Use AI to analyze video content and extract structured data. Provide either a prompt describing what to extract, a JSON Schema for the output format, or both. Supports YouTube, TikTok, Instagram, Twitter/X, and Facebook videos. Returns a job ID for asynchronous processing. Use the /extract/:jobId endpoint to poll for results.
URL to any supported video media. Supports YouTube, TikTok, Instagram, Twitter/X, and Facebook videos.
"https://www.youtube.com/watch?v=dQw4w9WgXcQ"
"https://www.tiktok.com/@user/video/1234567890"
"https://www.instagram.com/reel/ABC123"
Description of what data to extract from the video. Required if schema is not provided.
"Extract the main topics discussed and key takeaways"
JSON Schema defining the structure of data to extract. Required if prompt is not provided.
{
"type": "object",
"properties": {
"topics": {
"type": "array",
"items": { "type": "string" },
"description": "Main topics discussed"
},
"summary": {
"type": "string",
"description": "Brief summary of the video"
}
},
"required": ["topics", "summary"]
}Job created for asynchronous processing
The ID of the job
"123e4567-e89b-12d3-a456-426614174000"