these features. For a full video walkthrough of this workflow, watch this YouTube tutorial. Setup Instructions All of the below steps are required for this workflow to function properly unless otherwise noted. Create a Slack App Visit api.slack.com and click "Your Apps" Create a new app from scratch and follow the setup instructions In the Agents & AI Apps tab, enable the toggle and give your app a brief description In the OAuth & Permissions tab, enable the following bot token scopes: assistant:write chat:write channels:read im:history Install the app into your workspace and grant the requested permissions In your Slack workspace, right click your app's name in the sidebar, click "View app details", and make note of your apps Channel ID - you'll need this later. Copy your app's Bot User OAuth Token - you'll need that to create your n8n credentials In the Event Subscriptions tab, enable events and paste the workflows PRODUCTION webhook url (from this workflow's trigger node) into the input. In the same tab under "Susbcribe to bot events", select message.im Create a Postgres database In order to save the chat history and give your agent a working memory, you'll need your own Postgres database. You can use Supabase, Neon, or any other Postgres database provider. Once you've added your database's credentials to n8n, you can select those credentials in the Postgres Chat Memory node. This worklow saves all chat history in a table called chat_histories, but you name the table whatever you want. Create n8n Credentials You'll need to create the following credentials: Slack API. Use your Bot User OAuth Token referenced above. Bearer Auth. Use the same Bot User OAuth Token. Postgres. Use the connection string or config from your database provider. OpenRouter (or any other LLM model for the agent's model node) Wire Everything Up Now that you've created your Slack app, have your Postgres database, and have created credentials, follow these steps to wire up your workflow: In the "On Message Received" trigger, use your Slack API credential and enter your apps Channel ID in the "Channel To Watch" field. In the "Set Thinking Status" node, use your Bearer Auth credential. In the "Postgres Chat Memory" node, use your Postgres credential. In the "Send Reply" node, use your Slack API credential. Using the Chatbot Once you've completed the setup process and added in your credentials, you'll have a fully functional Slack chatbot complete with threads, loading UI, and the ability to pin your app to your workspace's top bar. Taking the Next Steps Now that this skeleton app is in place, it's up to you to add horsepower to the AI agent at the center of it all. Customize the prompts and add whatever tools you'd like. The sky is the limit! If you have any questions or feedback about this workflow, or would like me to build custom workflows for your business, email me at n8n@paperjam.agency.

5 nodes40 views

Clean Company Names for Cold Emails with GPT-4 Mini and Google Sheets

by James Francis

Overview In cold email campaigns, the lead's company name is the 2nd most frequently inserted variable after their first name. They're critical for effective cold email personalization. However, company names are often messy and can contain taglines, legal suffixes (e.g. LLC, Inc.), and other variations that would never be written out by a human in an email. If your email starts with "I came across Techwave Solutions LLC on LinkedIn...", it's a dead giveaway that you're sending a tempalted email and a response is much less likely. This simple workflow uses AI to clean up messy company names in a Google Sheet so that your cold email campaigns can achieve better results. How It Works A form is submitted with a Google Sheet url The workflow grabs the leads and uses an LLM node to clean the company names The updated leads are saved back in a new sheet within the original spreadsheet Setup Steps Add your Google Sheets and OpenAI (or your AI model provider of choice) credentials to n8n Create a Google Sheet with your list of leads. IMPORTANT: the sheet MUST have a column called "Company" (Optional). The AI workflow has a highly optimized system prompt. However, you may achieve better results by updating the list of examples in the prompt with companies (real or fake) in the industry you're targeting. If you have any questions or feedback about this workflow, or would like me to build custom workflows for your business, email me at n8n@paperjam.agency.

