Go to example tasks
YouTube Transcripts for RAG Pipelines
Created by
Chronometrica
Collect clean transcript text and timestamps from supplied YouTube videos for retrieval-augmented generation, semantic search, and citation workflows.
YouTube Transcript Scraper – Clean Text & JSONchronometrica/youtube-transcript-scraper
Platform
Input #
Input URL
Video URL
+32 fieldsTextNumberBooleanListObject
Input
YouTube video URLs or IDs(required):https://www.youtube.com/watch?v=dQw4w9WgXcQ+2
Transcript languages (optional)
Transcript formats:json+2
Include failed input details:true
Output fields
Platform
Input #
Input URL
Video URL
Video ID
Title
Published At
Video Duration (Seconds)
Thumbnail
Channel ID
Channel Name
Channel URL
Language Preferences
Transcript Language
Transcript Language Name
Available Languages
Language Match
Auto-generated
Segments
Text
SRT
VTT
LLM Text
Segments
Words
Characters
First Segment Start (Seconds)
Last Segment End (Seconds)
Transcript Span (Seconds)
Video Coverage Ratio
Status
Status Reason
Error Category
Error Code
Retryable
Scraped At
Sign up on Apify01
Create your Apify account to access the YouTube Transcript Scraper – Clean Text & JSON.
Start the run02
The Actor will start running based on the input automatically.
Receive the output03
Monitor the progress in real-time. You will be notified as soon as your dataset is complete and ready for review.
Integrate into your workflow04
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow.
