Workflow Templates

This workflow automates the creation of audiobooks from structured text data using AI-powered text-to-speech and audio processing services. Click here to listen the result of my example. Key Advantages 1. ✅ Fully Automated Audiobook Production The entire pipeline—from text retrieval to final audio upload—is automated. This removes manual steps, reduces human error, and enables repeatable audiobook generation at scale. 2. ✅ Advanced Voice Customization By using voice design prompts (voice description + style instruction), the workflow produces highly expressive and context-aware narration, ideal for audiobooks, storytelling, and branded audio content. 3. ✅ Scalable and API-Safe Architecture The batch processing and looping logic respects external API limits. This makes the workflow robust even for large audiobooks with dozens or hundreds of segments. 4. ✅ Centralized Content Management Google Sheets acts as a lightweight CMS: Easy to edit scripts and voice parameters Clear tracking of processed items Temporary URLs and merge flags ensure full visibility into the workflow state 5. ✅ Asynchronous and Fault-Tolerant The use of wait nodes and status checks allows the workflow to handle long-running audio operations without blocking or failing prematurely. 6. ✅ Seamless Cloud Storage Integration Final audiobooks are automatically stored in Google Drive, making them immediately accessible for distribution, review, or further processing. 7. ✅ Modular and Extensible Design Each step (TTS generation, batching, merging, storage) is modular. This makes it easy to: Swap TTS providers Change storage destinations Add post-processing steps (e.g. metadata, chapter markers) How it Works This workflow automates the creation of audiobooks using AI-generated voice synthesis with custom voice design. The process begins by retrieving script data from a Google Sheets document containing text, speaker information, voice descriptions, and style instructions. The workflow then processes each row in batches, sending the text to the Qwen3-TTS model on Replicate with specified voice parameters to generate individual audio segments. Each generated audio URL is stored back in the spreadsheet. Concurrently, once multiple audio segments are ready, they are merged into a single audio file using an external FFmpeg API service. The system polls for merge completion, retrieves the final merged audio file, and uploads it to Google Drive as a complete audiobook with a timestamped filename. Set up Steps Data Source Configuration: Set up the Google Sheets node to connect to your spreadsheet containing the audiobook script with required columns: Text, Speaker, Voice Description, Style Instruction, Temp URL, and To Merge API Credentials Setup: Configure Replicate API credentials for Qwen3-TTS voice synthesis Set up Fal.run API credentials for FFmpeg audio merging operations Configure Google Drive OAuth2 credentials for uploading the final audiobook Voice Design Parameters: Ensure your spreadsheet contains appropriate voice descriptions and style instructions compatible with the Qwen3-TTS model's requirements Destination Settings: Verify the Google Drive folder ID in the upload node points to your desired storage location for the final audiobook Execution: Trigger the workflow manually to begin processing your script rows and generating the complete audiobook with custom voice design 👉 Subscribe to my new YouTube channel. Here I’ll share videos and Shorts with practical tutorials and FREE templates for n8n. Need help customizing? Contact me for consulting and support or add me on Linkedin.

This automated n8n workflow converts any technical documentation or blog post URL into a professional, step-by-step developer tutorial video complete with AI-generated narration, code syntax highlighting, terminal command animations, and visual diagrams. The system intelligently analyzes documentation structure, extracts code examples, generates natural voiceover narration, creates synchronized visual scenes, and automatically publishes the finished video to YouTube with SEO-optimized descriptions. Fundamental Aspects Webhook-Based Trigger**: Accepts HTTP POST requests containing a documentation URL to initiate the automated video creation pipeline on-demand. Intelligent Content Extraction**: Fetches HTML content, parses documentation structure, extracts code blocks with language detection, identifies headings for organization, and cleans irrelevant elements like navigation and scripts. AI-Powered Tutorial Planning**: Uses Claude AI to analyze documentation content and generate a comprehensive tutorial outline including section titles, duration estimates, narration scripts, visual types (code/terminal/diagram), and learning outcomes. Professional Audio Generation**: Converts narration scripts into high-quality audio using Google Cloud Text-to-Speech with natural-sounding neural voices, proper pacing, and timing synchronization. Dynamic Visual Scene Creation**: Generates code editor scenes with syntax highlighting and typewriter effects, terminal animations with command execution sequences, flowchart diagrams with progressive reveals, and text overlays with key points. Automated Video Rendering**: Combines audio narration with visual scenes using Remotion API to render publication-ready videos in 1080p resolution at 30fps with smooth transitions. Multi-Platform Distribution**: Automatically uploads completed videos to YouTube with AI-generated titles and descriptions, backs up to Google Drive for archival, and returns comprehensive metadata via webhook response. Setup Instructions Import the Workflow into n8n**: Download the workflow JSON file and import via n8n interface under "Workflows" → "Import from File" option. Configure Claude AI (Anthropic) Credentials**: Navigate to the "Analyze with Claude AI" node and click the credentials dropdown. Create new Anthropic credentials using your API key from console.anthropic.com. Ensure you have access to Claude Sonnet 4 model (claude-sonnet-4-20250514). Save and test the connection to verify API access. Set Up Google Cloud Text-to-Speech**: Go to Google Cloud Console and enable the Text-to-Speech API. Create a service account with "Cloud Text-to-Speech User" role. Generate and download a JSON key file for the service account. In n8n, navigate to "Generate Audio with Google TTS" node and add service account credentials. Upload the JSON key file when prompted. Configure Remotion API for Video Rendering**: Sign up for a Remotion account at remotion.dev and obtain API credentials. In the "Render Video with Remotion" node, add HTTP Header Auth credentials. Set authorization header with your Remotion API key. Ensure you