I would like to use the Bluemix Conversation sample application
and add speech input and output to it. There are other sample applications for Bluemix TTS and STT available.
What are options to integrate these 3 functions and which of them are recommended for beginners?
There are no immediate plans to provide a 'simple' sample app which demonstrates combining Watson STT (Speech to Text), Conversation, and TTS (Text to Speech). Longer term it is definitely on the radar.
In the immediate term, to get an idea as to how to do this, please take a look at the car-dashboard app code:
https://github.com/watson-developer-cloud/car-dashboard/blob/master/ui/index.html#L85
https://github.com/watson-developer-cloud/car-dashboard/tree/master/ui/ibm
https://github.com/watson-developer-cloud/car-dashboard/tree/master/speech
https://github.com/watson-developer-cloud/car-dashboard/blob/master/ui/ibm/stream_speech_to_text.js#L34
The car dashboard app uses the IBM Watson Speech JS SDK:
https://github.com/watson-developer-cloud/speech-javascript-sdk
Hopefully this helps.
This is an old question, but IBM Watson is still evolving so this may be a more up-to-date answer.
You have 2 options.
You can simply have your app submit an HTTP REST request (either GET or POST) by following this tutorial
Or you can leverage a language-specific SDK.
If you're using nodejs, then check out this example.
For java, see this example.
Edit
Here's an example git project I created to integrate text-to-speech to the conversation-simple sample app: conversation-simple-with-text-to-speech
Here's the specific commit where the integration was added: commit 3564aeb
I did something along these lines with the Dialog service demo app and the Speech JS SDK a few months ago:
http://speech-dialog.mybluemix.net/
Full code is on github but almost all of the changes were in this commit.
Note that it was built on an older beta of the SDK. You can get the latest release from github releases or npm (for use with webpack/browserify/etc.) and there are lots of examples.
Related
First of all, thanks for taking the time to read through our issue.
So, we have a Dialogflow project connected to an already existing google project. When we try to test our skills on google by the Integrations tab, it displays an error 'Precondition check failed' without any more information, even though it still updates and uses our Dialogflow intents as it should.
The problem comes when we update anything on the actions console or try to make an alpha deploy of our skill. The moment we change anything, it comes back to the default configuration with the message 'Start building your action by defining the main invocation.' on the main invocation.
We have no clue how to handle this problem or if we have to configure something special on either of the systems to make it work. Any ideas are welcome.
If you want to integrate the Google Assistant with Dialoflow, I strongly recommend you check the new development Google Assistant's platform with a built-in conversation builder, here. Furthermore, there is a quick start guide and conversational actions guide.
As I mentioned in the first comment, you need to have appropriate permissions to create an interaction within Dialogflow, you can check the pre-defined roles here. In addition, since you are starting with Dialogflow, I would advise you to start with the available quick-starts and the setup tutorial, which explains how to begin using Dialogflow.
I created a quiz application that I can use at Google homes.
Actions created a quiz using templates trivia (one of the templates) in Google on google.
I want to send http request according to the number of correct answers.
Please advice me.
The trivia template doesn't support this feature.
However, Google open sourced the original version of trivia, and you're able to use the source to adapt it to your own needs. It uses the previous version of the library, but should still work.
I am creating a chatbot for my website, I want to add clickable images, links, buttons in chatbot using Web demo in APIAI. How Can I achieve this?
You can't achieve it using Web demo. As name says it is only demo where you may test flow of your dialog - if api really can transform your language into intent ;) So good to share with your friends and ask them for feedback and maybe improve your feed data - not for a rich client in production.
You may build you own client using their javascript sdk for example - https://github.com/dialogflow/dialogflow-javascript-client. If you know html, css and basis of javascript you should be good to go.
There are many platforms that help you to add rich messages to your chatbot with simple steps.
Following are the platforms where you can build your chatbot with rich messages.
Dialogflow
Kompose
Amazon Lex
IBM Whatson
Kompose will help you in building a rich message chatbot without coding knowledge, it is a GUI platform where you will have to just click on buttons, link buttons, images to add the rich messages.
Once you are ready with the chatbot, copy the install script available in the Kommunicate install section and paste it into your website HTML page to add the chatbot to your website.
I am doing an app in which I require a business card reader I googled alot but BBY is the only solution which I was able to find out. Can anybody help me out with some opensource library which can be tweaked or used directly as a business card reader.
Please enlighten me on this.
you can look into the Tesseract open source engine... its pretty good for image processing.. i mean it will extract the text out of the image but then you will have to process it to extract name ,phone numbers and other details.
this guy has explained how to use it in iOS .. http://tinsuke.wordpress.com/2011/11/01/how-to-compile-and-use-tesseract-3-01-on-ios-sdk-5/
We started an open source project to build a Javascript library (based on the OCR engine tesseract.js for the OCR part) that exctract the relevant data from a business card based on heuristic criteria.
The library (BCR Library, available on github) is usable in any html project (included mobile cordova, phone gap or ionic projects) just including it via script tag.
The library doesn't have any external api call and fully works offline.
I think that you should give a try to Covve Bussiness Card Scan API. The quality of the result is great in various languages. You can check a comparison analysis of similar services here.
[Disclosure] I'm part of the team developing the service.
I am doing an app in which I require a business card reader I googled alot but BBY is the only solution which I was able to find out. Can anybody help me out with some opensource library which can be tweaked or used directly as a business card reader.
Please enlighten me on this.
you can look into the Tesseract open source engine... its pretty good for image processing.. i mean it will extract the text out of the image but then you will have to process it to extract name ,phone numbers and other details.
this guy has explained how to use it in iOS .. http://tinsuke.wordpress.com/2011/11/01/how-to-compile-and-use-tesseract-3-01-on-ios-sdk-5/
We started an open source project to build a Javascript library (based on the OCR engine tesseract.js for the OCR part) that exctract the relevant data from a business card based on heuristic criteria.
The library (BCR Library, available on github) is usable in any html project (included mobile cordova, phone gap or ionic projects) just including it via script tag.
The library doesn't have any external api call and fully works offline.
I think that you should give a try to Covve Bussiness Card Scan API. The quality of the result is great in various languages. You can check a comparison analysis of similar services here.
[Disclosure] I'm part of the team developing the service.