Skip to main content
PixVerse

PixVerse -- generate a video from text

Submit a PixVerse V6 text-to-video task

POST
/services/aigc/video-generation/video-synthesis
# Singapore (ap-southeast-1). This model is available only in this region.
# API keys are region-specific. See https://docs.qwencloud.com/developer-guides/getting-started/regions
curl --location 'https://ap-southeast-1.maas.qwencloudapi.com/api/v1/services/aigc/video-generation/video-synthesis' \
  -H 'X-DashScope-Async: enable' \
  -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "pixverse/pixverse-v6-t2v",
  "input": {
    "prompt": "In a rainy cyber city, a raccoon walks on a railing. Suddenly, its eyes glow blue, and it transforms into a high-tech drone, flying quickly out of the frame."
  },
  "parameters": {
    "size": "1280*720",
    "duration": 5,
    "watermark": true
  }
}'
{
  "request_id": "<string>",
  "output": {
    "task_id": "<string>",
    "task_status": "PENDING"
  }
}
Generate videos up to 15 seconds at 1080P from text prompts with PixVerse V6.
  • Model: pixverse/pixverse-v6-t2v.
  • Multi-shot: set parameters.shot_type to multi to let the model plan multiple shots automatically. The default single produces one continuous shot.
  • Aspect ratios: choose a size value such as 1280*720 (16:9), 1024*768 (4:3), or 960*960 (1:1). See the size parameter for the full list.
  • Audio: set audio to true to generate background music or sound effects that match the video.

Workflow

  1. Submit a task with this endpoint and save the returned task_id.
  2. Poll Retrieve task result every 15 seconds until task_status is SUCCEEDED or FAILED.

Billing

Billing depends on the resolution tier, duration, and whether audio is generated. Check the model pricing before calling.

Errors

For common error codes, see Error messages.

Authorizations

string
header
required

DashScope API Key. Get one from the QwenCloud console.

Header Parameters

enum<string>
required

Must be set to enable. HTTP requests support asynchronous mode only. Omitting this header returns the error "current user api does not support synchronous calls".

enable

Body

application/json
enum<string>
required

Model ID. Only pixverse/pixverse-v6-t2v is supported.

pixverse/pixverse-v6-t2v
pixverse/pixverse-v6-t2v
object
required

Basic input information, such as the prompt.

object
required

Video generation parameters, such as resolution, duration, and audio.

Response

200-application/json
string

Unique request ID, useful for tracing and troubleshooting.

object

Task output.