have a Remotion composition named "TutorialVideo" deployed. Note: You may need to create a custom Remotion project for code highlighting and terminal animations. Add YouTube OAuth2 Credentials**: Navigate to "Upload to YouTube" node and create YouTube OAuth2 credentials. Follow Google's OAuth flow to authorize n8n to upload videos on your behalf. Ensure your YouTube account has upload permissions and is verified for videos longer than 15 minutes. Configure default privacy settings (public, unlisted, or private) in node parameters. Configure Google Drive Backup**: Go to "Backup to Google Drive" node and add Google Drive OAuth2 credentials. Authorize n8n to access your Google Drive. Optionally specify a folder ID in node options to organize video backups. Activate Webhook Endpoint**: Activate the workflow using the toggle switch in the top-right corner. Copy the webhook URL from the "Webhook Trigger" node (appears after activation). The URL will be in format: https://your-n8n-instance.com/webhook/create-video. Test the Workflow**: Send a test POST request to the webhook URL using curl, Postman, or HTTPie: curl -X POST https://your-n8n-instance.com/webhook/create-video \ -H "Content-Type: application/json" \ -d '{"documentationUrl": "https://docs.example.com/getting-started"}' Monitor the execution in n8n's "Executions" tab to track progress through each node. Check YouTube and Google Drive for the generated video (processing may take 5-15 minutes depending on content length). Verify Output Quality**: Review the generated video for audio quality, code highlighting accuracy, and pacing. Check YouTube description for proper formatting of prerequisites and learning outcomes. Ensure code snippets are readable and terminal animations are properly synchronized. Technical Dependencies Claude AI (Anthropic)**: For intelligent content analysis, tutorial outline generation, section structuring, and narration script writing with natural language processing. Google Cloud Text-to-Speech**: For converting narration scripts into professional-quality audio with neural voice models (en-US-Neural2-J recommended for technical content). Remotion API**: For programmatic video rendering, scene composition, code syntax highlighting, terminal animations, and transition effects (requires custom React components). YouTube Data API v3**: For automated video uploads, metadata management, thumbnail generation, and playlist organization. Google Drive API**: For backup storage, file sharing, and archival of raw video files with organized folder structures. n8n Platform**: For workflow orchestration, webhook handling, conditional logic, error handling, and execution monitoring. JavaScript Runtime**: For custom content parsing, JSON manipulation, code language detection, timing calculations, and data transformation in Code nodes. Customization Possibilities Voice Customization**: Change narrator voice in "Generate Narration Script" node by modifying the voice parameter. Google TTS offers multiple voices (male, female, different accents). Adjust speed (0.25-4.0) and pitch (-20 to +20) for different pacing styles. Use different voices for intro/outro vs main content. Video Branding**: Add custom intro/outro animations by modifying Remotion composition. Include your logo, channel name, and subscribe animations. Customize color schemes in code editor themes (Dracula, Monokai, Solarized, One Dark). Add watermarks or corner branding throughout video. Code Editor Themes**: Change syntax highlighting themes in "Create Visual Scenes" node. Popular options include Dracula (default), VS Code Dark+, GitHub Light, Monokai Pro, Nord. Adjust font sizes, line spacing, and highlighting animation speeds for readability. Content Filtering**: Add pre-processing logic to filter specific documentation sections. Skip changelog entries, API reference tables, or installation instructions if not needed. Focus on tutorial-style content only. Add minimum/maximum content length thresholds. Multi-Language Support**: Extend the workflow to detect documentation language and use appropriate TTS voices. Support Spanish (es-ES), French (fr-FR), German (de-DE), Japanese (ja-JP), and other languages. Generate localized titles and descriptions. Advanced Visual Types**: Add screen recording capabilities for live demonstrations. Include animated flowcharts using Mermaid or D3.js. Generate architecture diagrams from code structure. Add picture-in-picture video of an instructor or animated avatar. Tutorial Complexity Detection**: Use Claude AI to assess documentation difficulty level and adjust pacing accordingly. Beginner content gets slower narration and more detailed explanations. Advanced content can move faster with less repetition. Interactive Elements**: Generate timestamp chapters for YouTube with clickable sections. Create accompanying blog post or GitHub repository with code examples. Generate quiz questions based on content for learning validation. Quality Assurance**: Add validation nodes to check video quality before upload. Verify audio levels are balanced, code is readable at 1080p, and total duration matches expectations. Implement retry logic for failed renders. Batch Processing**: Extend webhook to accept multiple URLs for bulk video generation. Create playlists automatically for related documentation pages. Schedule sequential uploads to avoid flooding your channel. Analytics Integration**: Track video performance by connecting to YouTube Analytics API. Monitor view counts, engagement rates, and audience retention. Use insights to improve future video generation parameters. Cost Optimization**: Implement caching for previously processed documentation URLs to avoid redundant API calls. Use cheaper TTS voices for internal testing. Compress videos before upload while maintaining quality. Set API rate limits to control costs. Custom Remotion Components**: Build specialized React components for your tech stack (e.g., database schema visualizers, API request/response animations, deployment pipeline diagrams). Create reusable templates for common tutorial patterns. Notification System**: Add email or Slack notifications when videos complete processing. Include video URLs, processing time, and any errors encountered. Send daily summaries of generated videos. SEO Enhancement**: Use Claude AI to generate SEO-optimized titles, descriptions, and tags. Research trending keywords in your niche. Auto-generate closed captions and subtitles for accessibility and searchability. Explore More AI Video Automation: Contact us to design custom video automation workflows for product demos, educational content, marketing videos, or AI-powered content creation pipelines tailored to your business needs.

