Generate a video

POST

generate-video

curl --request POST \
  --url https://api.postqueen.ai/public/v1/generate-video \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "type": "seedance",
  "output": "vertical",
  "customParams": {
    "prompt": "Slow push-in on a bowl of spring salad on a wooden table by a sunny window, steam rising from fresh bread beside it, warm morning light.",
    "images": []
  }
}
'

{
  "id": "c2f1a7d0-5b3e-4f7a-9d61-8e2b4c0a9f13",
  "name": "k3l4m5n6o7.mp4",
  "originalName": null,
  "path": "https://cdn.example.com/k3l4m5n6o7.mp4",
  "thumbnail": "https://cdn.example.com/p8q9r0s1t2.jpg",
  "alt": null,
  "status": "ready"
}

Pick a generator in type, a shape in output, and send the generator’s inputs in customParams. The request stays open until the video is ready, which takes minutes, and answers with the stored file.

curl -X POST "https://api.postqueen.ai/public/v1/generate-video" \
  -H "Authorization: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  --max-time 2400 \
  -d '{
    "type": "seedance",
    "output": "vertical",
    "customParams": {
      "prompt": "Slow push-in on a bowl of spring salad on a wooden table by a sunny window, warm morning light.",
      "images": []
    }
  }'

const res = await fetch("https://api.postqueen.ai/public/v1/generate-video", {
  method: "POST",
  headers: {
    Authorization: process.env.POSTQUEEN_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    type: "seedance",
    output: "vertical",
    customParams: {
      prompt: "Slow push-in on a bowl of spring salad on a wooden table by a sunny window, warm morning light.",
      images: [],
    },
  }),
});
const video = await res.json();

The answer has the same shape as Upload a file, with status already ready. Put its id and path in a post’s image array as they are: there is nothing to poll.

The generators

`type`	What it makes	`customParams`
`seedance`	One clip with sound, 5 seconds at 720p unless you ask otherwise.	`prompt` (string, required): one scene, as a visual brief of the camera, the subject, the motion, the light and the atmosphere, with no on-screen text or logos. `images` (list, required): up to three images from your media library, each as the `id` and `path` an upload returned. Send `[]` for a video from the prompt alone. `model` (optional): `mini` (the default), `fast` or `standard`. `resolution` (optional): `480p`, `720p` (the default) or `1080p`, which only `standard` offers. `duration` (optional): 4 to 15 seconds, 5 by default. `aspectRatio` (optional): `9:16`, `16:9`, `1:1`, `4:3` or `3:4`; left out, it follows `output`. `audio` (optional): `true` by default.
`image-text-slides`	A narrated slideshow of three to five slides, each with a generated picture, the narration read aloud and shown as captions.	`voice` (string, required): a voice `id` from Run a video helper. `prompt` (string, required): what the video should say and show, in plain text.

output is vertical (9:16) for Reels, Stories, TikTok and Shorts, or horizontal (16:9) for a feed post. An Image Text Slides video is 1080 × 1920 or 1920 × 1080.

How long it takes

A video takes a few minutes. Seedance gives up after about 30 minutes and answers 500. Set your HTTP client’s timeout above that. If the connection closes before the answer, the video is still made and saved: find it in the app’s media library.

Credits and the free trial

Each video is paid from your workspace’s credits. A seedance video is priced per second by model and resolution, from 2 credits a second (mini, 480p) to 20 (standard, 1080p); the default, 5 seconds of mini at 720p, costs 20. An image-text-slides video costs 20. Every price is on Credits.
Subscriptions started before 23 October 2026 keep the credits and prices they started with, and their seedance default is 8 seconds of fast at 720p.
A video that fails gives its credits back. A request refused with 400, 402 or 406 uses none.
During the free trial, seedance answers 406. image-text-slides works. See Free trial.

This endpoint has no hourly limit. Your credits balance is the limit.

If it fails

Answer	What to do
`400` with a `message` list	A field is missing or wrong. `type must be any of: ...` lists the generators you can use
`400` `Seedance <model> does not offer <resolution>`	Only `standard` offers `1080p`, and `mini` offers `480p` and `720p`
`402` `Not enough credits: this costs N and the balance is N.`	The balance does not cover the video. `required` and `balance` in the body give both numbers. Buy credits on Billing, or ask for a cheaper video
`406` `This video is not available during the trial. To use it now, open https://app.postqueen.ai/billing and click "End free trial": ...`	Seedance during the free trial. Use `image-text-slides`, or end the trial on Billing
`422` `Your request was rejected by the AI safety system.`	The provider refused the prompt. The message names the flagged categories when the provider gives them. Change the prompt
`500` `AI generation failed, please try again later.`	The generation failed or timed out. The credits were given back. Try again

Agents connected over MCP start the same video as a job and poll it, so nothing waits on an open connection: see generateVideoTool.

Authorizations

Authorization

string

header

required

Your API key from Connections > API key, or an OAuth access token (pos_...). Send it as it is, with no Bearer prefix.

Body

application/json

type

enum<string>

required

The generator. seedance makes a 5-second clip with sound, image-text-slides a narrated slideshow

Available options:

seedance,

image-text-slides

output

enum<string>

required

vertical (9:16) for Reels, Stories, TikTok and Shorts; horizontal (16:9) for a feed post

Available options:

vertical,

horizontal

customParams

seedance · object

required

The generator's inputs

seedance
image-text-slides

Show child attributes

Response

The video, saved in the media library

string

Unique file ID

name

string

Stored file name

originalName

string | null

The name the file was uploaded under

path

string

URL of the stored file. Send it with id as a post's media

thumbnail

string | null

Thumbnail URL, set for video

alt

string | null

Alt text, when one was set

status

enum<string>

A video (MP4 or MOV) is normalized in the background and starts as processing; poll GET /media/{id}/status until it is ready before you put it on a post. Images are ready at once.

Available options:

ready,

processing,

failed

Last modified on October 27, 2026

curl --request POST \
  --url https://api.postqueen.ai/public/v1/generate-video \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "type": "seedance",
  "output": "vertical",
  "customParams": {
    "prompt": "Slow push-in on a bowl of spring salad on a wooden table by a sunny window, steam rising from fresh bread beside it, warm morning light.",
    "images": []
  }
}
'

{
  "id": "c2f1a7d0-5b3e-4f7a-9d61-8e2b4c0a9f13",
  "name": "k3l4m5n6o7.mp4",
  "originalName": null,
  "path": "https://cdn.example.com/k3l4m5n6o7.mp4",
  "thumbnail": "https://cdn.example.com/p8q9r0s1t2.jpg",
  "alt": null,
  "status": "ready"
}

Get started

Endpoints

Posting settings by network

Build on PostQueen

SDK and no-code

The generators

How long it takes

Credits and the free trial

If it fails

Authorizations

Body

Response

​The generators

​How long it takes

​Credits and the free trial

​If it fails

Authorizations

Body

Response

The generators

How long it takes

Credits and the free trial

If it fails