## Create task
`POST /kling/v1/videos/text2video`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/kling/v1/videos/text2video \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model_name": "kling-2.6",
"prompt": "A corgi runs along a beach at sunset as waves cross the sand",
"negative_prompt": "blurry, shaky",
"duration": "5",
"mode": "pro",
"sound": "on",
"aspect_ratio": "16:9",
"watermark_info": {"enabled": false}
}'
```
```json 200 theme={null}
{
"id": "860260753860210752",
"task_id": "860260753860210752",
"object": "video",
"model": "kling-v2-6",
"status": "queued",
"progress": 0,
"created_at": 1773130665
}
```
## Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Must be `application/json`.
## Request body
Must be `kling-2.6`.
Positive prompt, up to 2,500 characters.
Content to avoid, up to 2,500 characters.
Up to two voices. Each item contains a `voice_id` from Voice Management.
`on` or `off`. Must be `on` when `voice_list` is used.
`std` for 720p or `pro` for 1080p.
Fixed duration: `5` or `10` seconds.
`16:9`, `9:16`, or `1:1`.
Preset or custom camera movement.
Use `enabled` to request an additional watermarked result.
### Specified voice
`voice_list` accepts up to two voices. Reference them as `<<>>` and `<<>>` in list order, and set `sound` to `on`.
```json theme={null}
{
"model_name": "kling-2.6",
"prompt": "<<>> says: 'Welcome to today's program'",
"voice_list": [{"voice_id": "voice-id"}],
"duration": "5",
"mode": "pro",
"sound": "on",
"aspect_ratio": "16:9"
}
```
### Camera control
`camera_control.type` supports `simple`, `down_back`, `forward_up`, `right_turn_forward`, and `left_turn_forward`. In `simple` mode, set one nonzero property in `config`: `horizontal`, `vertical`, `pan`, `tilt`, `roll`, or `zoom`. Each property ranges from -10 to 10.
## Query task by ID
`GET /kling/v1/videos/text2video/{task_id}`
### Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Data exchange format. Use `application/json`.
### Path parameters
The `task_id` returned by the create request.
```bash cURL theme={null}
curl --request GET \
--url https://www.anyfast.ai/kling/v1/videos/text2video/TASK_ID \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json'
```
### Response fields
`0` indicates that the query was accepted.
Error information; empty for a successful query.
Queried task ID.
`submitted`, `processing`, `succeed`, or `failed`.
Failure details when the task fails.
Generated videos, returned after success.
Temporary generated-video URL.
Actual duration in seconds.
Creation Unix timestamp in milliseconds.
Last update Unix timestamp in milliseconds.
```json 200 theme={null}
{
"code": 0,
"data": {
"created_at": 1784720894000,
"task_id": "asyntask_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"task_result": {"videos": [{"duration": "5", "url": "https://example.com/generated-video.mp4"}]},
"task_status": "succeed",
"updated_at": 1784721103000
},
"message": ""
}
```
Generated result URLs are removed after 30 days. Save the files promptly.
## Create task
`POST /kling/v1/videos/image2video`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/kling/v1/videos/image2video \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model_name": "kling-2.6",
"image": "https://example.com/first-frame.png",
"image_tail": "https://example.com/end-frame.png",
"prompt": "The camera slowly pulls back as the person smiles",
"duration": "5",
"mode": "pro",
"sound": "off"
}'
```
```json 200 theme={null}
{
"id": "860260753860210752",
"task_id": "860260753860210752",
"object": "video",
"model": "kling-v2-6",
"status": "queued",
"progress": 0,
"created_at": 1773130665
}
```
## Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Must be `application/json`.
## Request body
Must be `kling-2.6`.
Start frame URL or raw Base64. At least one of `image` and `image_tail` is required.
End frame. It cannot be combined with `dynamic_masks`, `static_mask`, or `camera_control`.
Positive prompt, up to 2,500 characters.
Negative prompt, up to 2,500 characters.
Up to two items, each containing `voice_id`.
`on` or `off`. Must be `on` when a voice is referenced.
`std` for 720p or `pro` for 1080p.
`5` or `10` seconds.
Static motion mask as a URL or raw Base64.
Up to six dynamic motion-brush masks.
Preset or custom camera movement.
Use `enabled` to request an additional watermarked result.
### Image requirements
* Use a public URL or raw Base64 without a `data:image/...;base64,` prefix.
* Use JPG, JPEG, or PNG. Files must be no larger than 10 MB, each side must be at least 300 px, and the aspect ratio must be between 1:2.5 and 2.5:1.
* At least one of `image` and `image_tail` is required.
* End-frame control, motion brush, and `camera_control` cannot be used together.
### Motion brush
A dynamic-area mask matching the input image dimensions.
Trajectory coordinates. A 5-second video accepts 2–77 points.
X coordinate, using the image's bottom-left corner as the origin.
Y coordinate, using the image's bottom-left corner as the origin.
### Specified voice example
```json theme={null}
{
"model_name": "kling-2.6",
"image": "https://example.com/person.png",
"prompt": "<<>> makes the person say: 'Welcome everyone'",
"voice_list": [{"voice_id": "voice-id"}],
"duration": "5",
"mode": "pro",
"sound": "on"
}
```
## Query task by ID
`GET /kling/v1/videos/image2video/{task_id}`
### Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Data exchange format. Use `application/json`.
### Path parameters
The image-to-video task ID.
```bash cURL theme={null}
curl --request GET \
--url https://www.anyfast.ai/kling/v1/videos/image2video/TASK_ID \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json'
```
### Response fields
`0` indicates that the query was accepted.