This n8n template demonstrates how to automate YouTube content repurposing using AI. Upload a video to Google Drive and automatically generate transcriptions, A/B testable titles, AI thumbnails, short-form clips with captions, and YouTube descriptions with chapter timestamps. Use cases include: Content creators who publish 1-2 long-form videos per week and need to extract 5-10 short-form clips, YouTube agencies managing multiple channels, or automation consultants building content systems for clients. Good to know Processing time is approximately 10-15 minutes per video depending on length Cost per video is roughly $1.00 (transcription $0.65, AI generation $0.35) YouTube captions take 10-60 minutes to generate after upload - the workflow includes automatic polling to check when captions are ready Manual steps still required: video clipping (using provided timestamps), social media posting, and YouTube A/B test setup How it works When a video is uploaded to Google Drive, the workflow automatically triggers and creates an Airtable record The video URL is sent to AssemblyAI (via Apify) for transcription with H:MM:SS.mmm timestamps GPT-4o-mini analyzes the transcript and generates 3 title variations optimized for A/B testing When you click "Generate thumbnail" in Airtable, your prompt is optimized and sent to Kie.ai's Nano Banana Pro model with 2 reference images for consistent branding After uploading to YouTube, the workflow polls YouTube's API every 5 minutes to check if auto-generated captions are ready Once captions are available, click "Generate clips" and Grok 4.1 Fast analyzes the transcript to identify 3-8 elite clips (45+ seconds each) with proper start/end boundaries and action-oriented captions GPT-4o-mini generates a YouTube description with chapter timestamps based on the transcript All outputs are saved to Airtable: titles, thumbnail, clip timestamps with captions, and description How to use Duplicate the provided Airtable base template and connect it to your n8n instance Create a Google Drive folder for uploading edited videos After activating the workflow, copy webhook URLs and paste them into Airtable button formulas and automations Upload your edited video to the designated Google Drive folder to trigger the system The workflow automatically generates titles and begins transcription Add your thumbnail prompt and 2 reference images to Airtable, then click "Generate thumbnail" Upload the video to YouTube as unlisted, paste the video ID into Airtable, and check the box to trigger clip generation Use the provided timestamps to manually clip videos in your editor Copy titles, thumbnail, clips, and description from Airtable to publish across platforms Requirements Airtable account (Pro plan recommended for automations) Google Drive for video upload monitoring Apify account for video transcription via AssemblyAI actor OpenAI API key for title and description generation (GPT-4o-mini) OpenRouter API key for clip identification (Grok 4.1 Fast) Kie.ai account for AI thumbnail generation (Nano Banana Pro model) YouTube Data API credentials for caption polling Customising this workflow Tailor the system prompts to your content niche by asking Claude to adjust them without changing the core structure Modify the clip identification criteria (length, caption style, number of clips) in the Grok prompt Adjust thumbnail generation style by updating the image prompt optimizer Add custom fields to Airtable for tracking performance metrics or additional metadata Integrate with additional platforms like TikTok or Instagram APIs for automated posting

Who is this for? This workflow is ideal for Gmail users and teams who receive a high volume of emails and want to streamline inbox management. It suits professionals seeking to organize messages automatically, including sales teams, project managers, support staff, and anyone who benefits from automated email categorization. What problem is this workflow solving? / Use case Manually labeling emails is time-consuming and can lead to inconsistent organization. This automated n8n workflow uses Gmail and OpenAI to analyze incoming messages and apply the appropriate labels, such as "Quotation", "Inquiry", "Project progress", and "Notification", based on content—improving productivity and ensuring important messages are prioritized. What this workflow does The workflow retrieves new Gmail messages, analyzes their content with OpenAI, and automatically assigns pre-defined Gmail labels that match the email’s intent. This ensures emails are sorted efficiently using AI-powered content analysis and Gmail’s labeling system. Setup Ensure Gmail labels (e.g., "Quotation", "Inquiry") are created in your Gmail account. Connect your Gmail and OpenAI accounts as credentials in n8n. Import the workflow into your n8n instance and update node configurations to match your Gmail label names. How to customize this workflow to your needs Edit or add Gmail labels both in your Gmail account and within the workflow logic. Adjust the prompt or parameters sent to OpenAI to better match your categorization style. Expand or refine the list of label categories to fit your team’s or business’s requirements.