🤖AI & Machine Learning

4 nodes166 views

Scrape Latest 20 TechCrunch Articles

by Teddy

Retrieve 20 Latest TechCrunch Articles Who is this for? This workflow is designed for developers, content creators, and data analysts who need to scrape recent articles from TechCrunch. It’s perfect for anyone looking to aggregate news articles or create custom feeds for analysis, reporting, or integration into other systems. What problem is this workflow solving? This workflow automates the process of scraping recent articles from TechCrunch. Manually collecting article data can be time-consuming and inefficient, but with this workflow, you can quickly gather up-to-date news articles with relevant metadata, saving time and effort. What this workflow does This workflow retrieves the latest 20 news articles from TechCrunch’s “Recent” page. It extracts the article URLs, metadata (such as titles and publication dates), and main content for each article, allowing you to access the information you need without any manual effort. Setup Clone or download the workflow template. Ensure you have a working n8n environment. Configure the HTTP Request nodes with your desired parameters to connect to the TechCrunch API. (Optional) Customize the workflow to target specific sections or topics of interest. Run the workflow to retrieve the latest 20 articles. How to customize this workflow to your needs Modify the HTTP request to pull articles from different pages or sections of TechCrunch. Adjust the number of articles to retrieve by changing the selection criteria. Add additional processing steps to further filter or analyze the article data. Workflow Steps Send an HTTP request to the TechCrunch "Recent" page. Parse a posts box that holds the list of articles. Parse all posts to extract all articles. spilt out posts for each article. Extract the URL and metadata from each article. Send an HTTP request for each article using its URL. Locate and parse the main content of each article. Note: Be sure to update the HTTP Request nodes with any necessary headers or authentication to work with TechCrunch’s website.

Check if a Twitch Stream is Live

by Roger Filomeno

Introduction: This workflow template helps you determine if a Twitch user's stream is currently live or offline. Setup Instructions: The Document node holds the sample Twitch username you wish to check, you may adapt it in your workflow by replacing this with a chain that contains the Twitch username you want to check. This value is passed to the GraphQL node query as $('Document').item.json.twitch so make sure to change this based on your workflow. How it Works: The important nodes here are the GrapQL and IF nodes. The GrapQL queries the Twitch API, and then the output returns a document with the stream property. The IF node then checks if this property has a value, if null means the user is offline, otherwise the user is online or live. Common Use Cases: You can use this with other workflow templates to post live stream alerts to Twitter/X, Bluesky, and Discord via webhooks, etc to notify your community to join youR stream. You may also use an LLM node to write a custom alert based on the value of property title How to adjust this template If you want to check a list of Twitch channels, you can simply exchange the Document set node in the beginning with your list of channels. For more information on the GraphQL output please see the official Twitch API documentation: Get Streams

