Text To Video Endpoint

Generate a video from text prompt only (no starting image). Creates a container scene with the generated video.

Supports multiple models:

• Seedance 1.0 Pro Fast (text-to-video)
• Seedance 1.5 Pro (text-to-video)
• Kling 2.5 Pro (text-to-video)
• Kling 2.6 Pro (text-to-video, supports native audio)
• Veo 3.1 Fast (text-to-video, supports native audio)

Args: request: JSON body containing: - project_id (str, required): Project ID to add the video to - prompt (str, required): Text prompt describing the video - model (str, optional): Model to use. Default: "seedance" - duration (str, optional): Duration in seconds. Default: "5" - aspect_ratio (str, optional): Aspect ratio. Default: "16:9" - generate_audio (bool, optional): Whether to generate audio - negative_prompt (str, optional): Negative prompt - cfg_scale (float, optional): CFG scale 0.0-1.0 - seed (int, optional): Random seed for reproducibility - max_retries (int, optional): Max retry attempts. Default: 3 - initial_delay (float, optional): Initial backoff delay. Default: 1.0

Returns: Success response with scene and video data