| prompt | STRING | | The text prompt used to guide video generation. |
| reference_imageopt | IMAGE | | The image to use as a reference for content or style. |
| reference_image_gcs_uriopt | STRING | | No documentation available |
| reference_typeopt | COMBO | ASSET | Asset image: You provide up to three images of a single person, character, or product. Veo preserves the subject's appearance in the output video. Style image: You provide a single style image. Veo applies the style from your uploaded image in the output video. This feature is only supported by veo-2.0-generate-exp in Preview. |
| negative_promptopt | STRING | | Optional. A text string that describes anything you want to discourage the model from generating. |
| output_gcs_uriopt | STRING | None/videos/video-with-reference-20260720-202149.mp4 | GCS URI where the generated videos will be stored, in the format 'gs://BUCKET_NAME/SUBDIRECTORY'. |
| modelopt | COMBO | veo-3.1-generate-preview | The Veo model to use for video generation. |
| aspect_ratioopt | COMBO | 16:9 | Optional. Specifies the aspect ratio of generated videos. |
| mime_typeopt | COMBO | image/png | No documentation available |
| duration_secondsopt | INT | 81–10 | Required. The length in seconds of video files that you want to generate. |
| resolutionopt | COMBO | 1080p | Optional. Veo 3 models only. The resolution of the generated video. |
| fpsopt | INT | 241–60 | Optional. Frames per second for the generated video. |
| number_of_videosopt | INT | 11–4 | Optional. Number of video variations to generate. |
| enhance_promptopt | BOOLEAN | true | Optional. Use Gemini to enhance your prompts. |
| generate_audioopt | BOOLEAN | false | Generate audio for the video. |
| person_generationopt | COMBO | allow_adult | Optional. The safety setting that controls whether people or face generation is allowed. |
| seedopt | INT | 00–2147483647 | Optional. A number to request to make generated videos deterministic. Adding a seed number with your request without changing other parameters will cause the model to produce the same videos. |