I am in the process of designing a game, and I require all the innovative features of Game Engine that are available.
One that is not, however, is microphone or voice recognition support.
Could something like a system where you input a voice sample into Blender and then program it to recognise the sample when said, and then carry out a task that has been allocated to it be made?
I hope something like this is being considered for 2.5 release.
Well, Not built in no not at all. Not even through python. But, assuming you’re making something so innovative you’d probably have someone expierienced with any other programming language in which you could make seperate DLL’s.
That’s an extremely advanced feature which has not even to this point been perfected in operating systems. The last open source voice recognition software I looked at was written in Perl. I think it is a bit much to ask at this point. I foresee voice recognition to come into the mainstream in the next five years or so, but at this point unless you want to write the interface that is unlikely to the point of unreasonable.
I don,t think its that advanced my cheap cell phone does it fine. That said I am not a coder or familiar with the game engine so its implementation may be hard.
It’s like handwriting recognition. There are programs that do it, but it’s still sketchy. If it was easy we would already have it. Like I said wait a year or two and I bet it will be all over. Right now no one has released any good packages for it that I know of.
what are you guys talking about? Naturally Speaking is up to 99 % accurate, and it’s always at least 95 % accurate for me and I don’t use it much. Voice recognition is here today if you want it. the only reason it’s not mainstream is because I’d rather click than say a link, and I’d rather type than say a word. (less effort)
They key is being able to trigger an event in blender that is transmitted from outside of blender. For example, the text is being inputed to windows notepad, and python is reading it. It can definately be done. Just depends on how interactive you need.
for example, write a very simple app in visual basic that is just a text box and make it save to a file whenever a word is entered. Then in blender, you can have a python script tied to a timer that every 3 seconds reads the text file and if it finds “left” in the text file, then spin the cube left, etc etc etc. The ONLY issue to worry about really is having that little app be in the background but still be the active window that Naturally speaking is putting text into.
If you don’t have access to Naturally speaking, I suppose you might be able to use the winXP built in recognition, but It’s not very good.
give a little more detail on what you’re trying to accomplish
by the way, the text to a file thing is a worst case scenario, hopefully, we can save a variable in memory in our little app that python in blender can access. but I haven’t tried it yet
I’m not saying the software isn’t around, but there aren’t any programming packages that would allow one to code it for open source. Voice recognition as a mainstream widely available feature has not arrived yet. It is still cutting edge. You can windows hack things into your programs, but until there is an easily accessed coding library that is open and not controlled by a corporation, and can thereby guarantee that everyone can access the features in your program, it’s not really a good option. No one is going to pay $160 to play your game, and like I said, the programs that might be available to people are sketchy at best. Now, if someone can prove me wrong, awesome. But realistically I think we are going to have to wait a little while until demand rises for this particular technology.