Tavily is great at web data. VeedCrawl speaks video.

# Get a transcript from any social video
curl -X POST "https://api.veedcrawl.com/v1/transcript" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
    "mode": "auto"
  }'

// Poll the job ID to get your result
{
  "jobId": "job_abc123",
  "status": "completed",
  "resultJson": {
    "text": "Never gonna give you up, never gonna let you down...",
    "segments": [
      { "start": 0.0, "end": 3.5, "text": "Never gonna give you up" },
      { "start": 3.5, "end": 7.2, "text": "never gonna let you down" }
    ]
  }
}

# Free metadata — no credits consumed
curl "https://api.veedcrawl.com/v1/metadata?url=https://www.tiktok.com/@creator/video/123" \
  -H "x-api-key: YOUR_API_KEY"

{
  "platform": "tiktok",
  "title": "5 AI tools every developer needs",
  "author": "@creator",
  "duration": 62,
  "views": 2100000,
  "likes": 87400,
  "comments": 3200,
  "thumbnail": "https://...",
  "credits_used": 0
}

# Ask a question about what's IN the video
curl -X POST "https://api.veedcrawl.com/v1/extract" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.instagram.com/reel/abc123/",
    "prompt": "Extract all product names and claims made in this video"
  }'

{
  "jobId": "job_xyz789",
  "status": "completed",
  "resultJson": {
    "products": ["iPhone 16 Pro", "Notion", "Arc Browser"],
    "claims": [
      "This app saved me 3 hours a day",
      "Better than any other note-taking tool"
    ],
    "tone": "promotional",
    "cta_present": true
  }
}