beginner

1 nodes1085 views

⚡ Text → Viral Shorts | AI Video Studio in Telegram /w Setup Video

by Joe V

🎬 AI Video Studio Bot - Telegram to YouTube Shorts, TikTok and Instagram Reels Automation Transform text into viral shorts — all from your phone 📱✨ 🎥 Watch It In Action 🔗 Full Demo: youtu.be/OI_oJ_2F1O0 🚀 What This Workflow Does Imagine having a full-stack AI video production studio in your pocket — no editing software, no dashboard hopping, no prompt engineering. Just pure creation magic through Telegram. This n8n workflow transforms Telegram into your personal AI video factory that: Your Message → AI Magic → Viral Short → Auto-Published ⏱️ 30 seconds 🎬 2-5 minutes 📤 Done! The Complete Pipeline: 📱 Message Telegram Bot - Send text, image, or voice memo 🤖 AI Prompt Generation - GPT-4 crafts perfect video prompts 🎬 Video Creation - Veo 3, Sora 2, or Seedance generates your short 📤 Auto-Upload - Instantly publishes to YouTube Shorts 🔁 Extend & Iterate - One-tap video extension (Veo only) No manual work. No technical skills. No limits. 💡 Why This Changes Everything | Traditional Way | This Workflow | |----------------|---------------| | ❌ Open 5+ platforms | ✅ One Telegram chat | | ❌ 30 min per video | ✅ 5 min per video | | ❌ Complex prompts needed | ✅ AI writes prompts for you | | ❌ Manual uploads | ✅ Auto-publishes everywhere | | ❌ Desktop only | ✅ Works from your phone | Result: Create 10+ YouTube Shorts during your lunch break 🚀 🎨 Video Styles - Choose Your Vibe Control everything with simple Telegram commands: | Command | Style | Perfect For | |---------|-------|------------| | /general | 🎭 Creative Shorts | Product demos, hooks, viral content | | /lost | 👻 Found Footage | Mystery, horror, urban exploration | | /3d | 🎮 3D Objects | Talking products, explainers, memes | | /story | 📖 Emotional Stories | Multi-scene narratives, brand stories | No command? AI intelligently picks the best style for your message. 🤖 AI Models - Pick Your Engine Choose your video generation model right from Telegram: Veo 3 / Veo 3 Fast ⚡ Best for: Quick iterations, realistic scenes Speed: 2-3 minutes Unique: Video extension support Sora 2 🎬 Best for: Cinematic quality, long sequences Speed: 4-5 minutes Unique: Best motion consistency Seedance 1.5 Pro 🌊 Best for: Artistic effects, fluid motion Speed: 3-4 minutes Unique: Stylized aesthetics Select directly in-chat with interactive buttons! ⚡ Power Features 🎯 Smart Video Generation AI analyzes your message intent Generates optimal prompts automatically Adapts to text, images, or voice input 📤 Auto-Publishing Pipeline Uploads to YouTube Shorts instantly AI-generated titles, descriptions, tags SEO-optimized for maximum reach 🔄 Extend & Refine One-tap video extension (Veo only) Keep the vibe, extend the story No re-generation needed 💳 Credit Management Real-time credit checking Prevents failed generations Session-based tracking with Redis 🔔 Status Monitoring Real-time generation updates Webhook polling for long jobs Graceful error handling & cancellation 🗂️ Session Storage Redis-powered state management Resume interrupted workflows Track generation history 🎪 Perfect For | Creator Type | Use Case | |-------------|----------| | 🎥 Faceless Channels | Generate endless Shorts without showing face | | 🏢 Agencies | Scale content production 10x for clients | | 📱 Solo Creators | Daily Shorts from your phone, no laptop needed | | 🤖 AI Farms | Automate content pipelines end-to-end | | 🧪 Experimenters | Rapid prototyping of video ideas | | 📊 Marketers | A/B test video concepts at scale | 🛠️ Tech Stack Telegram Bot API → User interface OpenAI GPT-4 → Prompt generation KIE.ai → Video generation (Veo/Sora/Seedance) YouTube Data API → Auto-publishing Redis → Session & state management S3-compatible → Video storage n8n → Orchestration layer Requirements: ✅ Telegram Bot Token ✅ OpenAI API Key ✅ KIE.ai Account (Veo/Sora/Seedance access) ✅ YouTube OAuth Credentials ✅ Redis Instance (recommended) ✅ S3-compatible Storage ✅ n8n Instance (cloud or self-hosted) 🎬 Real-World Workflow Example You: "A golden retriever puppy discovering snow for the first time" Bot: ✨ Generating your video... 📊 Credits: 50 remaining 🎬 Using: Veo 3 Fast ⏱️ ETA: 2 minutes 2 minutes later: ✅ Your video is ready! 📺 Uploaded to YouTube Shorts 🔗 Link: youtube.com/shorts/abc123 👁️ Views: 0 → 1.2K (24 hours) [Extend Video] [Generate New] Result: Viral short created from your phone while waiting for coffee ☕ 🔧 Customization Ideas 🎨 Extend the Platform Add TikTok publishing Include Instagram Reels Add Twitter video posts Support LinkedIn video 🎙️ Alternative Inputs Replace Telegram with WhatsApp Add Discord bot interface Support Slack commands Email-to-video pipeline 🎭 Creative Variations Swap OpenAI for Claude/Gemini Add custom style presets Include watermarking steps Generate captions automatically 📊 Analytics & Tracking Log all generations to Google Sheets Track video performance metrics A/B test title/thumbnail combinations Monitor credit usage trends 📊 Success Metrics After using this workflow for 30 days: | Metric | Before | After | Improvement | |--------|--------|-------|-------------| | ⏱️ Time per video | 45 min | 5 min | 9x faster | | 📹 Videos/week | 5 | 50+ | 10x volume | | 💰 Cost per video | $15 | $2 | 7.5x cheaper | | 📱 Creation location | Desktop only | Anywhere | ∞ flexibility | | 🧠 Prompt writing | Manual | Automated | No skill needed | 🚀 Quick Start Import workflow to n8n Add credentials (Telegram, OpenAI, KIE.ai, YouTube, Redis) Configure video storage (S3) Activate workflow Message your bot and watch the magic happen Setup time: ~20 minutes First video: ~5 minutes after setup 🏷️ Tags telegram ai-video youtube-shorts automation content-creation openai veo sora seedance text-to-video social-media creator-tools faceless-channel redis s3 n8n-workflow telegram-bot video-automation shorts-generator 📜 License MIT License - Use freely, modify, share, monetize! ⚡ Stop editing. Start generating. Scale your content empire. ⚡ Created by Joe Venner | Built with ❤️ and n8n

