omni_extract_url
Extract long-form articles, videos, transcripts, and code from X, TikTok, YouTube, GitHub, or anti-bot pages into clean Markdown. Turns any shared URL into readable text for AI agents.
Instructions
Universal, cookie-free content & transcript extractor for AI Agents. Extracts full long-form X (Twitter) Articles/Tweets, watermark-free Douyin/TikTok videos & photo galleries, YouTube/Bilibili video subtitles/transcripts with timestamps, GitHub READMEs/code, and anti-bot web pages into clean Markdown.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "omni_extract_url"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Target URL or share text containing a URL (X/Twitter, Douyin, TikTok, YouTube, Bilibili, GitHub, or any web page). | |
| api_key | No | Optional OmniExtract API key (omni_live_...) for paid credit packs. | |
| output_format | No | Return formatted Markdown ('markdown') or full structured JSON metadata ('json'). Default: 'markdown'. | markdown |
| include_transcript | No | Whether to extract full video subtitles/transcripts for video URLs (default: true). |