automations / n8n · updated 2026-07-20

YouTube channel → transcript corpus

Paste a channel URL or @handle and get one item per video with the full transcript as plain text — the two-actor answer to "get transcripts for a whole channel." The channel actor lists the videos, the transcript actor reads each one, and captionless or unplayable videos exit as typed rows instead of stopping the corpus build.

Get the workflow on GitHub YouTube Channel Scraper docsYouTube Transcript Scraper docs

A 50-video channel costs at most $0.18 — $0.025 to list it and $0.15 for the transcripts; captionless videos are $0.

What's inside

  1. 1.Run workflow (manual trigger — swap for a schedule to keep the corpus current)
  2. 2.List channel videos (HTTP Request → channel scraper, one item per video)
  3. 3.Split channel rows (IF on {{ $json.success }}; a bad handle exits as a typed row)
  4. 4.Collect video IDs (Code node: gathers the IDs and batches them 50 per transcript run)
  5. 5.Get transcripts (HTTP Request → transcript scraper, one item per video)
  6. 6.Split transcript rows (IF on {{ $json.success }})
  7. 7.Transcript text (true branch: video_id, title, and the segments joined to plain text)
  8. 8.Transcript / channel failure rows (false branches: code, request_id — not billed)

Set it up

Open the workflow on GitHub (button above), click Raw and copy that URL, then in n8n: Workflow → Import from URL. Replace YOUR_APIFY_TOKEN in BOTH HTTP nodes (List channel videos and Get transcripts). Put your channel in channelUrls — a URL, @handle, or UC… ID — and raise maxResults to walk deeper than 50 videos. The token comes from Apify Console → Settings → API tokens; the free tier works, and the run bills per delivered row on your Apify account.

Ways to extend it

  • Wire Transcript text into a vector store or Notion to make the channel searchable — the text field is ready to embed.
  • Add an OpenAI node after the true branch to summarize each video before saving.
  • Swap the manual trigger for a weekly schedule and dedup on video_id downstream to only process new uploads.
  • Duplicate List channel videos with the Shorts scraper URL to include the channel's Shorts in the same corpus.

Going deeper: the n8n transcripts guide — the full HTTP-node walkthrough, the async pattern for big batches, and the community-node alternative. Actor pricing: what a YouTube Channel Scraper run costs, what a YouTube Transcript Scraper run costs. Error codes the failure branch can carry: the error-code reference.