Wow, it's very good though, but here's a few things:
--> Speech-to-speech dialog (Speech-to-text and text-to-speech plugin?)
That's handled by the Voice API, no need to worry about that.
--> Video support- Perhaps not only facial identification, but also
ability to recognize objects?
That's also handled by the Vision API, based on https://www.github.com/jalcine/OpenTLD. When it's more stable to push
into Winty as a plug-in, I'll try (but everyone's free to try to do
so).
--> Mobile messaging API for on-the-go queries (Will need to change to
Java for Android development)
Well, here, we'd need a means of having Wintermute communicate
swiftly. Perhaps a messaging daemon of sorts for this and pass
communication information via XML-RPC?
--> Speech/voice recognition
Voice API :D
--> Ontology/Reasoning skills (POSSIBLY separate API, still being discussed)
Yeah, we wouldn't want to bloat one API and make it heavy. United we
stand, divided we stand.
Wow, it's very good though, but here's a few things:
--> Speech-to-speech dialog (Speech-to-text and text-to-speech plugin?)
That's handled by the Voice API, no need to worry about that.
--> Video support- Perhaps not only facial identification, but also /www.github. com/jalcine/ OpenTLD. When it's more stable to push
ability to recognize objects?
That's also handled by the Vision API, based on
https:/
into Winty as a plug-in, I'll try (but everyone's free to try to do
so).
--> Mobile messaging API for on-the-go queries (Will need to change to
Java for Android development)
Well, here, we'd need a means of having Wintermute communicate
swiftly. Perhaps a messaging daemon of sorts for this and pass
communication information via XML-RPC?
--> Speech/voice recognition
Voice API :D
--> Ontology/Reasoning skills (POSSIBLY separate API, still being discussed)
Yeah, we wouldn't want to bloat one API and make it heavy. United we
stand, divided we stand.
-- jackyalcine. co.cc/> | Launchpad<https:/ /launchpad. net/~jackyalcin e>
Jacky Alcine
Blog <http://