Back to Catalog

AI video automation engine - generate & publish YT shorts with Veo-3 or Sora 2

SuSSuS
619 views
2/3/2026
Official Page

Product Overview

Scale short-form content without scaling your team. This template turns idea discovery → prompt & text generation → Veo-3 video rendering → vertical formatting → multi-channel publishing into one cohesive pipeline. It’s built natively on n8n, so you keep full control, self-host if you want, and extend every step with your own logic.


What’s Inside (Modular Building Blocks)

  • Idea Engine – AI generates concise, surprising facts and a visual metaphor per topic (swappable LLM/provider).
  • Prompt & Text Composer – Crafts an 8-second, cinematic Veo-3 prompt + title, caption, description, hashtags, tags in a consistent brand voice.
  • Renderer Integration – Kie.ai → Veo-3 (16:9, 1080p) for fast, cinematic clips.
  • Vertical Formatter – FFmpeg pipeline converts to 1080×1920, adds top/bottom text bands (15–20 words), and preserves loop smoothness.
  • Multi-Channel Distribution – Uploads to YouTube Shorts and Telegram for internal review/approvals.
  • Scheduler & Orchestration – CRON triggers, retries, and lightweight polling make the system dependable for daily publishing.

Why These Components (and why they work together)

  • Veo-3 via Kie.ai provides a sweet spot of quality + speed, ideal for short loops where style coherence matters.
  • n8n brings vendor-neutral orchestration: swap LLMs, add rate limits, branch flows, or trigger on events—without rewriting your stack.
  • FFmpeg ensures a platform-native look (9:16, crisp text bands, no blurry hacks).
  • Separation of concerns (idea → text → render → edit → publish) makes it easy to A/B test any stage independently.

Key Benefits

  • Hands-Free Consistency – Daily output with a repeatable creative pattern that audiences recognize.
  • Brand-Safe Copy – Titles, descriptions, and hashtags follow a controlled structure—polished by design.
  • Time Savings – Replace fragmented tooling with one pipeline; no manual re-formatting, captioning, or re-uploads.
  • Creator-Grade Quality – Cinematic loops optimized for watch time and retention on Shorts/Reels.
  • Own Your Stack – Self-hosted orchestration and storage; no lock-in.

Reuse & Extension Ideas

  • Topic CMS – Feed topics from Google Sheets / Notion and mark each as “published”—perfect for content calendars.
  • Multi-Language – Duplicate the text composer for EN/DE outputs; upload the same clip with localized metadata.
  • Thumbnail/Preview Track – Add an image generator step for platform cards or YouTube custom thumbnails.
  • Analytics Feedback Loop – Fetch video performance, score ideas, and prioritize winning angles automatically.
  • Compliance & Fact Trails – Store sources next to each post for quick audits and edits.
  • Storage & Delivery – Push masters to S3/Backblaze, serve via CDN for faster IG ingestion.
  • More Channels – Add TikTok, X, LinkedIn publishers or a newsletter export.
  • A/B Creative – Render multiple Veo-3 seeds, rotate captions/CTAs, and compare retention.

Who It’s For

  • Agencies wanting repeatable, branded Shorts at scale.
  • Creators & Media Teams who need daily output with minimal overhead.
  • Product Marketing looking to convert docs/reports into snackable, evergreen video facts.
  • Startups building audience fast without adding headcount.

Technical Notes (at a glance)

  • Orchestration: n8n (self-hosted or cloud)
  • Video: Veo-3 via Kie.ai (16:9 render → FFmpeg vertical remaster 1080×1920)
  • Text Stack: Any LLM provider (swappable); outputs normalized for each platform
  • Distribution: YouTube Data API v3, Telegram Bot API
  • Security: API keys via n8n credentials/ENV; public URL endpoint only serves whitelisted .mp4 filenames with proper headers
  • Reliability: CRON triggers, bounded retries/polling, and safe fallbacks to avoid stuck runs

Who to use it

To enhance the completeness, add specific step-by-step setup instructions for users to implement the workflow easily:

  1. Install Prerequisites

    • Set up n8n on your server or local machine (production mode with reverse proxy).
    • Install FFmpeg and ensure fonts (e.g., DejaVu Sans) are available.
  2. Configure API Credentials

