Start a Task

Global Server

https://video.a2e.ai

POST

/api/v1/talkingPhoto/start

Request

Authorization

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Body Params application/json

name

string

required

A name of talking photo task

image_url

string

required

URL of a photo for talking/singing

audio_url

string

required

URL of a audio file as talking/singing source

duration

integer

optional

Duration of the animating talking/singing video in seconds (1-10 seconds, default: 3)

prompt

string

required

Text prompt describing the desired talking/singing style, mood, or characteristics

negative_prompt

string

required

Negative prompt specifying what should be avoided in the talking/singing generation

Example

{
    "name": "My first AI Talking Photo",
    "image_url": "https://example.com/8857f31c-4873-4e12-aff3-dbc5640512e7.JPG",
    "audio_url":"https://example.com/zh.WAV",
    "duration": 3,
    "prompt": "speaking, looking at the camera, detailed eyes, clear teeth, static view point, still background, elegant, clear facial features, stable camera, professional shooting angle",
    "negative_prompt": "vivid colors, overexposed, flickering, blurry details, subtitles, logo, style, artwork, painting, image, static, overall grayish, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless person, cluttered background, three legs, crowded background, walking backwards"
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://video.a2e.ai/api/v1/talkingPhoto/start' \
--header 'Content-Type: application/json' \
--data-raw '{
    "name": "My first AI Talking Photo",
    "image_url": "https://example.com/8857f31c-4873-4e12-aff3-dbc5640512e7.JPG",
    "audio_url":"https://example.com/zh.WAV",
    "duration": 3,
    "prompt": "speaking, looking at the camera, detailed eyes, clear teeth, static view point, still background, elegant, clear facial features, stable camera, professional shooting angle",
    "negative_prompt": "vivid colors, overexposed, flickering, blurry details, subtitles, logo, style, artwork, painting, image, static, overall grayish, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless person, cluttered background, three legs, crowded background, walking backwards"
}'

Responses

🟢200OK

application/json

Body

code

integer

required

0 is OK

data

object

required

_id

string

required

The ID of the image singing task.

current_status

string

required

The status of the record.

initialized: initialization

sent: sent to algorithm

pending: in algorithm queue

processing: being processed

completed: completed

failed: algorithm failed

name

string

required

image_url

string

required

audio_url

string

required

duration

integer

required

coins

integer

required

createdAt

string

required

failed_message

string

required

failed_code

string

required

result_url

string

required

prompt

string

required

negative_prompt

string

required

trace_id

string

required

Example

{
    "code": 0,
    "data": {
        "_id": "686770ddbf319f630a1cb3f7",
        "name": "My first AI Talking Photo",
        "image_url": "https://example.com/8857f31c-4873-4e12-aff3-dbc5640512e7.JPG",
        "audio_url": "https://example.com/audio.WAV",
        "duration": 3,
        "current_status": "initialized",
        "coins": 50,
        "createdAt": "2025-07-04T06:12:45.856Z",
        "failed_message": "",
        "failed_code": "",
        "result_url": "",
        "prompt": "speaking, looking at the camera, detailed eyes, clear teeth, static view point, still background, elegant, clear facial features, stable camera, professional shooting angle",
        "negative_prompt": "vivid colors, overexposed, flickering, blurry details, subtitles, logo, style, artwork, painting, image, static, overall grayish, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless person, cluttered background, three legs, crowded background, walking backwards"
    },
    "trace_id": "f4350fa1-b092-4d33-99a7-79dc08197c63"
}

Modified at 2025-07-23 05:28:20

Delete Record

List Tasks