YouTube transcripts as plain text for RAG and LLMs
Plain-text transcripts of YouTube videos, one clean string per video, ready to chunk and embed in a RAG pipeline or to summarise with an LLM. The sample reads three talks with outputFormats set to text only, which keeps the items small; add channels or playlists to build a corpus.
Input
Output fields
Sign up on Apify or log in
The YouTube Transcript API — Videos, Channels, Playlists, SRT/VTT Actor is ready to run with the inputs already set for "YouTube transcripts as plain text for RAG and LLMs". Sign up or log in and you'll land in Apify Console with a copy of this exact task.
Start the "YouTube transcripts as plain text for RAG and LLMs" task
The YouTube Transcript API — Videos, Channels, Playlists, SRT/VTT Actor will start running based on the input automatically. You can also change all the input fields, like videos, channels or playlists and output formats, to match your specific use case.
Receive the "YouTube transcripts as plain text for RAG and LLMs" 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, status, 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 transcripts as plain text for RAG and LLMs" task via API.

Integrate "YouTube transcripts as plain text for RAG and LLMs" into your workflow
Connect "YouTube transcripts as plain text for RAG and LLMs" 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
This RAG transcript task sets outputFormats to text, so non_timestamped holds each transcript as one string without timestamps: smaller items, faster reads, ready to chunk. Add json for timestamps.
To build a RAG corpus with this transcript task, put a channel @handle in videoUrls with maxVideosPerSource (up to 5,000), schedule the task and deduplicate on video_id when you embed.
Through the Apify MCP server (mcp.apify.com), an agent in Claude, Cursor or ChatGPT can run this YouTube transcript task, fill videoUrls and read the plain-text items back.
This RAG transcript task returns YouTube's own caption tracks; set languages to pick one. YouTube refused machine translation in every test, so translate non_timestamped with your own LLM step.