Free tool that converts a video (MP4/WebM/MOV, <=30MB) or image into a structured English prompt. A vision model analyzes subject, action, camera move, lighting and style, adapting wording for Kling, Veo 3 and Sora. No s…
Free tool that converts a video (MP4/WebM/MOV, <=30MB) or image into a structured English prompt. A vision model analyzes subject, action, camera move, lighting and style, adapting wording for Kling, Veo 3 and Sora. No signup.
Discuss this product