Skip to main content
POST
/
v3
/
async
/
vidu-q3-turbo-i2v
Vidu Q3 Turbo Image-to-Video
curl --request POST \
  --url https://api.novita.ai/v3/async/vidu-q3-turbo-i2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "audio": true,
  "images": [
    "<string>"
  ],
  "is_rec": true,
  "prompt": "<string>",
  "duration": 123,
  "off_peak": true,
  "audio_type": "<string>",
  "resolution": "<string>"
}
'
import requests

url = "https://api.novita.ai/v3/async/vidu-q3-turbo-i2v"

payload = {
"seed": 123,
"audio": True,
"images": ["<string>"],
"is_rec": True,
"prompt": "<string>",
"duration": 123,
"off_peak": True,
"audio_type": "<string>",
"resolution": "<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({
seed: 123,
audio: true,
images: ['<string>'],
is_rec: true,
prompt: '<string>',
duration: 123,
off_peak: true,
audio_type: '<string>',
resolution: '<string>'
})
};

fetch('https://api.novita.ai/v3/async/vidu-q3-turbo-i2v', 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/vidu-q3-turbo-i2v",
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([
'seed' => 123,
'audio' => true,
'images' => [
'<string>'
],
'is_rec' => true,
'prompt' => '<string>',
'duration' => 123,
'off_peak' => true,
'audio_type' => '<string>',
'resolution' => '<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 main

import (
"fmt"
"strings"
"net/http"
"io"
)

func main() {

url := "https://api.novita.ai/v3/async/vidu-q3-turbo-i2v"

payload := strings.NewReader("{\n \"seed\": 123,\n \"audio\": true,\n \"images\": [\n \"<string>\"\n ],\n \"is_rec\": true,\n \"prompt\": \"<string>\",\n \"duration\": 123,\n \"off_peak\": true,\n \"audio_type\": \"<string>\",\n \"resolution\": \"<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/vidu-q3-turbo-i2v")
.header("Content-Type", "<content-type>")
.header("Authorization", "<authorization>")
.body("{\n \"seed\": 123,\n \"audio\": true,\n \"images\": [\n \"<string>\"\n ],\n \"is_rec\": true,\n \"prompt\": \"<string>\",\n \"duration\": 123,\n \"off_peak\": true,\n \"audio_type\": \"<string>\",\n \"resolution\": \"<string>\"\n}")
.asString();
require 'uri'
require 'net/http'

url = URI("https://api.novita.ai/v3/async/vidu-q3-turbo-i2v")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = '<authorization>'
request.body = "{\n \"seed\": 123,\n \"audio\": true,\n \"images\": [\n \"<string>\"\n ],\n \"is_rec\": true,\n \"prompt\": \"<string>\",\n \"duration\": 123,\n \"off_peak\": true,\n \"audio_type\": \"<string>\",\n \"resolution\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body
{
  "task_id": "<string>"
}
Vidu Q3 Turbo image-to-video tool converts static images into dynamic videos with text-guided motion, supporting multiple resolutions and aspect ratios.
This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.

Request Headers

Content-Type
string
required
Supports: application/json
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

Request Body

seed
integer
Random seed for reproducible generation; 0 or omitted means random.Value range: [0, 2147483647]
audio
boolean
default:true
Whether to use audio-video co-generation. When true, outputs video with dialogue and background sound. Default true for Q3 models.
images
string[]
required
Reference image URL array. Supports .jpg, .jpeg, .png, .webp. Max 50MB per image; aspect ratio must be between 1:4 and 4:1.
is_rec
boolean
default:false
Enable audio-visual matching; when true, audio rhythm syncs with video dynamics.
prompt
string
Motion description for video generation; describes scene movement, actions, and dynamic effects.Length limit: 0 - 5000
duration
integer
default:5
Video duration in seconds.Value range: [1, 16]
off_peak
boolean
default:false
Use off-peak pricing; when true, task queues for off-peak processing at lower cost.
audio_type
string
default:"all"
Audio type when audio is true. all = sound effects + voice, speech_only = voice only, sound_effect_only = sound effects only.Optional values: all, speech_only, sound_effect_only
resolution
string
default:"720p"
Output video resolution.Optional values: 540p, 720p, 1080p

Response

task_id
string
required
Use the task_id to request the Task Result API to retrieve the generated outputs.
Last modified on July 3, 2026