Generate videos from text prompts with optional image and audio inputs.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
The video generation model to use.
"p-video"
Optional text prompt describing the video to generate.
"A butterfly flying through a flower garden"
Duration of the generated video in seconds.
5
Output video resolution.
"720p"
Frames per second for the generated video.
24
Aspect ratio of the output video.
"16:9"
Optional input image URL to guide or initialize video generation.
"https://example.com/input-image.jpg"
Optional input audio URL to include in the generated video.
"https://example.com/audio.mp3"
Whether to generate a draft/preview version of the video.
Whether to retain the provided audio in the final generated video.
Whether to automatically enhance or expand the prompt before generation.