Create Muse Video

统一视频创建入口。当前可用 model：omni-10s、veo3.1-fast、veo3.1-lite、veo3.1-lite-hd、grok-imagine-video-1.5（及 fast/lite）、minimax-h3、minimax-h3-max、kling-4.0（720p/1080p）、sd2.5-480p / sd2.5-720p / sd2.5-1080p（按秒）、seedance2.0-md、sd2-480p-ac、sd2-720p-ac、sd2-720p-dl、sd2-720p-db、sd2.0-mini-720p、seedance2.5-30s、sd2.5-720p-ac、sd2.5-720p-933-ac、wan3-720p / wan3-1080p（按秒）、wan3.0-prime-720p / wan3.0-prime-1080p（按秒）、wan3-480p-20s-ac、muse-video / muse-video-20s / muse-video-30s / muse-video-40s / muse-video-50s / muse-video-60s（1–60 秒，按时长分档，原生 720p，按次）。Veo 也可用专用入口 POST /v1/veo/frames。

POST

videos

curl --request POST \
  --url https://sigrunai.com/v1/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "omni-10s",
  "prompt": "A golden retriever running across a sunny meadow, cinematic tracking shot",
  "aspect_ratio": "16:9"
}
'

{
  "code": 20000,
  "msg": "<string>",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "progress": 123,
    "model": "<string>",
    "created_at": 123,
    "completed_at": 123,
    "cost": 123,
    "error_message": "<string>",
    "result": {
      "image_url": "<string>",
      "video_url": "<string>"
    }
  }
}

Create async Muse Video jobs via the shared POST /v1/videos endpoint. On success you get a task_id; poll with Query video task and read result.video_url when completed. Output is native 720p. Billing is per_task (flat per job). Duration does not multiply the price, but it selects the billing model. See the model catalog and the create response cost for live prices.

Model by duration

Send duration or seconds from 1 to 60. The second count selects the billing model, which is returned as model on the create response. A different model name in the request does not override that.

Duration	Billing `model`	When duration is omitted
1–10 s	`muse-video`	5 s if the requested model is `muse-video`
11–20 s	`muse-video-20s`	20 s
21–30 s	`muse-video-30s`	30 s
31–40 s	`muse-video-40s`	40 s
41–50 s	`muse-video-50s`	50 s
51–60 s	`muse-video-60s`	60 s

Durations above 60 seconds are rejected. Requesting muse-video with duration 25 bills muse-video-30s. Requesting muse-video-60s with duration 8 bills muse-video.

Modes

Mode	How to send
Text-to-video	Omit images
First / first-last frames	Send `first_image` and optional `last_image`. Or set `first_last_frame: true` and put first/last URLs in `images`
Reference images	Send `images` / `reference_images` / `image_urls` / `reference_image_urls`

Frames and reference images can be used together. A last frame requires a first frame. Combined count: up to 10 when the job bills as muse-video, and up to 9 on the 20–60 second tiers. Reference videos and reference audios are not supported.

Request fields

Field	Type	Required	Description
`model`	string	yes	Any tier in the table. Underscore forms such as `muse_video_20s` are accepted
`prompt`	string	yes	Subject, action, and mood for the whole clip, 1–4000 characters
`duration` / `seconds`	int \| string	no	1–60. Defaults are in the table. String form is allowed (for example `"25"`)
`aspect_ratio` / `ratio`	string	no	`16:9`, `9:16`, `1:1`, `4:3`, `3:4`; default `16:9`
`orientation`	string	no	`portrait` / `vertical` → `9:16`; `landscape` / `horizontal` → `16:9`
`size`	string	no	A ratio, or `1280x720` / `1920x1080` / `720x1280` / `1080x1920`
`resolution`	string	no	`720p` only; omit it to use the default
`first_image` / `first_image_url`	string	no	First-frame URL
`last_image` / `last_image_url`	string	no	Last-frame URL; requires a first frame
`images` / `reference_images` / `image_urls` / `reference_image_urls`	string[]	no	Reference image URLs. If more than one field is set, the first non-empty list is used, in this order: `reference_images`, `image_urls`, `images`, `reference_image_urls`
`camera_movement`	string	no	Free-text camera move, up to 1000 characters. For example `zoom_in`, `pan_left`, `static`
`style`	string	no	Free-text style, up to 1000 characters. For example `cinematic`, `anime`
`negative_prompt`	string	no	Elements to avoid, separate from `prompt`, up to 1000 characters
`first_last_frame`	boolean	no	When `true`, the first two `images` are the first and last frames
`smart_queue`	bool	no	Default `false`. When `true`, a very low recent success rate keeps the task `queued` until recovery (up to about 2 hours). See Smart queue

Media URLs must be public https:// links, or data URLs.

Examples

Text-to-video (8 seconds, billed as `muse-video`)

curl -X POST 'https://sigrunai.com/v1/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "muse-video",
    "prompt": "A hot-air balloon rising out of morning fog in a valley",
    "duration": 8,
    "aspect_ratio": "16:9",
    "camera_movement": "zoom_in"
  }'

25 seconds (billed as `muse-video-30s`)

curl -X POST 'https://sigrunai.com/v1/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "muse-video",
    "prompt": "A person walking the whole coastline at dusk, coat moving in the wind",
    "duration": 25,
    "aspect_ratio": "9:16",
    "style": "cinematic"
  }'

Frames and a reference image

curl -X POST 'https://sigrunai.com/v1/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "muse-video-20s",
    "prompt": "The person in frame turns and smiles",
    "first_image": "https://example.com/first.png",
    "last_image": "https://example.com/last.png",
    "images": ["https://example.com/ref.png"],
    "negative_prompt": "blurry, watermark, text"
  }'

Omitting duration on muse-video-20s bills a 20-second job. Example success body:

{
  "code": 20000,
  "msg": "提交成功",
  "data": {
    "task_id": "vid_xxxxxxxx",
    "status": "queued",
    "progress": 0,
    "model": "muse-video",
    "cost": 0,
    "result": {}
  }
}

data.model is the billing tier selected from the duration.

