Arcadium Data Scrapers
Home / Use cases / YouTube transcripts for RAG and LLMs

YouTube transcripts for RAG and LLMs

Turn a channel, a course playlist or a list of videos into text an LLM can search and cite, with timed segments for links back to the moment in the video.

Steps

  1. Give the actor channel, playlist or video links, and a date range if you want only recent videos.
  2. Read transcript for the text and segments for timestamps.
  3. Chunk by segment, embed, and store the video URL with the start time for citations.

Actors for this job

YouTube Transcript & Subtitles Scraper

Give it YouTube video, Shorts, channel or playlist links (or plain video IDs) and it returns each transcript (subtitles, captions) as JSON: full text, timed segments, language, whether it was auto-generated, every caption language the video has, and the video's title, channel, length, publish date and views. From $2.48 per 1,000 transcripts (less on higher Apify plans); you pay only for rows you get.

$2.48 per 1,000 transcripts on the Free plan, down to $1.80 on higher plans

  • RAG and knowledge bases: index a channel's or a course playlist's transcripts with timestamps for citations.
  • Summaries and notes: feed transcript to an LLM; wordCount tells you how many tokens to expect.
  • Content and competitor research: what a channel talked about this month (publishedAfter).

Apify Store · Guide · Comparison

YouTube Scraper

Give it YouTube channels, playlists, search terms, hashtags or video links and it returns one JSON row per video or Short: title, channel, exact publish date, duration, views, likes, category, Shorts and live flags, tags, hashtags, description, thumbnail and caption languages. Shorts also get comment count and sound. $3.60 per 1,000 videos, or $1.17 in fast listing mode; you pay only for rows you get.

$3.60 per 1,000 videos on the Free plan, down to $2.16 on higher plans

  • Channel tracking: every new video of your competitors' channels each day, with views and likes.
  • Influencer research: recent output, average views and posting rhythm of a list of channels.
  • Search monitoring: who ranks for your keywords on YouTube (position), and how that changes.

Apify Store · Guide · Comparison

Quick start

Run the first actor from Python (set APIFY_TOKEN):

# pip install apify-client
import os
from apify_client import ApifyClient

client = ApifyClient(os.environ["APIFY_TOKEN"])
run = client.actor("arcadium/youtube-transcripts").call(run_input={
    "urls": ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"],
    "languages": [],
    "captionType": "any",
    "maxVideosPerSource": 10,
    "subtitleFormat": "none",
})
items = client.dataset(run.default_dataset_id).list_items().items  # apify-client 3.x returns a Run object
print(items)

Or give an AI assistant both actors as tools:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com/?tools=arcadium/youtube-transcripts,arcadium/youtube-videos",
      "headers": {
        "Authorization": "Bearer <APIFY_TOKEN>"
      }
    }
  }
}