Enable direct audio-video generation capability (default true for q3 model)

Audio type when audio is true: all (sound effects + vocals), speech_only, sound_effect_only. Ineffective for q3 model

Add background music to generated video (ineffective for q3 model)

Callback URL for task status updates

Video duration in seconds. viduq3-pro: 1-16, viduq2-pro-fast: 1-10, viduq2-pro/turbo: 1-8

Use recommended prompt (consumes additional 10 credits)

Metadata identification, JSON format string for custom metadata

Model name: viduq3-pro, viduq2-pro-fast, viduq2-pro, viduq2-turbo, viduq1, viduq1-classic, vidu2.0

Movement amplitude of objects in frame (ineffective for q2, q3 models)

Off peak mode (lower cost, tasks generated within 48 hours)

Transparent transmission parameters (max 1048576 characters)

Text prompt for video generation (max 2000 characters)

Resolution: 360p, 540p, 720p, 1080p, 2K (availability depends on model and duration)

Random seed (defaults to random if not specified)

Voice ID for audio (ineffective for q3 model)

Add watermark to video (default false)

Watermark position: 1 (top left), 2 (top right), 3 (bottom right, default), 4 (bottom left)

Watermark image URL (uses default watermark if not provided)

Whether background music was added

Off peak mode status

Transparent transmission parameters

Whether watermark was added