Hi, looking for help combing A

Question

Hi, looking for help combing AIML with Speech Synthesis? Basically I want to be able to use a mic and have a conversation with my robot and have him respond using my computers speakers. Not sure where to start with this. Any help would be much appreciated

DJ Sures · Answer

Oh that’s an easy one and I can help. I made a little write up in a robot I did. The sound can come out of an ezb or iotiny, it doesn’t have to be your computer speakers. Either way it’s only the difference of a checkbox take a look at this link: https://synthiam.com/Robot/Machine-Learning-And-Cognitive-Services-Jd-Humanoid-Robot-187  here’s the video

Xuven · Answer

Thanks for the help DJ! Got it up and running np. I do have one more question though. Is there any kind of plugin that does speech to text offline? The Bing plugin works fine but my robot won't always be near internet

DJ Sures · Answer

The answer is "sort of"... there is the Total Speech Recognition control, but it requires a lot of speech training and I HIGHLY recommend a microphone that you can hold to your mouth or wear in your lapel, etc.  The reason all the great speech recognition systems are online is because they are AI driven and get better with usage. So they put them on the "cloud", which is just a server online, and not an Ethernet cable connected to an aerosol of a visible mass of minute liquid droplets, frozen crystals, or other particles suspended in the atmosphere of a planetary body. Get the total speech recognition here: https://synthiam.com/Software/Manual/Total-Speech-Recognition-17688

Xuven · Answer

Is there a guide somewhere to get Total speech to connect AIML? I'm missing something but not sure what. I'm sure its a simple command I'm missing somewhere

Xuven · Answer

Found the command I was looking for. Thanks again for all the help DJ!

DJ Sures · Answer

I knew you could do it Great work!!!

EzAng · Answer

Xuven , what was the command?

DJ Sures · Answer

EZang60, the ControlCommand() for all controls is located in the cheatsheet. Also, the variable needed is in the config screen of the Total Speech Recognition Control.