Vidu Text-to-Video API

Generate video from a text prompt. Async task API: submit a request, receive a task_id, then poll the [Query Creations endpoint](./creations) for the result.

Generate video from a text prompt. Supports viduq3-turbo, viduq3-pro, viduq2, and viduq1 models, up to 1080p, with duration up to 16 seconds depending on the model.

This is an async task-based API: submit a request to receive a task_id, then poll the Query Creations endpoint for the result.

Base URL

https://api.autorouter.top — Production

Authentication

BearerAuth: http (bearer) Authenticate using a Bearer Token. Format: Authorization: Bearer sk-xxxxxx

Endpoints

POST `/vidu/ent/v2/text2video`

Create Text-to-Video Task

Create a video generation task from a text prompt.

Request Body

Content-Type: application/json

Example:

{
  "model": "viduq3-pro",
  "style": "general",
  "prompt": "In an ultra-realistic fashion photography style featuring light blue and pale amber tones, an astronaut in a spacesuit walks through the fog. The background consists of enchanting white and golden lights, creating a minimalist still life and an impressive panoramic scene.",
  "duration": 5,
  "seed": 0,
  "aspect_ratio": "4:3",
  "resolution": "540p",
  "movement_amplitude": "auto",
  "off_peak": false
}

Properties:

Name	Type	Required	Description
`model`	string	Yes	Model name. Available values: `viduq3-turbo`, `viduq3-pro`, `viduq2`, `viduq1`. `viduq3-turbo` generates faster; `viduq3-pro` has better audio-video quality; `viduq2` is the latest model; `viduq1` delivers clear visuals and stable camera motion
`style`	string	No	Style, default `general`. Available: `general`, `anime`. Not effective when using q2 or q3 series models
`prompt`	string	Yes	Text prompt describing the desired video content. Maximum 5,000 characters
`duration`	integer	No	Video duration in seconds. `viduq3-pro` / `viduq3-turbo`: default 5, range 1–16; `viduq2`: default 5, range 1–10; `viduq1`: default 5, only 5 supported
`seed`	integer	No	Random seed. Uses a random value if omitted or set to `0`
`aspect_ratio`	string	No	Aspect ratio, default `16:9`. Available: `16:9`, `9:16`, `3:4`, `4:3`, `1:1`. `3:4` and `4:3` supported only on q2 and q3 series
`resolution`	string	No	Resolution. `viduq3-pro` / `viduq3-turbo`: default `720p`, available `540p`, `720p`, `1080p`; `viduq2`: default `720p`, available `540p`, `720p`, `1080p`; `viduq1`: default `1080p`, available `1080p`
`movement_amplitude`	string	No	Motion amplitude, default `auto`. Available: `auto`, `small`, `medium`, `large`. Not effective on q2 and q3 series
`bgm`	boolean	No	Whether to add background music, default `false`. Not effective on q2 when duration is 9 or 10 seconds; not effective on q3 series
`audio`	boolean	No	Whether to output audio and video together, default `true`. `false` outputs a silent video; `true` outputs video with dialogue and sound effects. Supported only on q3 series
`payload`	string	No	Passthrough parameter, up to 1,048,576 characters
`off_peak`	boolean	No	Off-peak mode, default `false`. When `true`, credits cost less; the task is generated within 48 hours, and is automatically canceled with credits refunded if it times out
`watermark`	boolean	No	Whether to add a watermark, not added by default. Use `watermarked_url` from the query endpoint to retrieve the watermarked result
`wm_position`	integer	No	Watermark position: `1` top-left, `2` top-right, `3` bottom-right (default), `4` bottom-left
`wm_url`	string	No	Custom watermark image URL; uses the default watermark if omitted
`meta_data`	string	No	Metadata identifier, JSON format string, passthrough field
`callback_url`	string	No	Callback URL (POST) when task status changes. Callback body matches the Query Creations endpoint; statuses include `processing`, `success`, `failed`

