I have had this idea to be able to control broadcast equipment with verbal commands for about a quarter now but got super busy with classes and never really got to pursue too much expirimenting with it yet. My dad originally suggested being doing something with voice control and PTZ cameras as well as ATEM switchers. After doing thinking I came up with the 3 different ideas 1 of which I was really liking the idea of.
My original idea I was thinking I would go with was being able to use voice control with OBS or any other streaming software. I used to do casting for Rocket League and I would have to put on the shoes of production and on screen talent when doing that. That got very difficult pressing all the buttons while focusing on talking and also setting up lobbies at the same time. Having voice commands would have really taking a huge chunk of the work and making it a much smaller task. However, after a quick google I found that voice control has already been made for OBS and seemed to be sufficient enough for most needs and although it may not have been used for what I was thinking, it definitely could be so I wanted to look in diffrent ares.
After this I went back to thinking about what was originally suggested to me and the PTZ cameras seemed to have some emphasis on them when suggested to me. There are many educational and medical scenarios where people can't be hands on but need to record and possibly control a camera. Once again though it seems that someone else had also noticed that especially for medical educational recording. I know there are options for me to explore there but when also looking at the tech I have access to I don't see myself getting too far with that.
This all finally lead me to where I want to take my project. Again, one of the things suggested originally was controlling an ATEM switcher. This still fits into broadcasting as well as these scenarios where people may have multiple cameras in these situations that they can't use their hands. Being able to use voice commands to control and ATEM switcher could fall into many fields and be useful. I really want to focus on creating a visual experience with the voice control as well as include audio to allow feedback to the user as well as full functionality and customization abilities.
Luckily for me there doesn't seem to be anything about using voice control to switch between cameras and video feeds and on top of that Blackmagic has a great API to use with their equipment that other tools already use and I may be able to integrate into my project. To me this feels like it will be the perfect combination many disiplines as well as forcing me to use tools in ways I have never used them before.
My goal for this project as an initial concept will be to creat a 3D model of an ATEM Mini and bring that into unreal textured as a visual representation of the real ATEM which unreal will either directly be communicating and sending commands to or with a middle man software if I am unable to get there directly by when I need to have work to show.
Week 4 - Begin final tests of voice control capabilities from unreal
Week 5 & 6 - Create a usable model of an ATEM Switcher (Likely the ATEM Mini pictured above)
Week 7 & 8 - Implement models and program in the visual feedback.
Week 9 - Look into sound feedback and if that should be added(if so how and what)
Week 10 - Final tests ideally from other users