I purchased and tested Mootion because WAN 2.6 was advertised as part of the product, and that was a major reason I bought it. After using it, the current WAN 2.6 implementation does not work for my workflow because I could not upload my own audio and have the model generate a lip-synced video from it.

I did test the available options, including the record workflow suggested by the team, but that is not the same as uploading a song or audio clip directly. My use case is simple: I want to upload a 15-second music clip and have WAN 2.6 generate a video that lip-syncs to that audio. At the time of my use, that workflow was not available in Mootion.

This feedback is specifically about the implementation of an advertised model inside the product. If custom audio upload with lip-sync is important to your workflow, this limitation is worth knowing before purchase. This is apart of wan's function which is a model that mootion advertises. I hope the team improves this, because adding that functionality would make WAN 2.6 much more useful for creators working with their own audio.