Spark Dance 2.0 Mini | Vtrix API Docs

API Notes

Spark Dance 2.0 Mini accepts multimodal reference inputs through the content array. You can combine text prompts with reference images, a reference video, and reference audio in one request.

When using audio_url, include at least one reference image or reference video. Set generate_audio to true when you want the output video to include generated or synchronized audio.

Authentication

authorization `string` required

All APIs require authentication via Bearer Token.

Get API Key:

Visit API Key Management Page to get your API Key.

Usage:

Add to request header:

Authorization: Bearer YOUR_API_KEY

Parameters

model `string` required

Model ID to use for the request.

Value: spark_dance_v2_0_mini

content `object[]` required

Input content for video generation. Seedance 2.0 series multimodal reference generation supports 0-9 reference images, 0-3 reference videos, 0-3 reference audio inputs, and optional text. Supported combinations include:

Text only
Text (optional) + image
Text (optional) + video
Text (optional) + image + audio
Text (optional) + image + video
Text (optional) + video + audio
Text (optional) + image + video + audio

Audio cannot be used as the only input. When using audio, include at least 1 reference image or reference video.

Direct uploads of reference images or videos containing real human faces are not supported.

Text Information object

Text information input to the model.

type string required

Type of input content.

Value: text

text string required

Text prompt input to the model, describing the expected generated video. Text is optional for the overall content array. Prompts can describe the camera, subject, scene, audio, sound effects, and final-frame intent.

Image Information object

Image information input to the model.

type string required

Type of input content.

Value: image_url

image_url object required

Image object input to the model.

url string required

Public image URL, Base64 image string, or asset ID.

Image requirements:

Single image size: less than 30 MB

Request body size: no more than 64 MB

Width and height: 300 - 6000 px

Aspect ratio: (0.4, 2.5)

Reference image count: 0 - 9

role string

Position or purpose of the image.

Options: reference_image

Video Information object

Video input to the model.

type string required

Type of input content.

Value: video_url

video_url object required

Video object input to the model.

url string required

Public video URL.

Video requirements:

Formats: mp4, mov

Single video duration: 2 - 15 seconds

Reference video count: 0 - 3; total duration no more than 15 seconds

Single video size: no more than 200 MB

FPS: 24 - 60

role string

Position or purpose of the video.

Options: reference_video

Audio Information object

Audio input to the model. Audio cannot be used as the only input. Include at least 1 reference image or reference video.

type string required

Type of input content.

Value: audio_url

audio_url object required

Audio object input to the model.

url string required

Public audio URL.

Audio requirements:

Formats: wav, mp3

Single audio duration: 2 - 15 seconds

Reference audio count: 0 - 3; total duration no more than 15 seconds

Single audio size: no more than 15 MB

role string

Position or purpose of the audio.

Options: reference_audio

generate_audio `boolean`

Controls whether the generated video includes audio.

true: The video output includes generated or synchronized audio based on the prompt and reference audio.

false: The video output is silent.

Default: true

resolution `string`

Video resolution.

Default: 720p

Options: 480p, 720p

Do not set 1080p or 4k for Mini. 1080p is not supported by Seedance 2.0 Fast/Mini, and 4k is only supported by Seedance 2.0.

ratio `string`

Aspect ratio of the generated video.

When ratio is set to adaptive, the model automatically selects the aspect ratio according to the generation scenario. For multimodal reference generation, it judges from the prompt intent. If the intent is first-frame generation, video editing, or video extension, it selects the closest aspect ratio from the corresponding image or video; otherwise, it selects the closest aspect ratio from the first uploaded media file, with priority video > image.

Default: adaptive

Options: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive

duration `integer`

Generated video duration in seconds.

Set to an integer in the valid range, or set to -1 to let the model intelligently select an integer duration in the valid range.

Default: 5

Range: [4, 15], or -1 for auto duration

watermark `boolean`

Whether the generated video contains a watermark.

true: Add watermark
false: Do not add watermark

Default: false

return_last_frame `boolean`

Whether task query responses can return the last frame of the generated video.

true: Return the generated video’s last frame as a PNG image with the same width and height as the video and no watermark.

false: Do not return the last frame.