How it works: Accesses a target website, searches for new PDFs, and downloads them automatically. Extracts content from each PDF and sends it to an AI for summarization. Delivers the AI-generated summary directly to a Discord channel. Marks processed URLs in Google Sheets to avoid duplicates. Set up steps: Configure the website URL in the HTTP Request node. Connect to Google Cloud API (enable Drive & Sheets) and link your spreadsheet. Set up an OpenRouter API key and choose your preferred AI model. Create a Discord webhook for notifications.

📘 Description This workflow analyzes real-time stock market sentiment and intent from public social media discussions and converts those signals into operations-ready actions. It exposes a webhook endpoint where a stock-market–related query can be submitted (for example, a stock, sector, index, or market event). The workflow then scans Twitter/X and Instagram for recent public discussions that indicate buying interest, selling pressure, fear, uncertainty, or emerging opportunities. An AI agent classifies each signal by intent type, sentiment, urgency, and strength. These insights are transformed into a prioritized Asana task for market or research teams and a concise Slack alert for leadership visibility. Built-in validation and error handling ensure reliable execution and fast debugging. This automation removes the need for manual social monitoring while keeping teams informed of emerging market risks and opportunities. ⚠️ Deployment Disclaimer This template is designed for self-hosted n8n installations only. It relies on external MCP tools and custom AI orchestration that are not supported on n8n Cloud. ⚙️ What This Workflow Does (Step-by-Step) 🌐 Receive Stock Market Query (Webhook Trigger) Accepts an external POST request containing a stock market query. 🧾 Extract Stock Market Query from Payload Normalizes and prepares the query for analysis. 🔎 Analyze Social Media for Stock Market Intent (AI) Scans public Twitter/X and Instagram posts to detect actionable market intent signals. 📡 Social Intelligence Data Fetch (MCP Tool) Retrieves relevant social data from external intelligence sources. 🧠 Transform Market Intent Signals into Ops-Ready Actions (AI) Structures insights into priorities, summaries, and recommended actions. 🧹 Parse Structured Ops Payload Validates and safely parses AI-generated JSON for downstream use. 📋 Create Asana Task for Market Signal Review Creates a prioritized task with key signals, context, and recommendations. 📣 Send Market Risk & Sentiment Alert to Slack Delivers an executive-friendly alert summarizing risks or opportunities. 🚨 Error Handler → Slack Alert Posts detailed error information if any workflow step fails. 🧩 Prerequisites • Self-hosted n8n instance • OpenAI and Azure OpenAI API credentials • MCP (Xpoz) social intelligence credentials • Asana OAuth credentials • Slack API credentials 🛠 Setup Instructions Deploy the workflow on a self-hosted n8n instance Configure the webhook endpoint and test with a sample query Connect OpenAI, Azure OpenAI, MCP, Asana, and Slack credentials Set the correct Asana workspace and project ID Select the Slack channel for alerts 🛠 Customization Tips • Adjust intent and sentiment classification rules in AI prompts • Modify task priority logic or due-date rules • Extend outputs to email reports or dashboards if required 💡 Key Benefits ✔ Real-time market sentiment detection from social media ✔ Converts unstructured signals into actionable tasks ✔ Provides leadership-ready Slack alerts ✔ Eliminates manual market monitoring ✔ Built-in validation and error visibility 👥 Perfect For Market research teams Investment and strategy teams Operations and risk teams Founders and analysts tracking market sentiment

Who is this for? This template is ideal for DevOps engineers, automation specialists, and n8n users who manage multiple workflows and want a reliable version control system for backups. It’s especially useful for teams collaborating via GitHub. What problem is this workflow solving? Manually backing up n8n workflows to GitHub can be time-consuming and error-prone. This workflow solves that by automating the backup of new and updated n8n workflows, ensuring your GitHub repository always reflects the latest changes. What this workflow does Retrieves all workflows from your local n8n instance. Decodes their content and compares it with existing GitHub files. Detects newly created or updated workflows. Creates a new Git branch and commits changes. Opens a pull request (PR) to the main branch. Sends a Slack notification when the PR is created. The system uses GitHub API, n8n, Merge, Set, and Slack nodes for full automation. Setup GitHub credentials: Add your GitHub API credentials in n8n. Slack integration: Connect your Slack Bot token if you want PR notifications. Repository details: Update github_owner, repo_name, and workflow directory path in the “Define Local Variables” node. n8n API key - Check this doc How to customize this workflow to your needs Change the workflow directory from workflows/ to a custom path. Modify the Slack message or add email notification support. Add filters to back up only specific workflows based on naming or tags. Adjust branch naming conventions or use different GitHub base branches. This workflow provides a seamless backup and versioning pipeline, minimizing manual Git interactions and supporting collaborative automation development.

