Sat Dec 16, 2023 6:12 pm
+1
Would be nice for so many things like interview with 2 or more people, discussions, podcasts, theater productions.
I would not mind having a tool that looks for talking heads within my multicam Clip and makes some basic editing decisions according to a set of rules that can be set by the user. But unlike Autopod (that seems to focus on separated Audiotracks per Speaker) it should be able to do this with only one Audio track as well.
Thinking about AI tools that already exist like Audiotranscriptions that can separate people by their voice + face recognition + mouth tracking to (all to locate who is or is not speaking) I guess a simple AI multicam editing assistant should be already within reach.
Resolve Studio 18.x / i7 6700k / Windows 10 (64GB Ram) / GeForce GTX 1080TI 11GB / Tangent Wave Tablet / 3 Monitors + 1 Reference Monitor (by Intensity Pro)