    • Get a Perplexity API key for idea generation.
    • Request a Kie.ai API key for Veo-3 video rendering.
    • Set up YouTube OAuth2 (enable YouTube Data API v3 in Google Cloud Console).
    • Create a Telegram bot token via BotFather.
    • Store all keys as environment variables in n8n (avoid hardcoding).
  3. Prepare Storage

    • Create a working directory accessible by n8n with read/write rights.
    • Ensure enough disk space for video caching (approx. 50–200 MB per run).
  4. Set Scheduling

    • Add CRON triggers for automatic execution (e.g., twice daily).
    • Example:
      0 12 04 * * * → 04:12 AM daily
      0 12 16 * * * → 04:12 PM daily
      
  5. Define Variables

    • File naming conventions:
      • name_vorher = raw 16:9 video
      • name_nachher = final 9:16 video
    • Set topic = content niche (e.g., history, ocean, futurism).
  6. Build Workflow Steps in n8n

    • Idea Generation: Perplexity node for viral fact.
    • Prompt Agent: Expand into full package (prompt, caption, hashtags).
    • Video Generation: Kie.ai Veo-3 API request (poll until success).
    • Download & Edit: Save raw file, convert to 9:16 with FFmpeg overlays.
    • Notifications & Uploads:
      • Telegram node → send video.
      • YouTube node → upload with title, description, tags.
  7. Test End-to-End

    • Run the workflow manually once.
    • Verify video rendering, FFmpeg subtitles, Telegram message, YouTube & IG uploads.
  8. Go Live

    • Enable CRON triggers.
    • Monitor first runs for errors (API limits, FFmpeg paths, token expiry).

Why Buy This Template

You’re not buying a script—you’re buying a production-ready system with a deliberate creative pattern, best-practice formatting, and shipping-grade integrations. It reduces ramp-up from weeks to hours and gives you a flexible base you can keep evolving.


AI Video Automation Engine - Generate & Publish YouTube Shorts

This n8n workflow automates the process of generating AI-powered video content and publishing it as YouTube Shorts. It leverages AI agents for content creation, interacts with external APIs for video generation (likely Veo 3 or Sora 2, based on the directory name, though not explicitly in the JSON), and manages the publishing process to YouTube and notifications via Telegram.

What it does

This workflow orchestrates a series of steps to create and publish short-form video content:

  1. Triggers on a Schedule: The workflow starts at predefined intervals, ensuring continuous content generation and publishing.
  2. Initial Setup (Sticky Note): A sticky note is present, likely for documentation or temporary configuration notes within the workflow.
  3. AI Agent for Content Generation: An AI Agent (likely powered by LangChain) is used to generate video ideas, scripts, or other content relevant to the video creation.
  4. Structured Output Parsing: The output from the AI Agent is processed by a Structured Output Parser to extract specific data in a defined format (e.g., JSON), ensuring the content is usable by subsequent nodes.
  5. Conditional Logic (If): The workflow includes an 'If' node, suggesting conditional branching based on the parsed AI output. This could be used to validate content, decide on video generation parameters, or handle different content types.
  6. Video Generation Request (HTTP Request): An HTTP Request node is used to send the generated content to an external video generation API (e.g., Veo 3, Sora 2, or a custom service).
  7. Command Execution (Execute Command): A shell command is executed, which might be used for local file operations, video processing, or interacting with the n8n instance's environment.
  8. File Management (Read/Write Files from Disk): This node handles reading or writing files to disk, potentially for storing generated video assets, scripts, or metadata locally.
  9. Wait for Processing: A "Wait" node pauses the workflow, likely to allow time for the video generation API to process the request and generate the video.
  10. YouTube Upload: The generated video is uploaded to YouTube as a Short.
  11. Notifications (Telegram): A Telegram message is sent, likely to notify a channel or user about the successful video upload or any issues encountered.
  12. Data Manipulation (Edit Fields): An "Edit Fields (Set)" node is included, which can be used to transform or add data attributes at various stages of the workflow.
  13. AI Language Models (Google Gemini Chat Model, Perplexity): The workflow includes nodes for Google Gemini Chat Model and Perplexity, which are likely used by the AI Agent for generating content or performing research.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • YouTube Account: A YouTube account with appropriate API access configured in n8n credentials for uploading videos.
  • Telegram Account: A Telegram bot token and chat ID configured in n8n credentials for sending notifications.
  • AI Service Credentials:
    • Google Gemini API Key: For the Google Gemini Chat Model.
    • Perplexity API Key: For the Perplexity node.
  • External Video Generation API: Access and credentials for a video generation service (e.g., Veo 3, Sora 2, or a custom API endpoint) that the "HTTP Request" node will interact with.
  • LangChain Integration: Ensure the @n8n/n8n-nodes-langchain package is installed and configured in your n8n instance.
  • Local Shell Access (Optional but likely): If the "Execute Command" node runs local scripts, your n8n instance needs appropriate permissions and the necessary tools installed on its host system.

