# Kling v3.0 Pro Text-to-Video - Documentation

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown is available with `Accept: text/markdown` and `.md` URL variants.

Source: /docs/api-reference/model-apis-kling-v3.0-pro-t2v

# Kling v3.0 Pro Text-to-Video

POST

/

v3

/

async

/

kling-v3.0-pro-t2v

Kling v3.0 Pro Text-to-Video

cURL

```
curl --request POST \
--url https://api.novita.ai/v3/async/kling-v3.0-pro-t2v \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"sound": true,
"prompt": "<string>",
"duration": 123,
"cfg_scale": 123,
"aspect_ratio": "<string>",
"multi_prompt": [
"<string>"
],
"negative_prompt": "<string>"
}
'
```

```
import requestsurl = "https://api.novita.ai/v3/async/kling-v3.0-pro-t2v"payload = { "sound": True, "prompt": "<string>", "duration": 123, "cfg_scale": 123, "aspect_ratio": "<string>", "multi_prompt": ["<string>"], "negative_prompt": "<string>"}headers = { "Content-Type": "<content-type>", "Authorization": "<authorization>"}response = requests.post(url, json=payload, headers=headers)print(response.text)
```

```
const options = { method: 'POST', headers: {'Content-Type': '<content-type>', Authorization: '<authorization>'}, body: JSON.stringify({ sound: true, prompt: '<string>', duration: 123, cfg_scale: 123, aspect_ratio: '<string>', multi_prompt: ['<string>'], negative_prompt: '<string>' })};fetch('https://api.novita.ai/v3/async/kling-v3.0-pro-t2v', options) .then(res => res.json()) .then(res => console.log(res)) .catch(err => console.error(err));
```

```
<?php$curl = curl_init();curl_setopt_array($curl, [ CURLOPT_URL => "https://api.novita.ai/v3/async/kling-v3.0-pro-t2v", CURLOPT_RETURNTRANSFER => true, CURLOPT_ENCODING => "", CURLOPT_MAXREDIRS => 10, CURLOPT_TIMEOUT => 30, CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1, CURLOPT_CUSTOMREQUEST => "POST", CURLOPT_POSTFIELDS => json_encode([ 'sound' => true, 'prompt' => '<string>', 'duration' => 123, 'cfg_scale' => 123, 'aspect_ratio' => '<string>', 'multi_prompt' => [ '<string>' ], 'negative_prompt' => '<string>' ]), CURLOPT_HTTPHEADER => [ "Authorization: <authorization>", "Content-Type: <content-type>" ],]);$response = curl_exec($curl);$err = curl_error($curl);curl_close($curl);if ($err) { echo "cURL Error #:" . $err;} else { echo $response;}
```

```
package mainimport (	"fmt"	"strings"	"net/http"	"io")func main() {	url := "https://api.novita.ai/v3/async/kling-v3.0-pro-t2v"	payload := strings.NewReader("{\n \"sound\": true,\n \"prompt\": \"<string>\",\n \"duration\": 123,\n \"cfg_scale\": 123,\n \"aspect_ratio\": \"<string>\",\n \"multi_prompt\": [\n \"<string>\"\n ],\n \"negative_prompt\": \"<string>\"\n}")	req, _ := http.NewRequest("POST", url, payload)	req.Header.Add("Content-Type", "<content-type>")	req.Header.Add("Authorization", "<authorization>")	res, _ := http.DefaultClient.Do(req)	defer res.Body.Close()	body, _ := io.ReadAll(res.Body)	fmt.Println(string(body))}
```

```
HttpResponse<String> response = Unirest.post("https://api.novita.ai/v3/async/kling-v3.0-pro-t2v") .header("Content-Type", "<content-type>") .header("Authorization", "<authorization>") .body("{\n \"sound\": true,\n \"prompt\": \"<string>\",\n \"duration\": 123,\n \"cfg_scale\": 123,\n \"aspect_ratio\": \"<string>\",\n \"multi_prompt\": [\n \"<string>\"\n ],\n \"negative_prompt\": \"<string>\"\n}") .asString();
```

```
require 'uri'require 'net/http'url = URI("https://api.novita.ai/v3/async/kling-v3.0-pro-t2v")http = Net::HTTP.new(url.host, url.port)http.use_ssl = truerequest = Net::HTTP::Post.new(url)request["Content-Type"] = '<content-type>'request["Authorization"] = '<authorization>'request.body = "{\n \"sound\": true,\n \"prompt\": \"<string>\",\n \"duration\": 123,\n \"cfg_scale\": 123,\n \"aspect_ratio\": \"<string>\",\n \"multi_prompt\": [\n \"<string>\"\n ],\n \"negative_prompt\": \"<string>\"\n}"response = http.request(request)puts response.read_body
```

200

```
{
"task_id": "<string>"
}
```

Kling v3.0 Pro Text-to-Video generates high-quality videos from text prompts with natural motion and smooth scene dynamics. Supports flexible duration from 3 to 15 seconds, audio-video co-generation, and multi-shot video generation.

This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the [Task Result API](/docs/api-reference/model-apis-task-result) to retrieve the video generation results.

##

[​](#request-headers)

Request Headers

[​](#param-content-type)

Content-Type

string

required

Supports: `application/json`

[​](#param-authorization)

Authorization

string

required

Bearer authentication format, for example: Bearer {{API Key}}.

##

[​](#request-body)

Request Body

[​](#param-sound)

sound

boolean

default:false

Whether to generate audio simultaneously when generating video.

[​](#param-prompt)

prompt

string

required

Text prompt for video generation describing scene motion, camera moves, actions, voice style, ambience, and sound effects; must not exceed 2500 characters. Mutually exclusive with multi_prompt.Length limit: 0 - 2500

[​](#param-duration)

duration

integer

default:5

Duration of generated video in seconds. Supports flexible duration from 3 to 15 seconds.Value range: [3, 15]

[​](#param-cfg-scale)

cfg_scale

number

Controls the flexibility of video generation. Higher values result in generated content more closely following the prompt; lower values produce more natural motion.Value range: [0, 1]

[​](#param-aspect-ratio)

aspect_ratio

string

default:"16:9"

Aspect ratio of the generated video.Optional values: `16:9`, `9:16`, `1:1`

[​](#param-multi-prompt)

multi_prompt

string[]

List of prompts for multi-shot video generation. Divides video into multiple shots. Mutually exclusive with prompt.

[​](#param-negative-prompt)

negative_prompt

string

Negative prompt specifying elements to avoid in visuals and audio; must not exceed 2500 characters.Length limit: 0 - 2500

##

[​](#response)

Response

[​](#param-task-id)

task_id

string

required

Use the task_id to request the [Task Result API](/docs/api-reference/model-apis-task-result) to retrieve the generated outputs.

Last modified on July 3, 2026