YouTube Dataset of Transcripts for AI and RAG
Build a transcript dataset from one channel for embeddings, RAG or fine-tuning prep: clean text, segments and video metadata per row.
Input
Output fields
Sign up on Apify or log in
The YouTube Channel Transcript Scraper — 500 Videos, One URL Actor is ready to run with the inputs already set for "YouTube Dataset of Transcripts for AI and RAG". Sign up or log in and you'll land in Apify Console with a copy of this exact task.
Start the "YouTube Dataset of Transcripts for AI and RAG" task
The YouTube Channel Transcript Scraper — 500 Videos, One URL Actor will start running based on the input automatically. You can also change all the input fields, like channel or playlist, maximum videos per run, and more, to match your specific use case.
Receive the "YouTube Dataset of Transcripts for AI and RAG" output
Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as video id, title, channel title, and more.
Integrate into your workflow
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "YouTube Dataset of Transcripts for AI and RAG" task via API.

Integrate "YouTube Dataset of Transcripts for AI and RAG" into your workflow
Connect "YouTube Dataset of Transcripts for AI and RAG" with 100+ integrations, or run it via API or MCP.
Webhook
n8n
Make
Zapier
Airbyte
Keboola
IFTTT
Hubspot
GDrive
Gmail
Apify MCP
GitHub
Slack
LangChain
LlamaIndex
Flowise
Pinecone
OpenAI
Mastra
Clay
The YouTube RAG dataset preset returns up to 30 videos from @stanford in English, one row each: transcript text, timestamped segments, word count, duration, title and channel fields. maxVideos goes up to 500.
In the YouTube RAG dataset task, paste a channel or playlist and run. transcriptText feeds embeddings and segments keeps timestamps, so each chunk can point back to its moment.
YouTube Transcript Scraper returns transcripts verbatim and does not rewrite them, so plan your own cleanup step. The Issues view lists notFound and fallback rows worth a second look.
A weekly schedule of the YouTube RAG dataset task with Published after adds only new videos. Videos already delivered skip the per-row event; the $0.005 start still applies.
YouTube transcripts are third-party content. YouTube Transcript Scraper returns them verbatim from public subtitle tracks, and you stay responsible for copyright and YouTube's terms when they feed an AI index.
Each YouTube Transcript Scraper run costs a $0.005 start, then a RAG dataset is charged per delivered row: $0.009 on the free plan, $0.007 or less on paid plans. Cache hits and failures add no row charge, but the start still applies.