Responses

200: Task created successfully

Content-Type: application/json

400: Bad request / invalid parameters

Content-Type: application/json

429: Rate limit exceeded

Content-Type: application/json

Request Example

curl -X POST "https://api.autorouter.top/vidu/ent/v2/text2video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxx" \
  -d '{
  "model": "viduq3-pro",
  "style": "general",
  "prompt": "In an ultra-realistic fashion photography style featuring light blue and pale amber tones, an astronaut in a spacesuit walks through the fog.",
  "duration": 5,
  "seed": 0,
  "aspect_ratio": "4:3",
  "resolution": "540p",
  "movement_amplitude": "auto",
  "off_peak": false
}'

Response Example

{
  "task_id": "your_task_id_here",
  "state": "created",
  "model": "viduq3-pro",
  "style": "general",
  "prompt": "In an ultra-realistic fashion photography style featuring light blue and pale amber tones, an astronaut in a spacesuit walks through the fog.",
  "duration": 5,
  "seed": 123456,
  "aspect_ratio": "4:3",
  "resolution": "540p",
  "movement_amplitude": "auto",
  "payload": "",
  "off_peak": false,
  "credits": 4,
  "created_at": "2025-01-01T15:41:31.968916Z"
}

Response fields:

Name	Type	Description
`task_id`	string	Task ID for querying creations
`state`	string	Processing status. Enum: `created`, `queueing`, `processing`, `success`, `failed`
`model`	string	Model name used in this request
`prompt`	string	Prompt used in this request
`duration`	integer	Video duration in seconds
`seed`	integer	Random seed
`aspect_ratio`	string	Aspect ratio
`resolution`	string	Resolution
`bgm`	boolean	Whether background music was added
`movement_amplitude`	string	Motion amplitude
`payload`	string	Passthrough parameter
`off_peak`	boolean	Whether off-peak mode was used
`credits`	integer	Credits consumed by this request
`watermark`	boolean	Whether a watermark was added
`created_at`	string	Task creation time

GET `/vidu/ent/v2/tasks/{id}/creations`

Query Creations

Query task status and generation results using the task_id returned when creating the task. Creation URLs are valid for 24 hours. See the Query Creations endpoint for details.

Path Parameters

Name	Type	Required	Description
`id`	string	Yes	Task ID

Request Example

curl -X GET "https://api.autorouter.top/vidu/ent/v2/tasks/{task_id}/creations" \
  -H "Authorization: Bearer sk-xxxxxx"

Response Example

{
  "id": "your_task_id",
  "state": "success",
  "err_code": "",
  "credits": 4,
  "payload": "",
  "creations": [
    {
      "id": "your_creations_id",
      "url": "your_generated_results_url",
      "cover_url": "your_generated_results_cover_url",
      "watermarked_url": "your_generated_results_watermarked_url"
    }
  ]
}

Response fields:

Name	Type	Description
`id`	string	Task ID
`state`	string	Processing status: `created`, `queueing`, `processing`, `success`, `failed`
`err_code`	string	Error code, returned on failure
`credits`	integer	Credits consumed by this task
`payload`	string	Passthrough parameter
`creations`	array	List of generation results
`creations[].id`	string	Creation ID
`creations[].url`	string	Creation URL, valid for 24 hours
`creations[].cover_url`	string	Cover URL, valid for 24 hours
`creations[].watermarked_url`	string	Watermarked creation URL, valid for 24 hours

Error Handling

HTTP 400 Parameter Errors (pre-submit validation, no billing)

AutoRouter validates required fields before submitting upstream:

Scenario	Response
Missing `prompt`	`{"code":"InvalidParameter","message":"...","request_id":"..."}`
Unknown model	`{"code":"InvalidParameter","message":"unknown model: ...","request_id":"..."}`

HTTP 401 / 403 Auth Errors

401 Unauthorized: API Key invalid or expired
403 Forbidden: API Key has no access to this model (check token's model allowlist)

HTTP 402 Insufficient Balance

Returns insufficient user quota. Top up at the AutoRouter console.

Task `failed` Status

The task was accepted but upstream generation failed (state == "failed"). See err_code for details:

Reason	Suggested Action
Content moderation	Adjust prompt to avoid sensitive content
Illegal parameter combo (e.g. unsupported resolution)	Follow the Request Body specification

When a task enters failed, AutoRouter automatically refunds the billed quota. Check refund records in the logs page.

Text-to-Video

On this page