> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/integrations/catalog/sightengine.md).

# Sightengine

Moderate images, videos, text, and AI-generated media.

## Connectors

Choose the connector that matches your authentication method. The options below use the names shown in StackAI.

| Connector   | Authentication   |
| ----------- | ---------------- |
| Sightengine | API key or token |

### Sightengine

Moderate images, videos, and text with Sightengine.

#### Set up in Sightengine

1. Prepare the Sightengine account or service that the workflow will access. Grant access to the required resources and operations.
2. **API User:** Copy the API user from the Sightengine API-key page.
3. **API Secret:** Copy the API secret from the Sightengine API-key page.

#### Set up in StackAI

1. Open **Settings → Connections**, add a connection, and select **Sightengine**.
2. Enter the credentials and connection details in the fields below.
3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

**Connection fields**

| StackAI field | Required | What to enter                                                                                                                   |
| ------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------- |
| API User      | Yes      | Copy the API user from the Sightengine API-key page. [Provider instructions](https://sightengine.com/faq/get-my-credentials).   |
| API Secret    | Yes      | Copy the API secret from the Sightengine API-key page. [Provider instructions](https://sightengine.com/faq/get-my-credentials). |

### Verify the connection

Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.

If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.

## Use an action

1. Add the required **Sightengine** action to the workflow.
2. Select a connection when the action requests one.
3. Complete the required fields. Use the reference picker when a value comes from another workflow step.
4. Run the workflow and inspect the action’s output. Check the result before using it in a later step.

## Actions

### Detect AI-generated Image

Estimate whether a public image was generated by AI.

#### Inputs

| Field     | Type   | Required | Description                         |
| --------- | ------ | -------- | ----------------------------------- |
| Image URL | string | Yes      | Public URL of the image to analyze. |

#### Outputs

| Field              | Type   | Description                                                 |
| ------------------ | ------ | ----------------------------------------------------------- |
| Status             | string | Sightengine request status.                                 |
| Request id         | string | Sightengine request identifier.                             |
| Media id           | string | Sightengine identifier for the analyzed image.              |
| AI-generated score | number | Confidence from 0 to 1 that the image is AI-generated.      |
| Generator scores   | object | Optional structured scores for individual image generators. |

### Get Video Moderation Job Status

Check the progress and current results of a video moderation job.

#### Inputs

| Field    | Type   | Required | Description                             |
| -------- | ------ | -------- | --------------------------------------- |
| Media id | string | Yes      | Video media id returned by Sightengine. |

#### Outputs

| Field            | Type          | Description                                                       |
| ---------------- | ------------- | ----------------------------------------------------------------- |
| Job status       | string        | Current video job state.                                          |
| Media id         | string        | Sightengine video media identifier.                               |
| Request id       | string        | Sightengine request identifier for the job.                       |
| Started          | number        | Unix timestamp when Sightengine started the video job.            |
| Last update      | number        | Unix timestamp of the latest video-job update.                    |
| Progress         | number        | Current completion progress from 0 to 1.                          |
| Operations       | integer       | Moderation operations consumed so far.                            |
| Frames           | object\_array | Structured analyzed frames and their model results.               |
| Total frames     | integer       | Total number of analyzed frames reported by Sightengine.          |
| Frames truncated | boolean       | Whether additional analyzed frames were omitted from this result. |

### Moderate Image

Check a public image for unsafe content with a selected safety profile.

#### Inputs

| Field              | Type                      | Required | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
| ------------------ | ------------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Image URL          | string                    | Yes      | Public URL of the image to moderate.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
| Moderation profile | select (string)           | Yes      | Choose the types of unsafe content to check. Available values: Standard safety, Adult content, Violence and weapons, Hate and offensive content, Self-harm, Regulated content, Text in image, Custom. Default: standard\_safety.                                                                                                                                                                                                                                                                                                       |
| Custom models      | multiple\_select (string) | No       | Exact Sightengine models to use with the Custom profile. Available values: Nudity and adult content, Violence, Weapons, Gore, Hate and offensive content, Self-harm, Recreational drugs, Medical content, Alcohol, Tobacco, Gambling, Money, Destruction, Military content, Text in image.                                                                                                                                                                                                                                             |
| Text categories    | multiple\_select (string) | No       | Text categories to detect in images when visual-text moderation is selected. Available values: Sexual and suggestive, Insults and personal attacks, Discriminatory and hate, Inappropriate language, Grawlix, Email addresses, Phone numbers, Usernames, Social Security numbers, IP addresses, Links and URLs, Extremism, Weapons and firearms, Medical drugs, Recreational drugs, Self-harm and suicide, Violence and threats, Platform evasion, Off-platform mentions, Content trade, Money transactions, Grooming, Minor presence. |

