Kling Lip Sync

Use the Face Recognition tab first to obtain session_id and face_id, then submit them in the Lip Sync tab. The audio input is either face_choose[].audio_id or face_choose[].sound_file. To start from text, first call Kling Digital Human TTS and use the returned audio id.

Lip Sync
Face Recognition

Create task

POST /kling/v1/videos/advanced-lip-sync

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/videos/advanced-lip-sync \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "session_id": "923976763809071143",
    "face_choose": [
      {
        "face_id": "0",
        "sound_file": "https://example.com/speech.mp3",
        "sound_start_time": 0,
        "sound_end_time": 3000,
        "sound_insert_time": 1000,
        "sound_volume": 1.0,
        "original_audio_volume": 1.0
      }
    ],
    "watermark_info": {"enabled": false}
  }'

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Data exchange format.

Request body

string

required

Session ID returned by Identify Face.

object[]

required

Face and driving-audio configuration. Provide exactly one item.

string

required

Face ID returned in data.face_data[].face_id by Identify Face.

string

Audio ID created within the last 30 days. The selected audio must be 2–60 seconds. Provide exactly one of audio_id and sound_file.

string

Public audio URL or raw Base64. MP3, WAV, and M4A are supported through AnyFast; maximum size 5 MB and duration 2–60 seconds. Provide exactly one of sound_file and audio_id.

integer

required

Crop start in the source audio, in milliseconds.

integer

required

Crop end in the source audio, in milliseconds. It must not exceed the source audio duration.

integer

required

Insertion point in the video, in milliseconds. The inserted segment must remain inside the video and overlap the selected face by at least 2 seconds.

number

default:1

Inserted-audio volume from 0 through 2.

number

default:1

Original-video volume from 0 through 2.

object

Watermark configuration.

boolean

Whether to generate a watermarked result.

string

Public callback URL for task-status notifications.

Create response

200

{
  "code": 0,
  "message": "",
  "request_id": "",
  "data": {
    "task_id": "asyntask_AhmnzEDa847dDNcIR4sQ385evWXR44V7",
    "task_status": "submitted",
    "created_at": 1788321762398,
    "updated_at": 1788321762398
  }
}

integer

Business result code. 0 indicates acceptance.

string

Business message. It can be empty on success.

string

Request ID field. It can be empty.

string

AnyFast task ID used to query the result.

string

Initial task status. An accepted task returns submitted.

integer

Creation time as a Unix timestamp in milliseconds.

integer

Update time as a Unix timestamp in milliseconds.

Query task

GET /kling/v1/videos/advanced-lip-sync/{task_id}

cURL

curl --request GET \
  --url https://www.anyfast.ai/kling/v1/videos/advanced-lip-sync/asyntask_AhmnzEDa847dDNcIR4sQ385evWXR44V7 \
  --header 'Authorization: Bearer YOUR_API_KEY'

Request headers and path

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

required

AnyFast task ID returned by task creation.

Response

200

{
  "code": 0,
  "message": "",
  "data": {
    "task_id": "asyntask_AhmnzEDa847dDNcIR4sQ385evWXR44V7",
    "task_status": "succeed",
    "task_result": {
      "videos": [
        {
          "url": "https://example.com/lip-sync-result.mp4",
          "duration": "12"
        }
      ]
    },
    "created_at": 1788321762000,
    "updated_at": 1788322364000
  }
}

integer

Business result code. 0 indicates success.

string

Business message. It can be empty on success.

string

AnyFast task ID.

string

Task status: submitted, processing, succeed, or failed.

string

Failure details when the task fails.

object[]

Generated video results. Present when the task succeeds.

string

Generated video URL.

string

Reported video duration in seconds.

integer

Creation time as a Unix timestamp in milliseconds.

integer

Update time as a Unix timestamp in milliseconds.

Identify faces

POST /kling/v1/videos/identify-face

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/videos/identify-face \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "video_url": "https://example.com/person-speaking.mp4"
  }'

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Data exchange format.

Request body

string

Public MP4 or MOV URL. The video must be 2–60 seconds, no larger than 100 MB, and use 720p or 1080p resolution with each edge from 512 through 2,160 px. Provide exactly one of video_url and video_id.

string

ID of a Kling-generated video created within the last 30 days. Provide exactly one of video_id and video_url.

Response

200

{
  "code": "0",
  "message": "SUCCEED",
  "requestId": "request_01J8K7H4T7FQ6V6K6A",
  "data": {
    "session_id": "926174688823869522",
    "face_data": [
      {
        "face_id": "0",
        "face_image": "https://example.com/detected-face.png",
        "start_time": 0,
        "end_time": 12000
      }
    ],
    "final_unit_deduction": "0.05",
    "final_balance_deduction": {
      "quota": "0",
      "list_price": "0"
    }
  }
}

string

Business result code. 0 indicates success.

string

Business result message.

string

Request identifier returned by the current AnyFast endpoint.

string

Session ID required by the lip-sync request.

object[]

Detected faces and their usable time intervals.

string

Face ID to pass in face_choose[].face_id.

string

Preview image for the detected face.

integer

Usable interval start in milliseconds.

integer

Usable interval end in milliseconds.

string

Final Kling unit deduction.

object

Balance-deduction details returned by the provider.

Overview

Native Compatible Endpoints

Model APIs

Create task

Request headers

Request body

Create response

Query task

Request headers and path

Response

Identify faces

Request headers

Request body

Response

​Create task

​Request headers

​Request body

​Create response

​Query task

​Request headers and path

​Response

​Identify faces

​Request headers

​Request body

​Response

Create task

Request headers

Request body

Create response

Query task

Request headers and path

Response

Identify faces

Request headers

Request body

Response