Go to example tasks
Turn a YouTube channel into a RAG dataset
Point it at any channel and get every video transcribed into overlapping, timestamped chunks ready for a vector database. Each chunk keeps its start and end time, so a retrieved passage links back to the exact second in the video.
YouTube Transcript Scraper — Subtitles, SRT/VTT & RAG Chunksspool/youtube-transcript-api
Video
Channel
Lang
Auto
+5 fieldsTextNumberBooleanListObject
Input
YouTube videos, channels or playlists(required):https://www.youtube.com/@3blue1brown
Max videos per channel/playlist:25
Preferred languages:en
Chunk size (characters):1000
Chunk overlap (characters):150
Output fields
Video
Channel
Lang
Auto
Words
Chars
Chunks
Seconds
URL
Sign up on Apify01
Create your Apify account to access the YouTube Transcript Scraper — Subtitles, SRT/VTT & 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.