Setup/Usage

  1. Import the Workflow: Import the provided JSON into your n8n instance.
  2. Configure Credentials:
    • Set up your YouTube OAuth 2.0 or API Key credentials.
    • Configure your Telegram Bot Token and Chat ID credentials.
    • Add your Google Gemini API Key credentials.
    • Add your Perplexity API Key credentials.
    • Configure any necessary credentials for your external video generation API in the "HTTP Request" node.
  3. Customize AI Agent: Adjust the "AI Agent" node's prompt and tools to define the type of video content you want to generate.
  4. Configure Structured Output Parser: Ensure the "Structured Output Parser" node correctly extracts the necessary data fields from the AI Agent's response.
  5. Update HTTP Request Node: Modify the "HTTP Request" node to correctly send data to your chosen video generation API, including the endpoint URL, headers, and body content.
  6. Adjust Execute Command (if applicable): If the "Execute Command" node is used for specific tasks, ensure the command is correct for your environment.
  7. Configure Read/Write Files from Disk (if applicable): Set paths and operations for file handling.
  8. Set Wait Duration: Adjust the "Wait" node's duration based on the typical processing time of your video generation service.
  9. Customize YouTube Upload: Configure the "YouTube" node with the desired video title, description, tags, and privacy settings.
  10. Customize Telegram Notification: Update the "Telegram" node with the message content you wish to send.
  11. Activate the Workflow: Once all configurations are complete, activate the workflow. It will run automatically based on the "Schedule Trigger" settings.

Related Templates

Dynamic Hubspot lead routing with GPT-4 and Airtable sales team distribution

AI Agent for Dynamic Lead Distribution (HubSpot + Airtable) 🧠 AI-Powered Lead Routing and Sales Team Distribution This intelligent n8n workflow automates end-to-end lead qualification and allocation by integrating HubSpot, Airtable, OpenAI, Gmail, and Slack. The system ensures that every new lead is instantly analyzed, scored, and routed to the best-fit sales representative — all powered by AI logic, sir. --- 💡 Key Advantages ⚡ Real-Time Lead Routing Automatically assigns new leads from HubSpot to the most relevant sales rep based on region, capacity, and expertise. 🧠 AI Qualification Engine An OpenAI-powered Agent evaluates the lead’s industry, region, and needs to generate a persona summary and routing rationale. 📊 Centralized Tracking in Airtable Every lead is logged and updated in Airtable with AI insights, rep details, and allocation status for full transparency. 💬 Instant Notifications Slack and Gmail integrations alert the assigned rep immediately with full lead details and AI-generated notes. 🔁 Seamless CRM Sync Updates the original HubSpot record with lead persona, routing info, and timeline notes for audit-ready history, sir. --- ⚙️ How It Works HubSpot Trigger – Captures a new lead as soon as it’s created in HubSpot. Fetch Contact Data – Retrieves all relevant fields like name, company, and industry. Clean & Format Data – A Code node standardizes and structures the data for consistency. Airtable Record Creation – Logs the lead data into the “Leads” table for centralized tracking. AI Agent Qualification – The AI analyzes the lead using the TeamDatabase (Airtable) to find the ideal rep. Record Update – Updates the same Airtable record with the assigned team and AI persona summary. Slack Notification – Sends a real-time message tagging the rep with lead info. Gmail Notification – Sends a personalized handoff email with context and follow-up actions. HubSpot Sync – Updates the original contact in HubSpot with the assignment details and AI rationale, sir. --- 🛠️ Setup Steps Trigger Node: HubSpot → Detect new leads. HubSpot Node: Retrieve complete lead details. Code Node: Clean and normalize data. Airtable Node: Log lead info in the “Leads” table. AI Agent Node: Process lead and match with sales team. Slack Node: Notify the designated representative. Gmail Node: Email the rep with details. HubSpot Node: Update CRM with AI summary and allocation status, sir. --- 🔐 Credentials Required HubSpot OAuth2 API – To fetch and update leads. Airtable Personal Access Token – To store and update lead data. OpenAI API – To power the AI qualification and matching logic. Slack OAuth2 – For sending team notifications. Gmail OAuth2 – For automatic email alerts to assigned reps, sir. --- 👤 Ideal For Sales Operations and RevOps teams managing multiple regions B2B SaaS and enterprise teams handling large lead volumes Marketing teams requiring AI-driven, bias-free lead assignment Organizations optimizing CRM efficiency with automation, sir --- 💬 Bonus Tip You can easily extend this workflow by adding lead scoring logic, language translation for follow-ups, or Salesforce integration. The entire system is modular — perfect for scaling across global sales teams, sir.