Polling

curl -X GET 'https://sigrunai.com/v1/videos/vid_xxxxxxxx' \
  -H 'Authorization: Bearer sk_xxx'

Status values are documented in Query video task. When completed, read data.result.video_url and store the file promptly.

Authorizations

Authorization

string

header

required

控制台创建的 API Key，格式：Bearer sk_xxx

Body

application/json

model

string

required

omni-10s, veo3.1-fast, veo3.1-lite, veo3.1-lite-hd, grok-imagine-video-1.5 (and fast/lite), minimax-h3, minimax-h3-max, kling-4.0 / kling-4.0-720p / kling-4.0-1080p, sd2.5-480p / sd2.5-720p / sd2.5-1080p, seedance2.0-md, sd2-480p-ac, sd2-720p-ac, sd2-720p-dl, sd2-720p-db, sd2.0-mini-720p, seedance2.5-30s, sd2.5-720p-ac, sd2.5-720p-933-ac, wan3-720p / wan3-1080p, wan3.0-prime-720p / wan3.0-prime-1080p, wan3-480p-20s-ac, or muse-video / muse-video-20s / muse-video-30s / muse-video-40s / muse-video-50s / muse-video-60s

Example:

"omni-10s"

prompt

string

required

duration

omni-10s: fixed 10; seedance2.0-md: 5/10/15; sd2-*-ac: 4–15; sd2-720p-dl: fixed 15; sd2-720p-db: 5/10/15; sd2.0-mini-720p: 4–15; sd2.5-480p / sd2.5-720p / sd2.5-1080p: 5–30; seedance2.5-30s: fixed 30; sd2.5-720p-ac and sd2.5-720p-933-ac: 4–30; wan3-720p / wan3-1080p: 10–30; wan3.0-prime-720p: 10–30; wan3.0-prime-1080p: 8–30; wan3-480p-20s-ac: 5–20; Muse Video: 1–60, billed as muse-video (1–10, default 5s when omitted) or muse-video-20s through muse-video-60s

seconds

Alias of duration

aspect_ratio

string

ratio

string

Alias of aspect_ratio

orientation

string

portrait/landscape may imply aspect ratio

size

string

resolution

string

omni-10s is fixed at 720p. Muse Video supports 720p only

first_image

string<uri>

First-frame URL. Used by omni-10s and Muse Video

last_image

string<uri>

Last-frame URL; use with first_image. Muse Video also requires a first frame

images

string<uri>[]

reference_images

string<uri>[]

videos

string<uri>[]

reference_videos

string<uri>[]

reference_video_durations

integer[]

Required with reference videos for kling-4.0; same length as videos; seconds 1–30. Billable seconds = output duration + sum of these values.

Required range: 1 <= x <= 30

reference_audio_durations

integer[]

Required with reference audios for kling-4.0; same length as audios; seconds 5–30 (validation only, not billed).

Required range: 5 <= x <= 30

audios

string<uri>[]

reference_audios

string<uri>[]

first_image_url

string<uri>

Alias of first_image. Accepted by Muse Video

last_image_url

string<uri>

Alias of last_image. Muse Video requires a first frame as well

image_urls

string<uri>[]

Reference image URLs. Muse Video: frames plus references, up to 10 on the 10s tier and 9 on the 20–60s tiers

reference_image_urls

string<uri>[]

Alias of images

camera_movement

string

Muse Video camera move, free text, up to 1000 characters

style

string

Muse Video style, free text, up to 1000 characters

negative_prompt

string

Muse Video negative prompt, separate from prompt, up to 1000 characters

smart_queue

boolean

default:false

When true, a very low recent success rate keeps the task queued until recovery (up to about 2 hours)

Response

200 - application/json

Submitted

code

integer

Example:

20000

msg

string

data

object

Show child attributes

Last modified on November 13, 2026

curl --request POST \
  --url https://sigrunai.com/v1/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "omni-10s",
  "prompt": "A golden retriever running across a sunny meadow, cinematic tracking shot",
  "aspect_ratio": "16:9"
}
'

{
  "code": 20000,
  "msg": "<string>",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "progress": 123,
    "model": "<string>",
    "created_at": 123,
    "completed_at": 123,
    "cost": 123,
    "error_message": "<string>",
    "result": {
      "image_url": "<string>",
      "video_url": "<string>"
    }
  }
}

Gemini Omni

Veo 3.1

Grok Imagine Video

Muse Video

MiniMax H3

Kling 4.0

Wan 3

Seedance 2.0

Seedance 2.5

Create Muse Video

Model by duration

Modes

Request fields

Examples

Text-to-video (8 seconds, billed as `muse-video`)

25 seconds (billed as `muse-video-30s`)

Frames and a reference image

Polling

Authorizations

Body

Response

Model by duration

Modes

Request fields

Examples

Text-to-video (8 seconds, billed as muse-video)

25 seconds (billed as muse-video-30s)

Frames and a reference image

Polling

Authorizations

Body

Response

Text-to-video (8 seconds, billed as `muse-video`)

25 seconds (billed as `muse-video-30s`)