Kling Digital Human

Use TTS when you need to create speech from text, then pass its audio_id to avatar generation. If you already have an audio file, pass it with sound_file and skip TTS.

Avatar
TTS

Create task

POST /kling/v1/videos/avatar/image2video

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/videos/avatar/image2video \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "image": "https://example.com/portrait.png",
    "audio_id": "932365483050274872",
    "prompt": "The person looks at the camera, speaks naturally, and nods gently.",
    "mode": "std",
    "watermark_info": {"enabled": true}
  }'

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

Public image URL or raw Base64. Supports JPG, JPEG, and PNG up to 10 MB. Each side must be at least 300 px and the aspect ratio must be between 1:2.5 and 2.5:1. Do not add a data-URI prefix to Base64.

string

Audio ID produced within the last 30 days. The audio must be 2–300 seconds. Provide exactly one of audio_id and sound_file.

string

Public audio URL or raw Base64. Supports MP3, WAV, M4A, and AAC up to 5 MB and 2–300 seconds. Provide exactly one of sound_file and audio_id.

string

Optional motion, emotion, and camera direction. Maximum length: 2,500 characters.

string

default:"std"

Generation mode: std or pro.

object

Watermark configuration.

boolean

Whether to generate a watermarked result.

string

Public callback URL for task-status notifications.

Create response

200

{
  "id": "asyntask_6prd3xHk76S1sTivIgGjQzrA4ziDrRCX",
  "task_id": "asyntask_6prd3xHk76S1sTivIgGjQzrA4ziDrRCX",
  "object": "video",
  "model": "kling-v1",
  "status": "queued",
  "progress": 0,
  "created_at": 1790319846
}

string

AnyFast task ID.

string

AnyFast task ID, identical to id.

string

Returned object type. For this endpoint, video.

string

Underlying request model identifier returned by the endpoint.

string

Initial AnyFast status. An accepted task returns queued.

integer

Initial progress percentage.

integer

Creation time as a Unix timestamp in seconds.

Query task

GET /kling/v1/videos/avatar/image2video/{task_id}

cURL

curl --request GET \
  --url https://www.anyfast.ai/kling/v1/videos/avatar/image2video/asyntask_6prd3xHk76S1sTivIgGjQzrA4ziDrRCX \
  --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 avatar creation.

Response

200

{
  "code": 0,
  "message": "",
  "data": {
    "task_id": "asyntask_6prd3xHk76S1sTivIgGjQzrA4ziDrRCX",
    "task_status": "succeed",
    "task_result": {
      "videos": [
        {
          "url": "https://example.com/digital-human.mp4",
          "duration": "5"
        }
      ]
    },
    "created_at": 1790319846000,
    "updated_at": 1790320090000
  }
}

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. Intermediate states can repeat or move between submitted and processing; treat only succeed and failed as terminal.

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.

Generate speech

POST /kling/v1/audio/tts

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/audio/tts \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "text": "Hello, welcome to the AnyFast digital human service.",
    "voice_id": "oversea_male1",
    "voice_language": "en",
    "voice_speed": 1.0
  }'

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

Text to synthesize. Maximum length: 1,000 characters.

string

required

Voice ID from the Kling AI Voice List. Its listed language must match voice_language.

string

default:"zh"

required

Voice language. Supported values: zh, en.

number

default:1

Speech speed from 0.8 through 2.0, rounded to one decimal place.

Response

200

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "request_01J8K7E7H4T7FQ6V6K6A",
  "data": {
    "task_id": "tts_task_01J8K7E7H4",
    "task_status": "succeed",
    "task_result": {
      "audios": [
        {
          "id": "932365483050274872",
          "url": "https://example.com/generated-speech.mp3",
          "duration": "4.067"
        }
      ]
    },
    "created_at": 1790321772436,
    "updated_at": 1790321774387,
    "final_unit_deduction": "0.05",
    "final_balance_deduction": {
      "quota": "0",
      "list_price": "0"
    }
  }
}

integer

Business result code. 0 indicates success.

string

Business result message.

string

Request identifier for troubleshooting.

string

TTS task identifier.

string

TTS status. A successful synchronous request returns succeed.

object[]

Generated audio results.

string

Audio ID accepted by avatar and lip-sync APIs.

string

Generated audio URL.

string

Audio duration in seconds.

string

Final Kling unit deduction.

object

Balance-deduction details returned by the provider.

integer

Creation time as a Unix timestamp in milliseconds.

integer

Update time as a Unix timestamp in milliseconds.

Overview

Native Compatible Endpoints

Model APIs

Kling Digital Human

Create task

Request headers

Request body

Create response

Query task

Request headers and path

Response

Generate speech

Request headers

Request body

Response

​Create task

​Request headers

​Request body

​Create response

​Query task

​Request headers and path

​Response

​Generate speech

​Request headers

​Request body

​Response

Create task

Request headers

Request body

Create response

Query task

Request headers and path

Response

Generate speech

Request headers

Request body

Response