🎬 Generate social videos with AI avatars using VEED, Claude, and OpenAI

⚡ 243 views · 🎬 Content Creation & Video

💡 Pro Tip — Since TikTok doesn’t have a public API, getting data usually means fragile HTTP scraping. ScraperNode is a community node that gives you clean JSON for TikTok profiles, videos, and comments — drop it into your workflow and skip the parsing.

Description

Generate social videos with AI avatars using VEED and Claude

Overview

This n8n workflow automatically generates TikTok/Reels-ready talking head videos from scratch. You provide a topic and intention, and the workflow handles everything: scriptwriting, avatar generation, voiceover creation, and video rendering.

Output: Vertical (9:16) AI-generated videos with lip-synced avatars, ready for social media posting.

What It Does

Topic + Intention → Claude writes script → OpenAI generates avatar → OpenAI creates voiceover → VEED renders video → Saved to Google Drive + logged to Sheets

Pipeline Breakdown

Required Connections

API Keys (entered in Configuration node)

> ⚠️ OpenAI Note: gpt-image-1 requires organization verification. Go to https://platform.openai.com/settings/organization/general to verify.

n8n Credentials (connect in n8n)

Configuration Options

Edit the ⚙️ Workflow Configuration node to customize. The configuration uses a JSON format:

{
  "topic": "AI video creation tools",
  "intention": "informative",
  "brand_name": "YOUR_BRAND_NAME",
  "target_audience": "content creators and marketers",
  "trending_hashtags": "#AIvideo #ContentCreation #VideoMarketing #AItools #TikTokTips",
  "num_videos": 1,
  "anthropic_api_key": "YOUR_ANTHROPIC_API_KEY",
  "openai_api_key": "YOUR_OPENAI_API_KEY",
  "video_resolution": "720p",
  "video_aspect_ratio": "9:16",
  "custom_avatar_description": "",
  "custom_script": ""
}

Configuration Fields Explained

Intention Types

Custom Avatar & Script Options

The workflow supports flexible content generation - you can let Claude generate everything, or provide your own inputs.

Custom Avatar Description

Leave custom_avatar_description empty to let Claude decide, or provide your own:

"custom_avatar_description": "a female influencer in her 30s, with a coworking space in the background, attractive but charismatic"

Examples:

• "a woman in her 20s with gym clothes"
• "a bearded man in his 30s wearing a hoodie"
• "a professional woman with glasses in business casual"

Custom Script

Leave custom_script empty to let Claude write it, or provide your own:

"custom_script": "This is my custom script. VEED is a great platform for creating videos like this. You can try it too!"

Guidelines for custom scripts:

• Keep it 30-45 seconds when read aloud
• Maximum ~450 characters
• Avoid special characters for TTS compatibility
• Write naturally, as if speaking

Behavior Matrix

Content Angles (auto-rotated)

When generating multiple videos, the workflow automatically varies the approach:

Output

Per Video Generated

Google Sheets Columns

Estimated Costs Per Video

> Costs vary based on script length and current API pricing.

Setup Checklist

Step 1: Import Workflow

• Import generate-social-videos-with-ai-avatars-using-veed-and-claude.json into n8n

Step 2: Configure API Keys

• Open the ⚙️ Workflow Configuration node
• Replace YOUR_ANTHROPIC_API_KEY with your actual Anthropic API key
• Replace YOUR_OPENAI_API_KEY with your actual OpenAI API key
• Verify your OpenAI organization at https://platform.openai.com/settings/organization/general (required for gpt-image-1)

Step 3: Connect n8n Credentials

• Click on �� Generate Video (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: topic, intention, brand_name, content_theme, script_audio, script_image, caption, image_url, audio_url, video_url, status, created_at

Step 5: Customize Content

• Update topic, brand_name, target_audience, and trending_hashtags
• Optionally add custom_avatar_description and/or custom_script

Step 6: Test

• Set num_videos: 1 for initial testing
• Execute the workflow
• Check Google Drive for the output video
• Verify metadata was logged to Google Sheets

MCP Integration (Optional)

This workflow can also be exposed to Claude Desktop via n8n’s Model Context Protocol (MCP) integration, allowing you to generate videos through natural language prompts.

To enable MCP:

1. Add a Webhook Trigger node to the workflow (in addition to the Manual Trigger)
2. Connect it to the same ⚙️ Workflow Configuration node
3. Go to Settings → Instance-level MCP → Enable the workflow
4. Configure Claude Desktop with your n8n MCP server URL

Claude Desktop Configuration (Windows):

{
  "mcpServers": {
    "n8n-mcp": {
      "command": "supergateway",
      "args": [
        "--streamableHttp",
        "https://YOUR_N8N_INSTANCE.app.n8n.cloud/mcp-server/http",
        "--header",
        "authorization:Bearer YOUR_MCP_ACCESS_TOKEN"
      ]
    }
  }
}

> Note: Install supergateway globally first: npm install -g supergateway

Limitations & Notes

Technical Limitations

• tmpfiles.org: Temporary file URLs expire after ~1 hour. Final videos are safe in Google Drive.
• VEED processing: Takes 2-5 minutes per video depending on length.
• n8n Cloud network: Some external domains are blocked; workflow uses base64 for images to avoid this.

Content Considerations

• Scripts are optimized for 30-45 seconds (TTS-friendly)
• Avatar images are AI-generated (not real people)
• Captions include hashtags automatically
• Each video in a batch gets a different content angle

Best Practices

1. Start small: Test with 1 video before scaling to 5
2. Review scripts: Claude generates good content but review before posting
3. Monitor costs: Check API usage dashboards weekly
4. Backup sheets: The Google Sheet serves as your content database

Troubleshooting

Version History

Credits

Built with:

• n8n - Workflow automation
• Anthropic Claude - Script generation
• OpenAI - Image & audio generation
• VEED Fabric - AI video rendering
• Google Workspace - Storage & logging

🔗 Nodes Used

Google Sheets, HTTP Request, Google Drive

📥 Import

Download workflow.json and import into n8n: Workflow menu → Import from File

📖 Importing guide · 🔑 Credential setup