extract_youtube_transcript
Extract transcripts from YouTube videos with timestamps, translation options, and metadata. Supports captioned videos and includes fallback crawling for reliable access.
Instructions
Extract YouTube transcripts with timestamps. Works with public captioned videos. Supports fallback to page crawl.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | YouTube video URL | |
| languages | No | Language codes in preference order | |
| translate_to | No | Target language for translation | |
| include_timestamps | No | Include timestamps | |
| preserve_formatting | No | Preserve formatting | |
| include_metadata | No | Include video metadata | |
| auto_summarize | No | Summarize long transcripts | |
| max_content_tokens | No | Max tokens before summarization | |
| summary_length | No | 'short'|'medium'|'long' | medium |
| llm_provider | No | LLM provider | |
| llm_model | No | LLM model | |
| enable_crawl_fallback | No | Enable page crawl fallback when API fails | |
| fallback_timeout | No | Fallback crawl timeout in seconds | |
| enrich_metadata | No | Enrich metadata (upload_date, view_count) via page crawl |