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

# Text to video

> Submit a video prompt with dimensions, duration, quality, and optional media or voice references.

`textVideoSimplify` returns `Content!` for an asynchronous generation. Use
[API key authentication](/api-reference/authentication) and an accessible ready
image model.

## Submit a video generation

```graphql TextToVideo theme={null}
mutation TextToVideo($metadata: SimpleText2VideoContentMetadataInput!) {
  textVideoSimplify(metadata: $metadata) {
    id
    task {
      id
      status
      progress { finishCode }
    }
  }
}
```

```json Variables theme={null}
{
  "metadata": {
    "modelId": "<IMAGE_MODEL_ID>",
    "inputPrompt": "A woman in a red coat walks through a snowy courtyard. The camera follows her at shoulder height.",
    "width": 16,
    "height": 9,
    "isRatio": true,
    "durationInMilliseconds": 5000,
    "quality": "ultra",
    "resolution": "FHD"
  }
}
```

## Metadata

| Field | Type / default | Meaning |
| - | - | - |
| `modelId` | `String!` | Required model ID. |
| `width`, `height` | `Int!` | Required dimensions or ratio components. |
| `isRatio` | `Boolean!`, `false` | Interpret dimensions as an aspect ratio. |
| `durationInMilliseconds` | `Long!` | Required requested video duration, in milliseconds. |
| `inputPrompt` | `String` | Action, scene, and camera direction. |
| `inputNegativePrompt` | `String` | Optional content to avoid. |
| `quality` | `OutputQuality!`, `best` | Video quality: `high`, `best`, `ultra`, or `ultraS`. |
| `resolution` | `VideoResolution` | Optional `SD`, `HD`, `FHD`, `QHD`, or `UHD`, subject to quality support. |
| `seed` | `Long` | Optional generation seed. |
| `modifierIds` | `[Long!]` | Predefined prompt modifiers. |
| `multiShotPrompt` | `[SingleShotPrompt!]` | Structured shot prompts where supported. |
| `elementIds` | `[ID!]` | Accessible image, video, or audio references supported by the selected workflow. |
| `enableBgm` | `Boolean!`, `false` | Request background audio where supported. |
| `voiceModelId` | `ID` | A selected reference voice. |
| `voiceModelIds` | `[ID!]` | Additional ordered reference voices. |

`UHD` requires `ultra` or `ultraS`. Not every quality supports every duration,
resolution, reference type, or shot combination. An accepted enum value does
not guarantee that the combination is valid.

<Note>
  This mutation uses `quality`. [Image to video](/api-reference/image-to-video)
  and [Extend](/api-reference/extend-video) use `outputQuality`.
</Note>

For speech, put dialogue in `inputPrompt` or shot prompts and select the voices
through `voiceModelId` or `voiceModelIds`. Follow the
[voice notation](/api-reference/image-to-video#dialogue-and-voice-references).
Voice and audio references share the selected workflow's reference budget.

Save the returned content and task IDs and use
[tasks and results](/api-reference/tasks-and-results) to poll and download.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.