# Youtube

The **YouTube Node** allows you to extract the transcript (captions) from a YouTube video, which is useful for summarization, analysis, or further AI processing.

***

### Available Actions

#### Extract YouTube Transcript

This action retrieves the transcript (captions) from a specified YouTube video in your chosen language. It returns both a structured array of transcript segments and a plain text version.

#### Input Parameters

* **video\_url\_or\_id** (required):\
  The YouTube video URL (e.g., `https://www.youtube.com/watch?v=dQw4w9WgXcQ`) or just the video ID (e.g., `dQw4w9WgXcQ`).
* **language** (required):\
  The language code for the transcript you want to extract (ISO 639-1 format, e.g., `en` for English, `es` for Spanish, etc.).

Supported languages include: en, es, de, fr, it, pt, ru, ja, zh, ar, hi, bn, ur, ko, nl, sv, no, da, fi, pl, el, tr, cs, hu, th, vi.

#### Output

* **status**: Indicates if the extraction was successful ("success") or failed ("error").
* **message**: A human-readable message about the result.
* **transcript**: An array of transcript segments (each with text, start time, and duration).
* **transcript\_text**: The full transcript as a single plain text string.
* **video\_id**: The YouTube video ID.
* **video\_url**: The YouTube video URL.

***

### Example Usage

Suppose you want to extract the English transcript from a YouTube video:

* **video\_url\_or\_id**: `https://www.youtube.com/watch?v=dQw4w9WgXcQ`
* **language**: `en`

The node will return:

* The transcript as an array (with timing and text for each segment).
* The full transcript as plain text.
* Status and message fields for error handling.

***

### How to Connect and Use in a Workflow

1. **Add the YouTube node to your workflow.**
2. **Set the required inputs** (video URL/ID and language).
3. **Connect the output** to downstream nodes (e.g., an LLM node for summarization, or an Output node to display the transcript).

**Example node reference in a prompt:**\
If your YouTube node is `action-0`, you can reference the plain text transcript as `{action-0.transcript_text}` in downstream nodes to get the full text from the video.

***

### Summary Table

| Field              | Description                         |
| ------------------ | ----------------------------------- |
| video\_url\_or\_id | YouTube video URL or ID (required)  |
| language           | Transcript language code (required) |
| transcript         | Array of transcript segments        |
| transcript\_text   | Full transcript as plain text       |
| status             | "success" or "error"                |
| message            | Human-readable result message       |
| video\_id          | The YouTube video ID                |
| video\_url         | The YouTube video URL               |

***

**Tip:**\
If you want to process or summarize the transcript, connect the YouTube node’s output to an LLM node and reference it in your prompt.