# How do you keep camera and audio direction in one prompt?

**URL:** <https://discuss.pytorch.org/t/how-do-you-keep-camera-and-audio-direction-in-one-prompt/225720>\
**Category:** Site Feedback\
**Created:** [October 31, 2026, 6:27pm UTC](https://discuss.pytorch.org/t/how-do-you-keep-camera-and-audio-direction-in-one-prompt/225720 "2026-10-31T18:27:46Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![michael.anderson2689](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/m/e95f7d/32.png) [@michael.anderson2689](https://discuss.pytorch.org/u/michael.anderson2689)\
**Post date:** [October 31, 2026, 6:27pm UTC](https://discuss.pytorch.org/t/how-do-you-keep-camera-and-audio-direction-in-one-prompt/225720/1 "2026-10-31T18:27:46Z")

</div>

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/](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.