6 nodes71 views

One Telegram Chat to Edit, Thumbnail & Auto-Post Your Videos Everywhere

by Juan Carlos Cavero Gracia

This workflow turns any Telegram bot into an AI-powered social media command center for photos, videos and voice notes. video demo From one Telegram chat you can: Send a photo and auto-post it to Instagram, TikTok and Pinterest with AI captions. Send a video and: Let AI generate titles + descriptions and upload it to TikTok, Instagram and YouTube. Use /thumb to generate 4 custom thumbnails with Nano Banana Pro. Use /edit ... to run FFmpeg edits (cut, mute, resize, speed, etc.) via Upload-Post FFmpeg jobs and get the edited video back in Telegram. Send a voice note and turn it into posts for LinkedIn, X (Twitter) and Threads, then auto-publish. Keep human approval in the loop: every caption or text post is shown in Telegram for you to accept before publishing. Out of the box, the captions and long descriptions are optimized for Spanish (es-ES), but you can easily change the prompts to any language or brand voice. What You Can Do From Telegram 1. Photo → Instagram, TikTok & Pinterest Just send a photo (or image as document) to your Telegram bot: The workflow downloads the photo from Telegram. Gemini 2.5 Flash** analyzes the image plus your caption/text (if any). An AI Agent generates platform-specific descriptions for: TikTok (short hook, 90 chars) Instagram Pinterest (title + description) You receive a message in Telegram with all the proposed descriptions. You approve or reject with inline buttons. On approval, Upload-Post publishes the photo to: Instagram TikTok Pinterest (to the board you configured) and sends back a status message with success flags, post URLs and error messages. 2. Video → TikTok, Instagram & YouTube (no commands) If you send a video with no special caption: The workflow treats it as a standard video post. It fetches the file from Telegram. Gemini 2.5 Flash** analyzes the video and describes its content. An AI Agent turns that description + your caption into: TikTok description Instagram description YouTube title + description You get a Telegram message with the three platform descriptions to review. Once you approve: It shows “Uploading…” in Telegram. The video is sent to Upload-Post, which uploads to TikTok, Instagram and YouTube with the generated text. Finally, you receive an upload report for each platform (success, URL, error message). 3. /thumb → AI Thumbnails for Your Video (Nano Banana Pro) If you send a video with caption exactly /thumb: The workflow downloads the video. Gemini 2.5 Flash* generates a *long, SEO-rich description in Spanish** of everything that happens in the video. A second AI Agent uses that detailed description to create 3 concepts: Each concept has: title, description, and a full prompt_thumbnail (Spanish, single line) specially crafted for Nano Banana Pro. In Telegram you see the 3 concepts (titles) and select: 0, 1, 2 or “create new”. Once you choose a concept: The prompt is sent to Nano Banana Pro (fal-ai/nano-banana-pro/edit) with your reference face image (configurable). Nano Banana Pro generates 4 thumbnails (16:9). The workflow downloads the 4 images and sends them back to you in Telegram as photos so you can pick and use your favorite in your YouTube/Upload-Post pipeline. Use /thumb whenever you already have the video and just want killer thumbnails generated with AI. 4. /edit … → Natural-Language FFmpeg Video Editor If you send a video with a caption starting with /edit, for example: /edit cut the first 3 seconds and remove the audio /edit crop to vertical 9:16 and speed up x1.5 /edit blur the background and keep the subject centered The workflow behaves as a text-to-FFmpeg command generator: An AI Agent (powered by Gemini) reads your /edit instructions. It generates a safe FFmpeg command in JSON format: Always uses ffmpeg -y Uses {input} and {output} placeholders No