TextToShot, a translator for AI video dialects

Field notes

The interface accepts a raw idea or another model’s prompt, then lets the user choose source and target model profiles before setting cinematic and technical parameters. Its visible structure separates eight elements—subject, action, context, cinematography, lighting, style, dialogue, and audio—from controls such as duration, aspect ratio, resolution, and negative direction. The page lists eight supported model profiles and presents free, subscription, and credit-based access options.