> For the complete documentation index, see [llms.txt](https://help.blotato.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.blotato.com/rest-api-reference/create-source.md).

# Source

Submit a typed URL or text source for extraction and retain its ID for completion checks.

Submit content for extraction and receive a source ID for polling.

## Endpoint

```
POST https://backend.blotato.com/v2/source-resolutions-v3
```

**Rate Limit:** 30 requests / minute

## Authentication

Include your Blotato API key in the request headers:

```
blotato-api-key: YOUR_API_KEY
```

## Source Types

| Value              | Requires | Description                                              |
| ------------------ | -------- | -------------------------------------------------------- |
| `youtube`          | `url`    | Extract YouTube transcript (English captions only)       |
| `tiktok`           | `url`    | Extract TikTok transcript (English captions only)        |
| `article`          | `url`    | Extract article text from a web page                     |
| `pdf`              | `url`    | Extract text from a PDF                                  |
| `audio`            | `url`    | Transcribe audio (mp3, wav, m4a, ogg, flac, aac)         |
| `twitter`          | `url`    | Extract tweet content                                    |
| `text`             | `text`   | Transform raw text content with optional AI instructions |
| `perplexity-query` | `text`   | AI-powered web research query                            |

## Parameters

| Parameter            | Type   | Required                                   | Description                                                                                   |
| -------------------- | ------ | ------------------------------------------ | --------------------------------------------------------------------------------------------- |
| `source.sourceType`  | string | Yes                                        | One of: `youtube`, `tiktok`, `article`, `pdf`, `audio`, `twitter`, `text`, `perplexity-query` |
| `source.url`         | string | Required for URL-based types               | The URL to extract content from                                                               |
| `source.text`        | string | Required for `text` and `perplexity-query` | Raw text or search query                                                                      |
| `customInstructions` | string | No                                         | AI instructions to transform extracted content                                                |

## Examples

### Extract YouTube Transcript

```json
{
  "source": {
    "sourceType": "youtube",
    "url": "https://www.youtube.com/watch?v=VIDEO_ID"
  }
}
```

YouTube and TikTok transcript extraction reads **English captions only**. A non-English video, or a video with no captions, returns a `failed` status. For those videos, pass the transcript or a summary using `sourceType: "text"` instead.

### Extract Article with Custom Instructions

```json
{
  "source": {
    "sourceType": "article",
    "url": "https://example.com/article"
  },
  "customInstructions": "Summarize in 5 bullet points"
}
```

### AI Research Query

```json
{
  "source": {
    "sourceType": "perplexity-query",
    "text": "latest AI trends in social media marketing"
  }
}
```

### Transform Raw Text

```json
{
  "source": {
    "sourceType": "text",
    "text": "Your raw content here..."
  },
  "customInstructions": "Rewrite as a Twitter thread"
}
```

## Response

```json
{
  "id": "123e4567-e89b-12d3-a456-426614174000"
}
```

Use this ID with the [Get Source](/rest-api-reference/create-source/get-source.md) endpoint to retrieve the extracted content.

## n8n and Make.com

1. In n8n, select Source > Create.
2. Save the returned `id`.
3. Use Source > Get to check the saved ID until `status` is `completed` or `failed`.
4. Read `content` after `completed`, or report `message` after `failed`.

Follow the [n8n polling instructions](/integrations-and-automation-templates/n8n/n8n-blotato-node.md#using-source-operations) or the [source-to-publication workflow](/integrations-and-automation-templates/templates/11-build-your-first-ai-automation.md).

For Make, follow the [Make setup guide](/integrations-and-automation-templates/make.com.md). Inspect the installed module's fields or use the [async REST contract](/api-and-mcp-concepts/workflows.md). n8n operation labels do not establish Make module labels.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.blotato.com/rest-api-reference/create-source.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.