---
title: "Identify Face"
method: POST
path: "/kling/v1/videos/identify-face"
---

# Identify Face

`POST /kling/v1/videos/identify-face`

Analyze a video and detect all human faces in it. Returns a `session_id` and a `face_list` that are required for the subsequent lip sync generation step.

This is a **synchronous** call — the result is returned immediately, not as an async task.

## Request body

- object
  - `video_url` string — Public URL of the video to analyze. The video must contain at least one clearly visible human face. Required if `video_id` is not provided.
  - `video_id` string — ID of a video previously generated by Kling (e.g. from a text-to-video or image-to-video task result). Required if `video_url` is not provided.

## Response `200`

Face detection successful

- object
  - `code` integer
  - `message` string
  - `data` object
    - `session_id` string — Session ID binding the video and face analysis result. Pass this to the lip sync endpoint.
    - `face_list` object[] — List of detected faces. May contain multiple entries if multiple people appear in the video.
      - `face_id` string — Unique identifier for this face within the session.
      - `face_rect` object — Bounding box of the face in the video frame.
        - `x` integer
        - `y` integer
        - `width` integer
        - `height` integer

## Other responses

- `400` — Invalid request or face detection failed
- `401` — Unauthorized

---

[API](https://skmtc.net/anyfast/apis/anthropic-claude-compatible-endpoint.md) · [All operations](https://skmtc.net/anyfast/apis/anthropic-claude-compatible-endpoint/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/anyfast/anthropic-claude-compatible-endpoint/revisions/edfc53e182a1/schema)