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

# Video capabilities

> Discover model parameters and media inputs to build a dynamic video-generation form.

## Read the catalog

```bash theme={"dark"}
curl 'https://gengen.farm/v1/video/capabilities?workflow=scriptToVideo'
```

This read-only endpoint requires no API key and creates no task or charge.
Use `workflow=api` (the default) for API modes, or `scriptToVideo` for modes
available in the script-to-video workflow. Unsupported workflows return HTTP 400.

The response contains `schemaVersion`, `endpoint`, `workflow`, `defaultModel`,
and `models`. Version 1 describes visible models on the standard video task
endpoint. Refresh this response after a model update instead of keeping your own
model list. Account permissions, input validation and available balance are
checked separately when generating.

## Build a request from a mode

1. Select a model and one of its `modes`.
2. Render its `controls` using `type`: `select`, `boolean`, `number` or `text`.
   Apply `defaultValue`, `required`, bounds and `readOnly`. Numeric controls allow
   decimals when `integer` is `false`.
3. Apply matching `valuesWhen` constraints when another control changes.
   Each rule's `when` keys must all match. `valuesByResolution` supplies the same
   behavior for resolution-dependent choices. Review changed settings again.
4. Collect the images, videos or audio described by `mediaSlots`, respecting
   `required`, `multiple`, `max`, model `mediaLimits` and mode `materialRules`.
5. Place each control at its `requestPath`. Without an explicit path, use
   `controls[key]`. Place media at `assets[requestKey ?? key]`; a slot with
   `requestMultiple: false` expects a single URL.
6. Submit the canonical body to the returned `endpoint` with your API key.

For example, a Veo `negativePrompt` selection maps to
`providerOptions.google.negativePrompt`, while `duration` remains
`controls.duration`. Image references map to `assets.referenceImages`.

```json theme={"dark"}
{
  "model": "veo-3.1-generate-001",
  "mode": "text_to_video",
  "prompt": "An orange soda bottle on a sunny table.",
  "assets": {},
  "controls": {
    "duration": 8,
    "resolution": "1080p",
    "ratio": "16:9",
    "generateAudio": true
  },
  "providerOptions": {
    "google": { "negativePrompt": "blurry image" }
  }
}
```

Keep request values unchanged when translating the interface. Optional
`translations` provide localized labels, help and enum display names.

Discovery covers form-compatible choices. Additional native parameters and
legacy request formats documented for each model remain available. Modes may
have different workflow availability; for example, Veo video extension is
API-only. Actual media bytes are validated before upstream submission, so
metadata discovery does not guarantee that a particular file will be accepted.


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