Create AI screencast videos with VEED and automated slides Overview This n8n workflow automatically generates presentation-style "screen recording" videos with AI-generated slides and a talking head avatar overlay. You provide a topic and intention, and the workflow handles everything: scriptwriting, slide generation, avatar creation, voiceover, and video composition. Output: Horizontal (16:9) AI-generated videos with animated slides as the main content and a lip-synced avatar in picture-in-picture, ready for YouTube, LinkedIn, or professional presentations. What It Does Topic + Intention → Claude writes script → Parallel processing: ├── OpenAI generates avatar → ElevenLabs voiceover → VEED lip-sync └── FAL Flux Pro generates slides → Creatomate composites everything → Saved to Google Drive + logged to Sheets Pipeline Breakdown | Step | Tool | What Happens | |------|------|--------------| | 1. Script Generation | Claude Sonnet 4 | Creates hook, script (25-40 sec), slide prompts, caption, and avatar description | | 2. Avatar Generation | OpenAI gpt-image-1 | Generates photorealistic portrait image (1024×1536) | | 3. Slide Generation | FAL Flux Pro | Creates 5-7 professional slides (1920×1080) with text overlays | | 4. Voiceover | ElevenLabs | Converts script to natural speech (multiple voice options) | | 5. Talking Head | VEED Fabric 1.0 | Lip-syncs avatar to audio, creates 9:16 talking head video | | 6. Video Composition | Creatomate | Combines slides + avatar in 16:9 PiP layout | | 7. Storage | Google Drive | Uploads final MP4 | | 8. 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 | | ElevenLabs | API Key | https://elevenlabs.io/app/settings/api-keys | | FAL.ai | API Key | https://fal.ai/dashboard/keys | | Creatomate | API Key | https://creatomate.com/dashboard/settings | > ⚠️ 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 | |------|-----------------|---------| | 🎬 Generate Talking Head (VEED) | FAL.ai API | VEED video rendering | | 📤 Upload to Drive | Google Drive OAuth2 | Store final videos | | 📝 Log to Sheets | Google Sheets OAuth2 | Track all generated content | Configuration Options Edit the ⚙️ Workflow Configuration node to customize: { // 📝 CONTENT SETTINGS topic: "How AI is transforming content creation", intention: "informative", // informative, lead_generation, disruption brand_name: "YOUR_BRAND_NAME", target_audience: "sales teams and marketers", trending_hashtags: "#AIvideo #ContentCreation #VideoMarketing", // 🎨 SLIDE STYLE slide_style: "vibrant_colorful", // See slide styles below // 🎥 VIDEO SETTINGS video_resolution: "720p", // VEED only supports 720p seconds_per_slide: 6, // How long each slide shows // 🖼️ BACKGROUND (Optional) background: "", // URL, gradient array, or empty // 🔑 API KEYS (Required) anthropic_api_key: "YOUR_ANTHROPIC_API_KEY", openai_api_key: "YOUR_OPENAI_API_KEY", elevenlabs_api_key: "YOUR_ELEVENLABS_API_KEY", creatomate_api_key: "YOUR_CREATOMATE_API_KEY", fal_api_key: "YOUR_FAL_API_KEY", // 🎤 VOICE SELECTION voice_selection: "susie", // cristina, enrique, susie, jeff, custom // 🎨 AVATAR OPTIONS (Optional) custom_avatar_description: "", // Leave empty for AI-generated custom_avatar_image_url: "", // Direct URL to use existing image // 📝 CUSTOM SCRIPT (Optional) custom_script: "" // Leave empty for AI-generated } Slide Style Options | Style | Description | Best For | |-------|-------------|----------| | dark_professional | Dark gradients, white text, sleek look | Tech, SaaS, premium brands | | light_modern | Light backgrounds, dark text, clean | Corporate, educational | | vibrant_colorful | Bold colors, energetic, eye-catching | Social media, startups | | minimalist | Lots of whitespace, simple, elegant | Luxury, professional services | | tech_corporate | Blue tones, geometric shapes | Enterprise, B2B | Background Options | Type | Example | Description | |------|---------|-------------| | None | "" | Full bleed layout, slides take 78% width | | URL | "https://example.com/bg.jpg" | Image background with margins | | Gradient | ["#ff6b6b", "#feca57", "#48dbfb"] | Gradient background with margins | Voice Options | Voice | Language | Description | |-------|----------|-------------| | cristina | Spanish | Female voice | | enrique | Spanish | Male voice | | susie | English | Female voice (default) | | jeff | English | Male voice | | custom | Any | Use your ElevenLabs voice clone ID | 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 Custom Avatar Description Leave custom_avatar_description empty to let Claude decide, or provide your own: custom_avatar_description: "female marketing influencer, cool, working in tech" 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 Avatar Image URL Skip avatar generation entirely by providing a direct URL: custom_avatar_image_url: "https://example.com/my-avatar.png" > Image should be portrait orientation, high quality, with the subject looking at camera. Custom Script Leave custom_script empty to let Claude write it, or provide your own: custom_script: "This is my custom script. AI is changing how we create content..." Guidelines for custom scripts: Keep it 25-40 seconds when read aloud (60-100 words) Avoid special characters