#### Outputs

| Field         | Type   | Description                                                 |
| ------------- | ------ | ----------------------------------------------------------- |
| Status        | string | Sightengine request status.                                 |
| Request id    | string | Sightengine request identifier.                             |
| Media id      | string | Sightengine identifier for the analyzed image.              |
| Model results | dict   | Structured scores and detections from every selected model. |

### Moderate Text

Check text or a username for unsafe content.

#### Inputs

| Field           | Type                      | Required | Description                                                                                                                                                                    |
| --------------- | ------------------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Text            | textarea                  | Yes      | Text, message, review, or username to moderate.                                                                                                                                |
| Analysis mode   | select (string)           | No       | Use ML for overall scores, Rules for matched terms, or Username for account names. Available values: ML classification, Rule matches, Username analysis. Default: ml.          |
| ML model        | select (string)           | No       | Choose general safety classes or dedicated self-harm analysis. Available values: General, Self-harm. Default: general.                                                         |
| Language        | select (string)           | No       | Language of the text being checked. Available values: DA, DE, EN, ES, FI, FR, IT, KO, NL, NO, PL, PT, RO, RU, SV, TL, TR, ZH. Default: en.                                     |
| Rule categories | multiple\_select (string) | No       | Categories to check in Rules mode. Available values: Profanity, Personal, Link, Drug, Weapon, Violence, Self Harm, Medical, Extremism, Spam, Content Trade, Money Transaction. |

#### Outputs

| Field              | Type   | Description                                                      |
| ------------------ | ------ | ---------------------------------------------------------------- |
| Status             | string | Sightengine request status.                                      |
| Request ID         | string | Sightengine request identifier.                                  |
| Moderation classes | object | Structured ML class scores when ML mode is used.                 |
| Rule matches       | object | Structured category matches when Rules or Username mode is used. |

### Moderate Video

Start an asynchronous moderation job for a video at a public URL.

#### Inputs

| Field              | Type                      | Required | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
| ------------------ | ------------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Video URL          | string                    | Yes      | Public URL of the stored video to moderate.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
| Moderation profile | select (string)           | No       | Choose the types of unsafe content to check in the video. Available values: Standard safety, Adult content, Violence and weapons, Hate and offensive content, Self-harm, Regulated content, Text in video, AI-generated content, Custom. Default: standard\_safety.                                                                                                                                                                                                                                                                          |
| Custom model ids   | multiple\_select (string) | No       | Video-capable model ids to use when the profile is Custom. Available values: Nudity, Violence, Weapons, Gore, Hate and offensive content, Self-harm, Recreational drugs, Medical content, Alcohol, Tobacco, Gambling, Money, AI-generated content, Face analysis, Text moderation.                                                                                                                                                                                                                                                           |
| Text categories    | multiple\_select (string) | No       | Text categories to detect in video frames when visual-text moderation is selected. Available values: Sexual and suggestive, Insults and personal attacks, Discriminatory and hate, Inappropriate language, Grawlix, Email addresses, Phone numbers, Usernames, Social Security numbers, IP addresses, Links and URLs, Extremism, Weapons and firearms, Medical drugs, Recreational drugs, Self-harm and suicide, Violence and threats, Platform evasion, Off-platform mentions, Content trade, Money transactions, Grooming, Minor presence. |
| Maximum duration   | integer                   | No       | Stop analysis after this many seconds, up to one hour. Maximum: 3600. Default: 1800.                                                                                                                                                                                                                                                                                                                                                                                                                                                         |

#### Outputs

| Field      | Type   | Description                                         |
| ---------- | ------ | --------------------------------------------------- |
| Status     | string | Sightengine request status.                         |
| Request id | string | Sightengine launch-request identifier.              |
| Media id   | string | Identifier used to check this video moderation job. |
| Media URI  | string | Provider URI for the submitted video.               |

## Important behavior

Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.

The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.


---

# 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://docs.stackai.com/integrations/catalog/sightengine.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.
