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

# Generate a Video

> Generate videos from images and text prompts using the Hedra API.

All examples use the base URL `https://api.hedra.com/web-app/public` and require an `X-API-Key` header.

```bash theme={null}
export HEDRA_API_KEY="your_api_key"
```

## Text-to-video

Generate a video from a text prompt alone using Grok Video T2V (`827122cd-5fdd-4412-86f2-554f7bb8eef9`):

```bash theme={null}
curl -X POST https://api.hedra.com/web-app/public/generations \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $HEDRA_API_KEY" \
  -d '{
    "type": "video",
    "ai_model_id": "827122cd-5fdd-4412-86f2-554f7bb8eef9",
    "generated_video_inputs": {
      "text_prompt": "A woman walking through a busy market at golden hour",
      "aspect_ratio": "16:9",
      "resolution": "720p",
      "duration_ms": 5000
    }
  }'
```

## Image-to-video

Generate a video from a start image using Grok Video I2V (`0435547d-1b30-41ad-bf66-ca476ff0564e`).

### Step 1: Upload a start image

```bash theme={null}
# Create the asset record
curl -X POST https://api.hedra.com/web-app/public/assets \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $HEDRA_API_KEY" \
  -d '{
    "name": "my-image.png",
    "type": "image"
  }'

# Upload the file
curl -X POST https://api.hedra.com/web-app/public/assets/{asset_id}/upload \
  -H "X-API-Key: $HEDRA_API_KEY" \
  -F "file=@/path/to/image.png"
```

### Step 2: Generate the video

```bash theme={null}
curl -X POST https://api.hedra.com/web-app/public/generations \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $HEDRA_API_KEY" \
  -d '{
    "type": "video",
    "ai_model_id": "0435547d-1b30-41ad-bf66-ca476ff0564e",
    "start_keyframe_id": "{image_asset_id}",
    "generated_video_inputs": {
      "text_prompt": "The scene comes to life with gentle movement",
      "aspect_ratio": "16:9",
      "resolution": "720p",
      "duration_ms": 5000
    }
  }'
```

## Required fields

| Field                                | Description                           |
| ------------------------------------ | ------------------------------------- |
| `type`                               | Set to `"video"`                      |
| `generated_video_inputs.text_prompt` | Text description of the video content |

## Optional fields

| Field                                 | Description                                           |
| ------------------------------------- | ----------------------------------------------------- |
| `ai_model_id`                         | The model to use (see `GET /models` for video models) |
| `start_keyframe_id`                   | Asset ID of the start image (required for I2V models) |
| `end_keyframe_id`                     | Asset ID of the end image                             |
| `generated_video_inputs.aspect_ratio` | e.g. `"16:9"`, `"9:16"`, `"1:1"`                      |
| `generated_video_inputs.resolution`   | e.g. `"540p"`, `"720p"`                               |
| `generated_video_inputs.duration_ms`  | Duration in milliseconds                              |
| `batch_size`                          | Generate 1-8 variations at once (default: 1)          |

## Poll for completion

```bash theme={null}
curl https://api.hedra.com/web-app/public/generations/{generation_id}/status \
  -H "X-API-Key: $HEDRA_API_KEY"
```

When `status` is `"complete"`, the response includes an `asset_id` for the generated video.

<Note>
  For avatar and talking-head videos that require audio input, see the [Generate an Avatar Video](/pages/developer/guides/generate-avatar-video) guide.
</Note>