for TTS compatibility Write naturally, as if speaking Behavior Matrix | custom_avatar_description | custom_avatar_image_url | custom_script | What Claude Generates | |---------------------------|-------------------------|---------------|----------------------| | Empty | Empty | Empty | Avatar + Script + Slides + Caption | | Provided | Empty | Empty | Script + Slides + Caption | | Empty | Provided | Empty | Script + Slides + Caption | | Empty | Empty | Provided | Avatar + Slides + Caption | | Provided | Provided | Provided | Slides + Caption only | Video Layout The final video uses a picture-in-picture (PiP) layout: Without Background (Full Bleed) ┌─────────────────────────────────┬──────┐ │ │ │ │ │ │ │ SLIDES (78%) │AVATAR│ │ │(22%) │ │ │ │ │ │ │ └─────────────────────────────────┴──────┘ With Background (Margins + Rounded Corners) ┌─────────────────────────────────────────┐ │ BG ┌───────────────────────────┐ ┌────┐ │ │ │ │ │ │ │ │ │ SLIDES (74%) │ │AVA │ │ │ │ │ │TAR │ │ │ │ │ │20% │ │ │ └───────────────────────────┘ └────┘ │ └─────────────────────────────────────────┘ Output Per Video Generated | Asset | Format | Location | |-------|--------|----------| | Final Video | MP4 (1920×1080, 60fps) | Google Drive folder | | Avatar Image | PNG (1024×1536) | tmpfiles.org (temporary) | | Slide Images | PNG (1920×1080) | FAL CDN (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 | | slide_style | Visual style used | | content_theme | 2-3 word theme summary | | script | Full voiceover script | | caption | Ready-to-post caption with hashtags | | num_slides | Number of slides generated | | video_url | Google Drive link to final video | | avatar_video_url | VEED talking head video URL | | audio_url | Temporary audio URL | | 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 (1024×1536) | ~$0.04-0.08 | | FAL Flux Pro | 5-7 images (1920×1080) | ~$0.10-0.15 | | ElevenLabs | 100 words | $0.01-0.02 | | VEED/FAL.ai | 1 video render | ~$0.10-0.20 | | Creatomate | 1 video composition | ~$0.10-0.20 | | Total | | ~$0.35-0.65 per video | > Costs vary based on script length and current API pricing. Setup Checklist Step 1: Import Workflow [ ] Import create-ai-screencast-videos-with-veed-and-automated-slides.json into n8n Step 2: Configure API Keys [ ] Open the ⚙️ Workflow Configuration node [ ] Replace all YOUR_*_API_KEY placeholders with your actual API keys [ ] Verify your OpenAI organization at https://platform.openai.com/settings/organization/general Step 3: Connect n8n Credentials [ ] Click on 🎬 Generate Talking Head (VEED) node → Add FAL.ai credential [ ] Click on 📤 Upload to Drive node → Add Google Drive OAuth2 credential [ ] Click on 📝 Log to Sheets node → Add Google Sheets OAuth2 credential Step 4: Configure Storage [ ] Update the 📤 Upload to Drive node with your Google Drive folder URL [ ] Update the 📝 Log to Sheets node with your Google Sheets URL [ ] Create column headers in your Google Sheet (see Output section) Step 5: Customize Content [ ] Update topic, brand_name, target_audience, and trending_hashtags [ ] Choose your preferred slide_style and voice_selection [ ] Optionally configure background, custom_avatar_description, and/or custom_script Step 6: Test [ ] Execute the workflow [ ] Check Google Drive for the output video [ ] Verify metadata was logged to Google Sheets MCP Integration (Optional) This workflow can be exposed to Claude Desktop via n8n's Model Context Protocol (MCP) integration. To enable MCP: Add a Webhook Trigger node to the workflow (in addition to the Manual Trigger) Connect it to the ⚙️ Workflow Configuration node Go to Settings → Instance-level MCP → 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 1-3 minutes for the talking head. Creatomate processing**: Takes 30-60 seconds for composition. Total workflow time**: ~3-5 minutes per video. Content Considerations Scripts are optimized for 25-40 seconds (TTS-friendly) Avatar images are AI-generated (not real people) Slides are dynamically generated based on script length Slide count: 5-7 slides depending on script duration Best Practices Start simple: Test with default settings before customizing Review scripts: Claude generates good content but review before posting Monitor costs: Check API usage dashboards weekly Use backgrounds: Adding a background image creates a more polished look Match voice to content: Use Spanish voices for Spanish content 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 binary field | | JSON parse error from Claude | Workflow has fallback content; check Claude node output | | Slides not matching script | Increase seconds_per_slide for fewer slides | | Avatar cut off in PiP | Avatar is designed for right-side placement | | MCP "Server disconnected" | Install supergateway globally: npm install -g supergateway | | Render timeout | Increase wait time in "⏳ Wait for Render" node | Version History | Version | Date | Changes | |---------|------|---------| | 2.1 | Jan 2026 | Renamed workflow, improved documentation with section sticky notes, consolidated setup information | | 2.0 | Jan 2026 | Added dynamic slide count, background options, FAL Flux Pro for slides, improved PiP layout | | 1.0 | Jan 2026 | Initial release with fixed slide count, basic composition | Credits Built with: n8n** - Workflow automation Anthropic Claude** - Script & slide prompt generation OpenAI** - Avatar image generation FAL.ai** - Slide image generation (Flux Pro) ElevenLabs** - Voice synthesis VEED Fabric** - AI lip-sync video rendering Creatomate** - Video composition Google Workspace** - Storage & logging

