Generate video with actions based on speech AI Image Prompt

Content: The prompt requires generating a video with actions dynamically adjusted based on speech content. It is a dynamic generation instruction, lacking detailed visual elements such as subject, scene, style, composition, etc.

Pros: Concise and direct, giving AI greater freedom in generation.

Cons: Lacks visual details, which may lead to uncontrollable or unexpected results.

Reference image: No obvious reference-image dependency