Go to example tasks
Turn a YouTube channel into RAG-ready transcript chunks
Pull transcripts for the latest videos of any YouTube channel and get one row per chunk, sized for embeddings, with timestamps and deep links. Drop the dataset into a vector database or LangChain/n8n pipeline.
YouTube Transcript Extractor & API (Bulk + RAG Chunks)agentbuilt/youtube-transcript-bulk
Video ID
Title
Channel
URL
+5 fieldsTextNumberBooleanListObject
Input
Video, channel, or playlist URLs
url:https://www.youtube.com/@lexfridman/videos
Max videos per source:25
Output mode:chunks
Chunk size (approx. tokens):400
Chunk overlap (approx. tokens):40
Output fields
Video ID
Title
Channel
URL
Lang
Duration (s)
Words
Chunks
Status
Sign up on Apify01
Create your Apify account to access the YouTube Transcript Extractor & API (Bulk + RAG Chunks).
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.