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Who's it for Content creators, marketers, and researchers who need to monitor multiple RSS feeds and get AI-generated summaries without manual work. How it works This workflow automatically monitors RSS feeds, filters new articles from the last X days, checks for duplicates, and generates structured AI summaries. It fetches full article content, converts HTML to markdown, and uses Gemini AI to create consistent summaries with quick takeaways, key points, and practical insights. All data is saved to Google Sheets for easy access and sharing. The system processes RSS feeds in batches, ensuring no duplicate articles are processed twice by checking existing URLs in your Google Sheets. Each new article gets a comprehensive AI summary that includes the main message, key takeaways, important points, and practical applications. Requirements Google Sheets access OpenRouter API key for Gemini AI model or other language model RSS feed URLs to monitor How to set up Copy the template Google Sheet, add your RSS feeds in the "RSS FEEDS" tab, configure Google Sheets and OpenRouter credentials in n8n, and adjust the time filter in the Settings node. The workflow can run manually or on schedule every hour. How to customize Modify AI prompts for different summary styles, change the time filter duration, add more data fields to Google Sheets, or switch to a different AI model in the LLM Chat Model node.

Complete AI support system using website data (RAG pipeline) This template provides a full end-to-end Retrieval-Augmented Generation (RAG) system using n8n. It includes two connected workflows: A data ingestion pipeline that crawls a website and stores its content in a vector database. A customer support chatbot that retrieves this knowledge and answers user queries in real time. Together, these workflows allow you to turn any public website into an intelligent AI-powered support assistant grounded in real business data. Use cases AI customer support chatbot for your website Internal company knowledge assistant Product FAQ automation Helpdesk or IT support bot AI receptionist for services Semantic search over company content How it works Ingestion workflow Discover all URLs from a website sitemap. Filter and normalize the URLs. Fetch each page and extract readable text. Clean HTML into plain text. Split text into overlapping chunks. Generate embeddings using OpenAI. Store vectors in Pinecone with metadata. Chatbot workflow A user sends a message via chat webhook. The agent queries Pinecone for relevant knowledge. Retrieved content is passed to OpenAI. OpenAI generates a grounded response. Short-term memory maintains conversation context. How to use Step 1 – Run ingestion Set your target website URL. Add Firecrawl, OpenAI, and Pinecone credentials. Create a Pinecone index. Execute the ingestion workflow. Wait until all pages are indexed. Step 2 – Run chatbot Deploy the chatbot workflow. Set the same Pinecone index and namespace. Copy the chat webhook URL. Connect it to a website, chat widget, or WhatsApp bot. Start chatting with your AI assistant. Requirements Firecrawl account OpenAI API key Pinecone account and index Public website to crawl Optional: frontend chat interface Good to know The chatbot never answers from memory for business data. All company knowledge comes from Pinecone. If Pinecone returns nothing, the bot fails safely. HTML cleaning is basic and can be replaced with: Mozilla Readability Jina Reader Unstructured Chunk size and overlap affect retrieval quality. Pinecone can be replaced with: Qdrant Weaviate Supabase Vector Chroma Customising this workflow You can extend this system by: Adding PDF or document loaders Scheduling ingestion daily or weekly Connecting CRM or ticketing systems Adding appointment booking tools Switching to local or open-source models Adding multilingual support Storing raw content in a database Adding feedback or logging What this n8n template demonstrates Real-world RAG architecture Web crawling pipelines Text chunking strategies Vector database integration AI agent orchestration Memory-controlled conversations Production-grade AI support systems End-to-end AI infrastructure with n8n Architecture overview This template follows a modern AI system design: Website → Ingestion → Embeddings → Pinecone → Retrieval → OpenAI → User It separates: Data preparation (offline) Knowledge storage Runtime inference This makes the system scalable, maintainable, and safe for production use. Need a custom setup? If you want a similar AI system built for your business (custom data sources, CRM integration, WhatsApp bots, booking systems, dashboards, or private deployments), feel free to reach out at dinakars2003@gmail.com. I help companies design and deploy production-ready AI workflows.

