I'm implementing a customer service bot and I'd love to be able to set it up so that if the bot's confidence is above a certain threshold, say 90%, it auto-responds, if not it notifies the operator via Email or SMS that there is a question it needs help with.

What I'm envisioning is a being able to step in and answer correctly as my bot learns.

Eventually, I'd like to have one operator monitoring multiple instances of the same bot, so one human could handle dozens of incoming channels at once.

I'd prefer the user not know when they are talking to a bot or a human, I just want them to feel like they are getting expert advice, regardless of who is answering.

How big of ask is this and do you have any plans for this in the future?

 

Currently if you have your own speech audio files you can use our SDK to have an avatar simulate speaking them. You can copy the SDK source code that uses our TTS audio and insert your own speech audio.

-> Could you please let me know in which file / class we can insert our own audio files?

You can copy the SDK source code that uses our TTS audio and insert your own speech audio.

-> So far, in Java SDK source code I did not find any such place to insert own audio. What I have found in the sample application that it plays the audio file returned from server in default player and the video of the avatar in media player in Android. According to the sample the video is looping until the audio is finished.

Could you please clarify this!

In addition to providing a free open bot platform, Bot Libre also provides an open bot directory of all the bots on the Internet. Chat bots, Twitter bots, Facebook bots, Telegram bots, Slack bots, IRC bots, email bots, bot apps, and every other type of bot on the Internet.

The Open Bot Directory

Meet Sandy 3, our newest HD 3D animated avatar. She is a photo realistic 3D generated animated video female avatar.

We support the AIML2 XML web API through REQUEST (Self) and SRAIX (AIML) to let your bot access information from other bots, and other datasources.
We are also working on a more generic API to access web data and scrape HTML.
As well we can custom develop you a specific solution as part of our commercial bot service Paphus Live Chat.

Hi Admin,

Thanks for making this! Is it possible to add another searchable source with domain knowledge that I want my bot to have?

Unfortunately mobile web browsers are not perfect yet, but at least they are improving.
Hopefully Chrome will fix the flash when changing videos.

Hi,  Everything is working! However I've noticed that something isn't quite right.  In chrome when the SDK switches mp4 files the video tag placeholder flashes black.  This can be seen even on the examples on the website.

Sorry, from Google translate I get "Htny nearest vshark bsssrh :-)"?

The speech issue was that your were using the native speech, but Chrome does not support HTML5 speech on mobile. The server voices work.

You can use your own JavaScript to render your avatar however you wish. You can copy the code from createBox() and modify it to suite your needs, our SDK is open source.

حطني مقرب وشارك بسسسرعة:-)

web.createBox(); seems to render differently depending on platform is there any way of embedding it on the page?

Nothing is rendered unfortunately and I don't get any sound

What issue are you seeing exactly?
Does the chat work?
Do you get a still image instead of an animated video and speech?

Autolike friend post

I've tried it on both my Nexus 7 and Samsung S4 Mobile

Which avatar/bot are you using, and what table brand/model?

I've set the flag to enabled but the content still doesn't load unfortunately.  It works perfectly in Firefox tho!

That should do it, chrome://flags, scroll down to "Disable gesture requirement for media playback", click "Enable".

What issue are you having?

Hi,

Could you explain to me exactly needs changing in mobile chrome? :) I think I have that setting already changed.

best wishes,

matt

Emotions, actions, and poses can used to interface with your bot's avatar.

Avatars are a collection of media files (images, video, audio) that have been tagged with emotions, actions, and poses. You can choose your bot's avatar from its Avatar page in its Admin Console. You can choose any existing avatar from our avatar library, or create your own.

How to pick text string from question and add in answer.

We added two new Julie avatars, Julie3 Sport, and Julie3 Beach Both are universal avatars that support HD webm and mp4 video, and images.

We have released Bot Libre 4 on Android.

Bot Libre for android lets you create your own bot from your Android phone or device, or chat with thousands of bots in our open bot directory.

