> ## Documentation Index
> Fetch the complete documentation index at: https://docs.a2v2.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Add YouTube Videos

> Train your agent on the spoken content of a YouTube video.

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](/building/create-agent)).
* A public YouTube video that has captions/a transcript available.
* Enough credits to process the transcript (see [Credits](/concepts#credits)).

## Add a YouTube video

<Steps>
  <Step title="Open the Knowledge Base">
    In the agent sidebar, go to **Expertise → Knowledge Base**.
  </Step>

  <Step title="Open the YouTube tab">
    Select **New Knowledge Item**, then open the **YouTube** tab.
  </Step>

  <Step title="Paste the video link">
    Enter the full YouTube URL.
  </Step>

  <Step title="Process the transcript">
    Confirm. A2V2.ai fetches the transcript, extracts the text, and indexes it.
    The source shows **Processing** until it's done.
  </Step>

  <Step title="Wait for Completed">
    When the status turns **Completed**, the video's content is live in your agent.
  </Step>
</Steps>

<Frame>
  <img src="https://mintcdn.com/a2v2ai/ItYQQYTHsiiRmr-t/images/knowledge-base/youtube.png?fit=max&auto=format&n=ItYQQYTHsiiRmr-t&q=85&s=9e3cd48158833f5c86f6d0eddc62e5f8" alt="The YouTube tab of New Knowledge Item with a video URL entered." width="1440" height="900" data-path="images/knowledge-base/youtube.png" />
</Frame>

## Options & limits

| Item                | Detail                                                  |
| ------------------- | ------------------------------------------------------- |
| **Input**           | A public YouTube video URL                              |
| **Requirement**     | The video must have a transcript/captions available     |
| **Indexed content** | The spoken words (transcript) — not the visuals         |
| **Updates**         | Re-add or reprocess if the video or its captions change |

<Note>
  Videos without captions can't be transcribed. If a video has no transcript,
  summarize its key points as [Q\&A pairs](/knowledge-base/qa) instead.
</Note>

## Tips

<Tip>
  * 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.
</Tip>

## Troubleshooting

<AccordionGroup>
  <Accordion title="The source failed or returned no transcript">
    The video likely has no captions, or it's private/restricted. Use a public
    video with captions, or add the content another way.
  </Accordion>

  <Accordion title="Answers miss on-screen details">
    Only spoken words are transcribed. Add slides or visuals as an
    [uploaded file](/knowledge-base/upload-files) or [Q\&A](/knowledge-base/qa).
  </Accordion>
</AccordionGroup>

## Related

<CardGroup cols={2}>
  <Card title="Add a website" icon="globe" href="/knowledge-base/website" />

  <Card title="Add a Q&A" icon="comments" href="/knowledge-base/qa" />

  <Card title="Manage & reprocess sources" icon="arrows-rotate" href="/knowledge-base/manage-sources" />
</CardGroup>