Skip to main content
Add a YouTube source to train your agent on what’s said in a video. A2V2.ai pulls the video’s transcript and indexes it like any other source — useful for webinars, tutorials, talks, and product walkthroughs.

​
Prerequisites

  • An agent (see Create an agent).
  • A public YouTube video that has captions/a transcript available.
  • Enough credits to process the transcript (see Credits).

​
Add a YouTube video

1

Open the Knowledge Base

In the agent sidebar, go to Expertise → Knowledge Base.
2

Open the YouTube tab

Select New Knowledge Item, then open the YouTube tab.
3

Paste the video link

Enter the full YouTube URL.
4

Process the transcript

Confirm. A2V2.ai fetches the transcript, extracts the text, and indexes it. The source shows Processing until it’s done.
5

Wait for Completed

When the status turns Completed, the video’s content is live in your agent.
The YouTube tab of New Knowledge Item with a video URL entered.

​
Options & limits

ItemDetail
InputA public YouTube video URL
RequirementThe video must have a transcript/captions available
Indexed contentThe spoken words (transcript) — not the visuals
UpdatesRe-add or reprocess if the video or its captions change
Videos without captions can’t be transcribed. If a video has no transcript, summarize its key points as Q&A pairs instead.

​
Tips

  • Long videos produce long transcripts — they index fine but consider whether the whole video is relevant.
  • Transcripts capture what was said, so on-screen-only information (slides, diagrams) won’t be included. Add those separately as files or Q&A.

​
Troubleshooting

The video likely has no captions, or it’s private/restricted. Use a public video with captions, or add the content another way.
Only spoken words are transcribed. Add slides or visuals as an uploaded file or Q&A.

Add a website

Add a Q&A

Manage & reprocess sources