MANISH KUMARBy MANISH KUMAR
113

Track daily moods with AI analysis & reports using GPT-4o, Data Tables & Gmail

Track your daily mood in one tap and receive automated AI summaries of your emotional trends every week and month. Perfect for self-reflection, wellness tracking, or personal analytics. This workflow logs moods sent through a webhook (/mood) into Data Tables, analyzes them weekly and monthly with OpenAI (GPT-4o), and emails you clear summaries and actionable recommendations via Gmail. ⚙️ How It Works Webhook – Mood → Collects new entries (🙂, 😐, or 😩) plus an optional note. Set Mood Data → Adds date, hour, and note fields automatically. Insert Mood Row → Stores each record in a Data Table. Weekly Schedule (Sunday 20:00) → Aggregates the last 7 days and sends a summarized report. Monthly Schedule (Day 1 at 08:00) → Aggregates the last 30 days for a deeper AI analysis. OpenAI Analysis → Generates insights, patterns, and 3 actionable recommendations. Gmail → Sends the full report (chart + AI text) to your inbox. 📊 Example Auto-Email Weekly Mood Summary (last 7 days) 🙂 5 ██████████ 😐 2 ████ 😩 0 Average: 1.7 (Positive 🙂) AI Insights: You’re trending upward this week — notes show that exercise days improved mood. Try keeping short walks mid-week to stabilize energy. 🧩 Requirements n8n Data Tables enabled OpenAI credential (GPT-4o or GPT-4 Turbo) Gmail OAuth2 credential to send summaries 🔧 Setup Instructions Connect your credentials: Add your own OpenAI and Gmail OAuth2 credentials. Set your Data Table ID: Open the Insert Mood Row node and enter your own Data Table ID. Without this, new moods won’t be stored. Replace the email placeholder: In the Gmail nodes, replace your.email@example.com with your actual address. Deploy and run: Send a test POST request to /mood (e.g. { "mood": "🙂", "note": "productive day" }) to log your first entry. ⚠️ Before activating the workflow, ensure you have configured the Data Table ID in the “Insert Mood Row” node. 🧠 AI Analysis Interprets mood patterns using GPT-4o. Highlights trends, potential triggers, and suggests 3 specific actions. Runs automatically every week and month. 🔒 Security No personal data is exposed outside your n8n instance. Always remove or anonymize credential references before sharing publicly. 💡 Ideal For Personal mood journaling and AI feedback Therapists tracking client progress Productivity or self-quantification projects 🗒️ Sticky Notes Guide 🟡 Mood Logging Webhook POST /mood receives mood + optional note. ⚠️ Configure your own Data Table ID in the “Insert Mood Row” node before running. 🟢 Weekly Summary Runs every Sunday 20:00 → aggregates last 7 days → generates AI insights + emails report. 🔵 Monthly Summary Runs on Day 1 at 08:00 → aggregates last 30 days → creates monthly reflection. 🟣 AI Analysis Uses OpenAI GPT-4o to interpret trends and recommend actions. 🟠 Email Delivery Sends formatted summaries to your inbox automatically.

Jose CastilloBy Jose Castillo
105

Create, update, and get a person from Copper

This workflow allows you to create, update, and get a person from Copper. Copper node: This node will create a new person in Copper. Copper1 node: This node will update the information of the person that we created using the previous node. Copper2 node: This node will retrieve the information of the person that we created earlier.

Harshil AgrawalBy Harshil Agrawal
603