Create Text-to-Video Task
Vidu text-to-video API guide: generate videos from text with viduq3-pro and viduq3-turbo, with direct audio output, off-peak mode, and a model comparison.
(Vidu Video)
Turn text descriptions into high-quality videos with the Vidu model series. Supports advanced features such as direct audio output, off-peak mode, and custom watermarks.
Quick Start
Video generation is asynchronous. The whole flow takes three steps:
1. Submit the task → get a task_id
2. Poll the status → wait for status to become completed and return a public URL📌 Basics
- Endpoint:
POST /v1/video/generations - Authentication:
Bearer Token(Authorization: Bearer {{YOUR_API_KEY}}) - Content type:
application/json
📥 Request Parameters (Request Body)
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Model name. Options: viduq3-turbo (fast), viduq3-pro (best quality), viduq2, viduq1. |
| prompt | string | Yes | Text description of the video (max 5000 characters). |
| duration | integer | No | Duration in seconds. Q3 series: 1-16; Q2: 1-10; Q1: fixed at 5. |
| seed | integer | No | Random seed. Pass 0 or omit for random. |
| metadata | object | No | Extended configuration object. |
| └─ aspect_ratio | string | No | Aspect ratio. Default 16:9. Options include 9:16, 1:1, etc. (3:4/4:3 are Q2/Q3 only). |
| └─ resolution | string | No | Resolution. Options: 540p, 720p, 1080p (Q1 only supports 1080p). |
| └─ audio | boolean | No | Direct audio output (with sound effects/dialogue). Q3 series only, default true. |
| └─ bgm | boolean | No | Automatically add background music. Default false. |
| └─ off_peak | boolean | No | Off-peak mode. Lower credit cost when enabled; generates within 48 hours. |
| └─ callback_url | string | Yes | Callback URL for receiving asynchronous task status notifications. |
| └─ watermark | boolean | No | Whether to add a watermark. |
🚀 Model Comparison
| Model | Core strengths | Duration range | Resolutions |
|---|---|---|---|
| viduq3-pro | Top-tier quality, vivid and dimensional | 1 - 16s | 540p / 720p / 1080p |
| viduq3-turbo | Blazing-fast generation, great value | 1 - 16s | 540p / 720p / 1080p |
| viduq2 | Latest general-purpose model | 1 - 10s | 540p / 720p / 1080p |
| viduq1 | Smooth transitions, stable camera work | 5s | 1080p |
📤 Response
Status code: 200 OK (task submitted)
| Field | Type | Description |
|---|---|---|
| id | string | Unique task ID. |
| task_id | string | Task ID (used for queries). |
| status | string | Task status (e.g. queued). |
| progress | integer | Generation progress. |
| created_at | integer | Creation timestamp. |
📝 Request Example
{
"model": "viduq3-turbo",
"prompt": "The camera captures a woman sitting in a cafe; she looks up out the window as the camera moves slowly. Warm tones, relaxed and cozy atmosphere.",
"duration": 7,
"seed": 3,
"metadata": {
"aspect_ratio": "16:9",
"resolution": "1080p",
"audio": true,
"bgm": false,
"off_peak": false,
"callback_url": "https://your-api.com/v1/callback/vidu"
}
}Get Video Generation Task Status
Query Vidu video task status by task_id: fetch progress, video download URL, cover image, speech and sound tracks, and consumed credits, with URL expiry tips.
Image-to-Video
Wan image-to-video API guide: turn a reference image and prompt into cinematic video with wan2.6-i2v-flash, covering request parameters and prompt tips.