A brief background on myself; I’m a modeler/animator/web designer with limited programming knowledge. 

I’m interested in creating a “virtual buddy” and allowing a user to teach it, via a 3D engine that will be run through a secure browser on a site that I’m hosting.  Are their any turn-key software packages available to purchase, where I can host everything myself?  I rather not integrate a chatbot from a 3rd-party site, like pandorabots.

Thanks!

Probably the premier turnkey chatbot today is Guile3D Denise http://www.guile3d.com ; however, I don´t know if its a learning bot per se, and am skeptical it could be integrated in the way you suggest, without significant expense.

Zabaware Ultra Hal Assistant http://www.ultrahal.com is a learning bot, but not clear to me that it could be integrated in the way you suggest.

Icogno/Existor Cleverbot http://www.cleverbot.com is another learning bot, but here again any integration such as you´re suggesting would be highend.

Perhaps someone else here can come up with a better suggestion?

- Marcus Endicott
  http://twitter.com/mendicott

Since you are hosting your own site, take a look at Program O (program-o.com)

Here… Let’s ask Program O your question… (Click for a response from the bot):

Are their any turn-key software packages available to purchase, where I can host everything myself

3D animation likes a simple XML response.

Program O is free, and it does learn right out of the box.

Here is a 2D animated interface: http://www.b-zg.com/Program-O/

Just joking about the 2D animation!  Those are just images scrolling in a marquee

If you want to spend money, then maybe you should check out SitePal.

There are more options then just these I’ve mentioned.

Marcus posts a lot of good information about all the different options available.

Is your host a LAMP stack?  Do you want something that is a extension of 3D engine on the host or is the engine in a browser?  What does stand-alone mean in respect to a web site, I mean, are you asking for authentication features like signing in to blog on a forum? Limited programming includes Java, Perl, Python, C++, HTML, or what?

I just don’t know how to answer an opportunity like yours.

The thing about chatbots is that there are three levels:

1) Intelligence

2) Avatar/Embodiment

3) Speech, Out & In

Most often when people talk about chatbots they are referring simply to intelligence, text-in & text-out.

Most commonly on the Web, even avatar-based (or embodied) chatbots (which may be talking heads or full body, either 2D or 3D) are still text-based.

Speech-out is fairly straight forward at this point, text-to-speech; however, speech-in or speech-to-text while do-able is still problematic at this point, though changing quickly.

To my knowledge Guile3D Denise is the first (decent) fully integrated chatbot product available for consumers.  At $820 for their Denise Business product the version comparison below claims it does offer integration with 3rd party applications.

http://guile3d.com/en/compare-the-versions-and-find-the-best-for-you/

Chatbot developers need to be thinking about modularity.  I don´t think its too early for chatbot developers to even be thinking about potentially porting their intelligences to hardbots (physical robots).

There is not a lot of competition for (decent) modular avatars such as SitePal at this point, and none for turnkey voice-in yet.  I really want an avatar that can accept any major intelligence plug-in on the backend.

I don´t see why there is no mobile app available yet where I can simply talk with *ANY* AIML chatbot for instance?

Modularity in intelligence means pluggable to any major avatar system (XMPP compatibilty).

Modularity in avatars means fully dress-up enabled, in other words optimized for customization.

Modularity in speech means applicable to major avatar systems, as well as optimized for customization (voices, accents etc).

I’ve been doing some experimentation with Windows 7’s native Speech Recognition and various programs, including ChatScript, and so far, I’m not having a lot of success with smooth, seamless integration. The main problem is that the Speech Recognition engine is too “purpose-driven”, in that it sees that a “command window” is the focus (ChatScript is a “console-based app, at the moment), and interprets every input as a command, so I get a lot of “what was that?” responses from the SR module. If I say, “Type Capital H-e-l-l-o”, spelling out every word in the intended input, it works about 80% of the time, but that’s no way to “talk” to a chatbot. When I get a few moments to do so, I’ll write a simple GUI with a place for the user’s name, their input to a “bot”, a button to “send” the input, and an output pane. then I’ll try some experiments with that, and see what happens. If that works, then I’ll see about working with Bruce to integrate a more functional GUI into CS, for Vista(?) and 7 users. Us lowly XP users would have to wait until I can learn how to integrate the .NET Speech namespace with the GUI.

Thanks everyone!

