> ## Documentation Index
> Fetch the complete documentation index at: https://mulerouter.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Wan 2.6 Text-To-Video Spark Generation

> Generate videos from text prompts using the wan2.6-t2v-spark model.

<Note>
  This is a fine-tuned model by MuleRouter based on the Wan2.6 Text-to-Video architecture. It offers improved quality and performance for specific use cases.
</Note>

## Overview

Generate videos from text prompts using the wan2.6-t2v-spark model with support for longer durations and multi-shot generation.

## Key Features

* Text-to-video generation with audio support
* 1080P resolution options
* 5s, 10s, or 15s duration
* Single or multi-shot generation
* Fine-tuned for enhanced visual quality

## Resolution Options

### 1080P

* 1920×1080 (16:9)
* 1080×1920 (9:16)
* 1440×1440 (1:1)
* 1632×1248 (4:3)
* 1248×1632 (3:4)

## Example Requests

### Basic Text-to-Video

```json theme={null}
{
  "prompt": "Miyazaki-style mule dancing",
  "size": "1920*1080",
  "duration": 5
}
```

### Multi-shot Video

```json theme={null}
{
  "prompt": "Waves crashing against rocks, water splashing, sunlight on the sea",
  "size": "1920*1080",
  "duration": 10,
  "prompt_extend": true,
  "multi_shots": "multi",
  "audio": true
}
```

### With Custom Audio

```json theme={null}
{
  "prompt": "A person walking through a city at night",
  "size": "1920*1080",
  "duration": 15,
  "audio_url": "https://example.com/city_sounds.mp3"
}
```

## Parameters

### multi\_shots

* **Default**: single
* **Effect**: When prompt rewriting is enabled, controls whether the output is single-shot or multi-shot
* **Only effective when**: `prompt_extend` is enabled

### duration

* **Options**: 5, 10, or 15 seconds
* **Note**: Longer durations may increase processing time


## OpenAPI

````yaml api-reference/endpoint/mulerouter/wan2.6-t2v-spark/wan2.6-t2v-spark.yaml POST /vendors/mulerouter/v1/wan2.6-t2v-spark/generation
openapi: 3.1.0
info:
  title: Wan2.6-t2v-spark API
  description: Wan2.6 Text-to-Video Spark Model API - Fine-tuned by MuleRouter
  license:
    name: MIT
  version: 1.0.0
servers:
  - url: https://api.mulerouter.ai/
security:
  - bearerAuth: []
paths:
  /vendors/mulerouter/v1/wan2.6-t2v-spark/generation:
    post:
      summary: Create Generation Task
      description: Generate videos from text prompts using the wan2.6-t2v-spark model.
      operationId: wan26_t2v_spark_generation
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/Wan26T2VSparkRequest'
        required: true
      responses:
        '202':
          description: Accepted - Task created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreatedResponse'
components:
  schemas:
    Wan26T2VSparkRequest:
      type: object
      additionalProperties: false
      properties:
        prompt:
          type: string
          description: >-
            Text description for the desired video content (max 2000
            characters).
          maxLength: 2000
        negative_prompt:
          anyOf:
            - type: string
            - type: 'null'
          description: Negative prompt describing unwanted content (max 500 characters).
          maxLength: 500
        size:
          type: string
          description: >-
            Output resolution ("width\*height"). Supported tiers:

            - 1080P: 1920\*1080 (16:9), 1080\*1920 (9:16), 1440\*1440 (1:1),
            1632\*1248 (4:3), 1248\*1632 (3:4)
          enum:
            - 1920*1080
            - 1080*1920
            - 1440*1440
            - 1632*1248
            - 1248*1632
          default: 1920*1080
        duration:
          type: integer
          description: Video duration in seconds. Supported values 5, 10, or 15.
          enum:
            - 5
            - 10
            - 15
        prompt_extend:
          type: boolean
          description: >-
            Enable intelligent prompt rewriting (slightly longer latency, better
            detail).
          default: true
        shot_type:
          anyOf:
            - type: string
              enum:
                - single
                - multi
            - type: 'null'
          description: |-
            Specifies the shot type for video generation.

            Only takes effect when prompt_extend is enabled.

            - single: Default value, outputs single-shot video
            - multi: Outputs multi-shot video
          default: single
        audio:
          anyOf:
            - type: boolean
            - type: 'null'
          description: >-
            Enable automatic audio generation. Set to false to force a silent
            output.
          default: true
        audio_url:
          anyOf:
            - type: string
              format: uri
            - type: 'null'
          description: >-
            Custom audio file URL (wav/mp3, 3-30s, ≤15MB). Overrides the audio
            flag.
        seed:
          type: integer
          description: Random seed [0, 2147483647].
          minimum: 0
          maximum: 2147483647
        safety_filter:
          anyOf:
            - type: boolean
            - type: 'null'
          description: >-
            Enable content safety filter. Defaults to true. Set to false to
            disable content safety inspection.
          default: true
      required:
        - prompt
    TaskCreatedResponse:
      type: object
      additionalProperties: true
      properties:
        task_info:
          $ref: '#/components/schemas/TaskInfoCreated'
    TaskInfoCreated:
      type: object
      additionalProperties: true
      properties:
        id:
          type: string
          description: UUID of the task
          format: uuid
        status:
          type: string
          description: Task status (pending when created)
          enum:
            - pending
        created_at:
          type: string
          description: Task creation timestamp (ISO 8601)
          format: date-time
        updated_at:
          type: string
          description: Task last update timestamp (ISO 8601)
          format: date-time
      required:
        - id
        - status
        - created_at
        - updated_at
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer

````