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

# Kling Face Identification

> Detect faces in a source video and establish a session for lip sync generation.

Face identification is the **first step** in the Kling lip sync workflow. It analyzes faces in a video and returns a `session_id` that must be used in the subsequent [lip sync generation](/en/guides/model-api/kuaishou/kling-lip-sync) request.

## Workflow Overview

```
identify-face  →  session_id  →  advanced-lip-sync  →  task_id  →  Poll for result
```

The `session_id` binds the video to the face analysis result. Without it, lip sync generation cannot proceed.

## Video Requirements

* The video must contain **at least one clearly visible, front-facing face**
* Faces that are well-lit and without heavy obstruction produce better results
* The video must be accessible via a public URL, or use a previously generated Kling video ID (`video_id`)

## Quick Example

<CodeGroup>
  ```bash cURL theme={null}
  curl https://ai.alad.com/kling/v1/videos/identify-face \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "video_url": "https://example.com/person-speaking.mp4"
    }'
  ```

  ```python Python theme={null}
  import requests

  response = requests.post(
      "https://ai.alad.com/kling/v1/videos/identify-face",
      headers={
          "Authorization": "Bearer YOUR_API_KEY",
          "Content-Type": "application/json"
      },
      json={"video_url": "https://example.com/person-speaking.mp4"}
  )

  data = response.json()
  session_id = data["data"]["session_id"]
  face_count = len(data["data"]["face_list"])
  print(f"Session ID: {session_id} ({face_count} face(s) detected)")
  ```
</CodeGroup>

## Request Parameters

| Parameter   | Type   | Required       | Description                              |
| ----------- | ------ | -------------- | ---------------------------------------- |
| `video_url` | string | One of the two | Public URL of the source video           |
| `video_id`  | string | One of the two | ID of a previously generated Kling video |

## Response

This endpoint is **synchronous** — results are returned immediately with no polling needed.

| Field                   | Description                                        |
| ----------------------- | -------------------------------------------------- |
| `data.session_id`       | Session ID to pass to the lip sync endpoint        |
| `data.face_list[]`      | All faces detected in the video                    |
| `face_list[].face_id`   | Unique identifier for each face                    |
| `face_list[].face_rect` | Face bounding box `{x, y, width, height}` (pixels) |

When multiple people are in the video, `face_list` will contain multiple entries.

<Card title="Next Step: Lip Sync Generation" icon="waveform" href="/en/guides/model-api/kuaishou/kling-lip-sync">
  Use the session\_id to generate a lip sync video.
</Card>

<Card title="API Reference" icon="code" href="/en/api-reference/model-api/kuaishou/kling-identify-face">
  View the interactive API documentation for Kling Face Identification.
</Card>