I’m going to be using the Unity game engine as my render platform, and I would like users be able to access their “virtual buddy” online through their browser after they login.  So all their data would be stored on a server. I’m also interested in possibly having it work as a stand-alone app, like a virtual assistant for your person computer. Not sure if I can have the online version access your data on your system to read emails, launch apps, etc. Once logged in you’ll be able to change the look of your chatbot; clothing, hair styles, skin color, etc. and be able to decide on the “template” personality such as aggressive, shy, sultry, etc.  After you select and configure your bot, you’ll then be able to interact with it and teach it whatever you fancy.  I’d also like to configure FaceFX for real-time lipsync with text-to-speech, as well as speech recognition in case a user would like to use a mic instead of a text box for input. 

I’m comfortable with the 3D elements of the project, but integrating a turn-key chat bot will provide a bit of a challenge. Cognitive Code sounds promising for a chat bot, and they seem to also be working on a Unity integrated version, but I believe that they need more development time and as of now they’re asking for 5k to use their software.  So I’m looking for other solutions that may be just as effective.

Since I’m just starting this endeavor, my budget is limited until I feel comfortable that I’m well on my way.  I’m going to see how far I can get on my own, but I may have to hire a programmer or partner up with someone to help with integration.

“I’m interested in creating a “virtual buddy” and allowing a user to teach it, via a 3D engine that will be run through a secure browser on a site that I’m hosting.  Are their any turn-key software packages available to purchase, where I can host everything myself?”

The quick answer is probably “No.”

Chatbot hosting
The longer answer is that depending on your skills, you could host a chatbot interpreter and hook it up to a 3D engine, but currently this is far from turn-key. You used to be able to get close to this with MS Agent (although the avatars were really 2d animations) or Haptek, but support for these has declined. The “learning” method/capabilities of the bot is very dependent on the platform. The amount of effort involved is why many have decided to use a hosted solution.

3D
If you just want to buy/use a pre-built avatar there are a number of solutions (Sitepal, Ava guide, Cantoche, CodeBaby, etc). Some are focused just on pre-built responses.

If you want to develop models on your own in Daz3d, SoftImage, 3ds, or another 3d package, there is no real standard for deploying 3D content across the web. (HTML 5 and accelerated browsers may help change that.) That leaves you with either rendering to 2d animations (gif, APNG, flash, JavaScript, etc.) or using a custom engine (Torque 3D, Unity3D, etc.). No one has hooked up a custom engine to a chatbot interpreter yet.

Voice IN
There are a variety of voice recognition engines; discrete commands are easiest to handle. “Dictation mode” is much harder and often prone to higher recognition error rates. Additionally, depending on if the engine is running on the local computer or across the web, the lag time between when a user speaks until the recognized text is submitted to the interpreter can be a problem.

Voice OUT
There are also a variety of TTS (text to speech) products. Quality of voices differs greatly, and if you want lip syncing with your avatar you are adding another layer of difficulty. These also can suffer from lag time issues if the service is being delivered across the web versus from the local computer.

> http://silvia4u.com

http://twitter.com/CogCode has been very hushhush (cryptic) about their development.  I´ve been unable to get anything coherent out of them.  That 5k figure is news to me.  I would definity be interested in more details, and better still seeing some demos.

- Marcus Endicott
  http://twitter.com/mendicott

Silvia might be the way to go since it might be tightly integrated within Unity when it’s available.  As far as the 5k, that’s when I emailed them directly to find out the cost if I decided to license it.

8pla.net in response, on → another thread, quoted Marcus as saying,

“Speech-out is fairly straight forward at this point, text-to-speech; however, speech-in or speech-to-text while do-able is still problematic at this point, though changing quickly.”

@ Marcus - I realize your posting was a little while back but this one was as well. It should however, help to bring you up to speed with what’s happening at Cognitive Code / Silvia.
http://aidreams.co.uk/forum/index.php?topic=3787.0

Hello, If think that there is low probability to find this for few bucks because the complexity of any NLP platform, they are mostly served as SASSO, and this is also my platform casey which caña beta edited remotely in a IDE RAD, similar to VS,
checkpoint my homepage, If.ll puto an English brochure ASAP.

Hi Andres, I’m interested in learning more about your platform, preferably in English..  (Mais, eu falo Portugues..) 

I’m looking at three cloud-based NLP platforms at the moment:

1) GATEcloud.net

2) Wmatrix3 cloud

3) GramLab.org

If think they are NLP research oriented, and there are only a few Dialog-Oriented