The Scrape and Analyze Amazon Product Info with Decodo + OpenAI workflow automates the process of extracting product information from an Amazon product page and transforming it into meaningful insights. The workflow then uses OpenAI to generate descriptive summaries, competitive positioning insights, and structured analytical output based on the extracted information. Disclaimer Please note - This workflow is only available on n8n self-hosted as it’s making use of the community node for the Decodo Web Scraping Who this is for? This workflow is ideal for: E-commerce product researchers Marketplace sellers (Amazon, Flipkart, Shopify, etc.) Competitive intelligence teams Product comparison bloggers and reviewers Pricing and product analytics engineers Automation builders needing AI-powered product insights What problem is this workflow solving? Manually extracting Amazon product details, ads, pricing, reviews, and competitive signals is: Time-consuming Requires switching across tools Difficult to analyze at scale Not structured for reporting Hard to compare products objectively This workflow automates: Web scraping of Amazon product pages Extraction of product features and ad listings AI-generated product summaries Competitive positioning analysis Generation of structured product insight output Export to Google Sheets for tracking and reporting What this workflow does This workflow performs an end-to-end product intelligence pipeline, including: Data Collection Scrapes an Amazon product page using Decodo Retrieves product details and advertisement placements Data Extraction Extracts: Product specs Key feature descriptions Ads data Supplemental metadata AI-Driven Analysis Generates: Descriptive product summary Competitive positioning insights Structured product insight schema Data Consolidation Merges descriptive, analytical, and structured outputs Export & Persistence Aggregates results Writes final dataset to Google Sheets for: tracking comparison reporting product research archives Setup Prerequisites If you are new to Decode, please signup on this link visit.decodo.com n8n instance** Decodo API credentials** OpenAI API credentials** Make sure to install the Decodo Community Node. Required Credentials Decodo API Go to Credentials Add Decodo API Enter API key Save as: Decodo Credentials account OpenAI API Go to Credentials Select OpenAI Enter API key Save as: OpenAi account Google Sheets Add Google Sheets OAuth Authorize via Google Save as desired account Inputs to configure Modify in Set the Input Fields node: product_url = https://www.amazon.in/Sony-DualSense-Controller-Grey-PlayStation/dp/B0BQXZ11B8 How to customize this workflow to your needs You can easily adapt this workflow for various use cases. Change the product being analyzed Modify: product_url Change AI model In OpenAI nodes: Replace gpt-4.1-mini Use Gemini, Claude, Mistral, Groq (if supported) Customize the insight schema Edit Product Insights node to include: sustainability markers sentiment extraction pricing bands safety compliance brand comparisons Expand data extraction You may extract: product reviews FAQs Q&A seller information delivery and logistics signals Change output destination Replace Google Sheets with: PostgreSQL MySQL Notion Slack Airtable Webhook delivery CSV export Turn it into a batch processor Loop over: multiple ASINs category listings search results pages Summary This workflow provides a complete automated product intelligence engine, combining Decodo’s scraping capabilities with OpenAI’s analytical reasoning to transform Amazon product pages into structured insights, competitive analysis, and summarized evaluations automatically stored for reporting and comparison.

🔥 Daily Web Scraper & AI Summary with Firecrawl + Email Automation Need to extract and summarize web content from a site that doesn’t have an API? This workflow runs daily to scrape a web page using Firecrawl, summarize the content with OpenAI, and send it directly to your email — fully automated. Watch Full Video Step-by-step Tutorial Here: https://www.youtube.com/@Automatewithmarc 🔧 How It Works Daily Trigger – Starts the workflow every 24 hours. Firecrawl Node – Crawls and extracts structured data from any web page you specify. OpenAI Node (Optional) – Processes and summarizes the raw content using a prompt you control. Gmail Node – Sends the final summary or content snapshot to your email inbox. ✅ Perfect For Business analysts tracking daily market or industry news Researchers and founders automating competitive intelligence Anyone who wants web data delivered without coding or scraping scripts 🪜 Setup Instructions Firecrawl API Key – Sign up and insert your key in the credentials. Update Target URL – Edit the URL in the Firecrawl node to your desired site. Customize the Prompt – Tailor the OpenAI prompt to extract the insights you want. Connect Gmail – Add your Gmail credentials and set your recipient email. 🧰 Built With Firecrawl (Web scraping without code) OpenAI (For summarizing and insight extraction) Gmail (Automated notifications) n8n (Workflow automation engine)