Error information; empty for a successful query.
Queried task ID.
`submitted`, `processing`, `succeed`, or `failed`.
Failure details when the task fails.
Generated videos, returned after success.
Temporary generated-video URL.
Actual duration in seconds.
Creation Unix timestamp in milliseconds.
Last update Unix timestamp in milliseconds.
```json 200 theme={null}
{
"code": 0,
"data": {
"created_at": 1784720894000,
"task_id": "asyntask_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"task_result": {"videos": [{"duration": "5", "url": "https://example.com/generated-video.mp4"}]},
"task_status": "succeed",
"updated_at": 1784721103000
},
"message": ""
}
```
Generated result URLs are removed after 30 days. Save the files promptly.
## Create task
`POST /kling/v1/videos/motion-control`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/kling/v1/videos/motion-control \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model_name": "kling-2.6",
"image_url": "https://example.com/character.png",
"video_url": "https://example.com/motion.mp4",
"prompt": "Preserve the character and reproduce the reference motion",
"character_orientation": "video",
"keep_original_sound": "yes",
"mode": "pro"
}'
```
```json 200 theme={null}
{"code":0,"message":"SUCCEED","request_id":"request-id","data":{"task_id":"task-id","task_status":"submitted"}}
```
## Request body
Must be `kling-2.6`.
Additional visual or camera instructions, up to 2,500 characters.
Character image URL or raw Base64.
Public URL for the motion reference video.
Up to one legacy element. When used, `character_orientation` must be `video`.
Element ID returned by the Legacy Element Management API.
Keep reference-video audio: `yes` or `no`.
Character orientation source: `image` or `video`.
`std` or `pro`.
Use `enabled` to request an additional watermarked result.
### Media requirements
* Images: JPG, JPEG, or PNG; up to 10 MB; each side 300–65,536 px; aspect ratio 1:2.5 through 2.5:1. Keep the head, upper body, or full body visible and avoid occlusion or extreme orientation.
* Videos: MP4 or MOV; up to 100 MB; each side 340–3,850 px; at least 3 seconds long.
* Maximum duration is 10 seconds for `character_orientation: "image"` and 30 seconds for `character_orientation: "video"`.
* Use one continuous shot, keep the person in frame, avoid cuts and aggressive camera movement, and prefer a single person with moderate motion speed.
For difficult or fast motion, the model may extract only the usable continuous segment and return a result shorter than the uploaded video. A task can still run when at least 3 seconds of continuous usable motion is found, and consumed credits are not refunded. Reduce the motion difficulty or speed when needed.
## Query task by ID
`GET /kling/v1/videos/motion-control/{task_id}`
### Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Data exchange format. Use `application/json`.
### Path parameters
The motion-control task ID.
```bash cURL theme={null}
curl --request GET \
--url https://www.anyfast.ai/kling/v1/videos/motion-control/TASK_ID \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json'
```
### Response fields
`0` indicates that the query was accepted.
Error information; empty for a successful query.
Queried task ID.
`submitted`, `processing`, `succeed`, or `failed`.
Failure details when the task fails.
Generated videos, returned after success.
Temporary generated-video URL.
Actual duration in seconds.
Creation Unix timestamp in milliseconds.
Last update Unix timestamp in milliseconds.
```json 200 theme={null}
{
"code": 0,
"data": {
"created_at": 1784720894000,
"task_id": "asyntask_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"task_result": {"videos": [{"duration": "5", "url": "https://example.com/generated-video.mp4"}]},
"task_status": "succeed",
"updated_at": 1784721103000
},
"message": ""
}
```
Generated result URLs are removed after 30 days. Save the files promptly.
## Endpoints
| Operation | Method and path |
| ------------------- | ------------------------------------------ |
| Create custom voice | `POST /kling/v1/general/custom-voices` |
| Query custom voice | `GET /kling/v1/general/custom-voices/{id}` |
| List preset voices | `GET /kling/v1/general/presets-voices` |
## Create custom voice
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/kling/v1/general/custom-voices \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"voice_name": "Narrator",
"voice_url": "https://example.com/voice.mp3"
}'
```
```json 200 theme={null}
{"id":"asyntask_xxx","task_id":"asyntask_xxx","object":"video","model":"kling-voices","status":"queued","progress":0,"created_at":1784778266}
```
Custom voice name, up to 20 characters.
Public MP3, WAV, MP4, or MOV URL. At least one of `voice_url` and `video_id` is required.
An eligible previously generated video ID. At least one of `voice_url` and `video_id` is required.
The source must contain one clear speaker and be 5–30 seconds long. Creation status can be `submitted`, `processing`, `succeed`, or `failed`. A successful result provides `voice_id` and `trial_url`.
## Query custom voice
```bash cURL theme={null}
curl --request GET \
--url https://www.anyfast.ai/kling/v1/general/custom-voices/VOICE_TASK_ID \
--header 'Authorization: Bearer YOUR_API_KEY'
```
A successful voice item contains `voice_id`, `voice_name`, `trial_url`, and `owned_by`.
## List preset voices
```bash cURL theme={null}
curl --request GET \
--url 'https://www.anyfast.ai/kling/v1/general/presets-voices?pageNum=1&pageSize=30' \
--header 'Authorization: Bearer YOUR_API_KEY'
```
Page number from 1 to 1,000.
Page size from 1 to 1,000.
Each item in `data[]` contains task metadata and `task_result.voices[]`. A voice contains `voice_id`, `voice_name`, `trial_url`, `owned_by`, and `status`. Current official preset voices return `owned_by: "vod"`.