Default: false

execution_expires_after `integer`

Task timeout threshold after submission, in seconds. When the threshold is reached, the task is marked as expired.

Default: 172800

Range: [3600, 259200]

safety_identifier `string`

Unique identifier for the end user, used to help the platform detect users who may violate usage policies. The value should be stable and unique for each user.

Maximum length: 64 characters

Recommendation: pass a username, user ID, or email hash, and avoid exposing private information.

callback_url `string`

Callback notification address for task results.

Polling

Since result generation takes time, you need to poll the task status after creating the task.

The initial response only returns information such as the task ID and initial status. The final result must be obtained by polling the task status endpoint using the task ID.

See the examples on the right for polling requests and responses.

Response Format

The task query response returns generated video resources under output[].content[] when status is completed. The usage object contains SeaCloud billing and usage information; upstream token usage is recorded by the system and may be included in the query response for reference.

error `object`

Error information, only present when status is failed

code string

Error code

message string

Detailed error message

output `array`

Generation results, only present when status is completed

content array

List of generated resource content

type string

Resource type

Value: image｜video

url string

Processed resource URL

jobId string

Remote task ID

usage `object`

Usage statistics, only present when status is completed

cost string

Total cost in USD

discount number

Discount amount

metadata `object`

Metadata information

curl --location --request POST 'https://cloud.vtrix.ai/model/v1/generation' \ --header 'Authorization: Bearer YOUR_API_KEY' \ --header 'Content-Type: application/json' \ --data-raw '{ "model": "spark_dance_v2_0_mini", "input": [ { "params": { "content": [ { "type": "text", "text": "Use the first-person POV framing from Video 1 throughout, and use Audio 1 as the background music throughout. First-person POV fruit tea promotional ad, Spark Dance brand limited-edition apple fruit tea." }, { "type": "image_url", "image_url": { "url": "https://example.com/image-1.jpg" }, "role": "reference_image" }, { "type": "image_url", "image_url": { "url": "https://example.com/image-2.jpg" }, "role": "reference_image" }, { "type": "video_url", "video_url": { "url": "https://example.com/reference-video.mp4" }, "role": "reference_video" }, { "type": "audio_url", "audio_url": { "url": "https://example.com/reference-audio.mp3" }, "role": "reference_audio" } ], "generate_audio": true, "resolution": "720p", "ratio": "16:9", "duration": 11, "watermark": false } } ] }'

{ "id": "task_id", "created_at": 1769757744021, "status": "completed", "model": "spark_dance_v2_0_mini", "output": [ { "content": [ { "type": "video", "url": "https://example.com/generated-video.mp4", "jobId": "remote_job_id_12345" } ] } ], "usage": { "cost": "0.000500", "discount": 0 } }

API Notes

Authentication

authorization string required

Parameters

model string required

content object[] required

Text Information object

type string required

text string required

Image Information object

type string required

image_url object required

url string required

role string

Video Information object

type string required

video_url object required

url string required

role string

Audio Information object

type string required

audio_url object required

url string required

role string

generate_audio boolean

resolution string

ratio string

duration integer

watermark boolean

return_last_frame boolean

execution_expires_after integer

safety_identifier string

callback_url string

Polling

Response Format

error object

code string

message string

output array

content array

type string

url string

jobId string

usage object

cost string

discount number

metadata object

authorization `string` required

model `string` required

content `object[]` required

Text Information `object`

type `string` required

text `string` required

Image Information `object`

type `string` required

image_url `object` required

url `string` required

role `string`

Video Information `object`

type `string` required

video_url `object` required

url `string` required

role `string`

Audio Information `object`

type `string` required

audio_url `object` required

url `string` required

role `string`

generate_audio `boolean`

resolution `string`

ratio `string`

duration `integer`

watermark `boolean`

return_last_frame `boolean`

execution_expires_after `integer`

safety_identifier `string`

callback_url `string`

error `object`

code `string`

message `string`

output `array`

content `array`

type `string`

url `string`

jobId `string`

usage `object`

cost `string`

discount `number`

metadata `object`