Hi all - a workflow note rather than a launch post.
Most prompt-to-video tools make you write the shot, then a separate camera note, then a separate sound pass, and the three drift apart by the time you render. We have been building Muse Video (https://muse-video.app/) around the opposite idea: one prompt-led brief carries the subject, its motion, the camera treatment, the visual details you want preserved, and the native-audio direction together.
The model is presented as preview-stage on the site, so treat it as a way to work in that prompt style today rather than a claim about general availability.
Full disclosure: I work on this project, so mods are welcome to move or remove the thread if it does not fit the category.