semicolons and no dangerous shell characters The workflow then: Downloads the original video from Telegram. Calls Upload-Post FFmpeg jobs API with the video and the generated full_command. Polls the job status until it’s finished. Downloads the processed (edited) video. Sends the edited video back to you in Telegram with a simple sendVideo node. This makes Telegram a front-end for a remote FFmpeg engine: you describe the edit in natural language, and the workflow handles all the FFmpeg complexity. > Note: The edited video is returned to Telegram; if you want to auto-post it, simply send the new video again without /edit so it goes through the normal multi-platform publishing path. 5. Voice Notes → LinkedIn, X & Threads (Text Posts) For voice messages: The Telegram Trigger detects message.voice. The workflow downloads the audio file. OpenAI Whisper** transcribes the recording. An AI Agent turns the transcription into: A LinkedIn post (Spanish, long-form dev/creator style, based on your examples). A Threads post (Spanish, up to ~500 chars). A Tweet / X post or thread (English, using hooks + hashtags like #n8n, #automation, #dev). In Telegram you see a preview message with the suggested copy for Threads, LinkedIn and X. After you approve: You get an “Uploading…” message. Upload-Post publishes: To your LinkedIn organization page (configured by ID). To X (Twitter). To Threads. The workflow sends a status message with success flags and URLs for each platform. This is perfect for “talk to your phone, ship content to all your text platforms”. How the Workflow Is Structured Telegram Trigger** Listens to every incoming message and routes by type: /start → No-Op voice → Audio pipeline document/photo → Photo pipeline video → Video/thumbnail/editor pipelines (/thumb, /edit or normal) AI Blocks (Gemini + OpenAI)** Gemini 2.5 Flash for: Photo understanding. Short video descriptions (for auto-posting). Long, detailed video summaries (for thumbnail generator). OpenAI Whisper for voice transcription. Multiple AI Agents (Gemini chat) with structured JSON output parsers for: Per-platform social captions. Threads/LinkedIn/X posts. Thumbnail prompts and title concepts. FFmpeg command generation. Upload-Post Integration** Photos → Instagram, TikTok, Pinterest. Videos → TikTok, Instagram, YouTube. Text → LinkedIn page, X, Threads. FFmpeg job endpoint for server-side video editing. All uploads return status, URL and error messages back into Telegram. Human-in-the-Loop** All critical AI outputs go through sendAndWait nodes in Telegram: You review and choose whether to publish or not. You choose which thumbnail concept to use. Requirements & Setup Accounts & APIs** Telegram bot (via @BotFather). Upload-Post.com account with your social profiles connected. OpenAI API key (Whisper). Google Gemini API key (AI Studio). Nano Banana Pro / fal.ai key (for thumbnails). Runtime** n8n instance (cloud or self-hosted). FFmpeg available where n8n runs (Docker image, VM, etc.) for local checks if needed (the heavy lifting is delegated to Upload-Post FFmpeg jobs). Configuration** Create Telegram credentials with your bot token. Create Upload-Post credentials with your API token. Set upload_post_user and pinterest_board_id in the Edit Fields node. Optionally replace: Example face image URL used for Nano Banana Pro. LinkedIn organization ID. Any language / tone in the AI agent system prompts. Ideal Use Cases Creators & influencers* who want to post to every platform from *one Telegram chat**. Agencies** who want a “content butler” clients can use without touching n8n. Solo devs & makers** who publish workflows, devlogs and product updates and want: Multi-platform video posts. Voice → LinkedIn/X/Threads posts. Easy text-based video editing and thumbnail generation. Install this template, plug in your keys, talk to your bot in Telegram, and turn it into your all-in-one AI social media machine.