Our bots work on mobile and tablets.

Depending what browser you are using some features may not work.

My bot works fine on all pc platforms but won't work on phones or tablets! Is there a way around this other than developing an app?

Using a script would be the easiest way to do this.

You can either use Self, or AIML.

Based on an initial user question, I need to have my bot ask a series of questions, and get answers, rather than the other way round ...

I'm struggling to see how to train it to ask questions rather than answer them.

For example, if the user starts with "I need to report problem type X", for each problem type my bot needs to then ask:

What's the address?

What's the size?

No, I don't think so.

Our Facebook automation support lets you automate posts and replies to a Facebook page, or profile.

hi there,

can i promote my video uploaded on FB using bot, for example adding tags that can help my video to be hooked up with related post?

We released Bot Libre 4.2 today.

This updated included several enhancements including:

The avatars normally use our Text To Speech support for speech (or native TTS in HTML5, Android, and iOS).

You can also associate audio files for actions and poses.

Bots and avatars are separate entities.

An Avatar is the visual/media representation of a bot or agent. An avatar can have images, video, and audio content associated with emotions, actions, and poses. An avatar integrates with our Text To Speech API, and the HTML5 Speech API to simulate talking.

There are avatars and BOT. So far BOT is for chatting and Avatar is kind of animation. With the avatar it should be possible to play audio sound with lip sync.

What kind of API support is there to achieve this in IOS and Java?

Is there anybody who can clarify me what is the difference between a BOT and an Avatar?

If Avatar is a separate entity than BOT then how to retrieve the list of avatar?

We do not have direct support for Telegram yet, but you can use our open API and open source SDK and AI engine to integrate your bot with Telegram.

The SDK is here,

Hi Admin,

Thanks a lot for helping me out. I started over with an empty template and now I am fine. I am understanding my mistakes now.

Cheers,

Marc

Are there any instructions how to integrate bots from BOTlibre with Telegram?

Bots can have both scripts and responses, which are both separate.
Responses are used if their question exactly matches the users input, or if no script returns a result, then the best matching response will be used, otherwise the bot's default response.
You can edit your bot's responses from the "Training & Chat Logs" page in its Admin Console.

Hi, first of all I am very impressed with this website.

Next, I have a question. I just created a bot from some AIML files. When I started chatting to it, it replied with answers that are not in my AIML templates! Is there some precompiled AIML script? If so, can I switch this off?

Thanks,

Marc

Bot Libre has finished migrating to a new smoking hot server.

Everything seems to be functioning normally, if you noticed something not working, please let us know.

This is the bot's default response. You can edit your bot's default responses from its "Training & Chat Logs" page. You can also add new responses, and greetings from there.

See,

What script is the default response "I don't understand, how should I respond?" located? I want to change what the bot asks in this situation because she's not going to be an English speaking bot. I've CTRL+F'd it in every script and I can't seem to find it.

Yes

That is odd, the pattern "(b c) [d e] ^" seems to work, it seems to be an issue with the first "^".

I think I have a fix for the issue, it will be in our next website update, maybe a week or two.

Could you please explain, why phrase "a d f" isn't handled by pattern "^ (b c) [d e] ^" ?

The define() function seem to be missing.
I will add it, but for now you can just set the word's meaning, and the meanings word. That is all define() does.

After saying "initTokens " to my bot id=11736722 I get an error "Missing function" with this code:

Language.define("плохо", #bad);

 

What is wrong? How can I asiign a meaning for the word?

Thank you in advance!

Glad that you got it working.

What error did you get when trying to import the file?

Sorry for a stupid question. It works so: 

conversation.speakerFirstName = star[0];
conversation.speakerLastName = star[1];

Script works if I paste it in a created script (without import). It's ok.

How can I save more than 1 value for the conversation? This code does not work:

conversation[speakerFirstName] = star[0];
conversation[speakerLastName] = star[1];

After it's execution both variables return value of star[1].