Skip to main content

Kookoo speech API

Hello! Can you hear me?

Well, yes. Kookoo can now hear you. Voice has suddenly become popular again and you can now find voice interfaces everywhere(Alexa, Google Home etc). Lucky for us, as we are the voice experts :)

Note: They say a demo is worth a 1000 words(well, I said that :)), so here goes a demo. Just call the number and say something, you will get an SMS with the text of what you said

040-3095 2027

We can already build innovative IVR apps using Kookoo. But what has been lacking for a long time is to allow natural communication using speech in an IVR. The major stumbling block for that was automated speech recognition. But that problem is now a thing of the past. Thanks to Google, Amazon and other players including yours truly, we now have access to good speech engines which give pretty good accuracy.

So today, we announce a new tag in Kookoo:


A new tag has been added to Kookoo after years. And what an addition it is :).
<recognize> opens up a whole new array of possibilities. You can now hear your callers. Put an NLP engine on top of it and you can then understand your callers.
<recognize> does a very important thing, it takes your data from the voice domain to the text domain. And this will allow you to perform all your analysis on textual data including things like, searching your recordings, sentiment analysis, bots etc.

Use Cases:

Some use cases in which you can use <recognize> immediately:
  • Customer feedback.
  • Surveys.
  • Ask users to say yes or no instead of press 1 or 2.
  • Ask callers to say their phone number.
  • Ask callers to say the order number and share the order details with them.
  • Callers can say ticket details and get the status.
The possibilities are limitless.

Currently <recognize> supports two engines. Our own, Zena engine and the Google engine. This is already in production with enterprise customers using it to understand their voice communications. You can go ahead and read the documentation.

If you are as excited as we are and want to try out this feature, please send an email to

Popular posts from this blog

Integrating Arborjs with Angular to create a live calls dashboard

Arborjs  is a cool graph visualization library. Angular  is one of the best JavaScript frameworks and we have been using Angular in a lot of our front end development. When you handle millions of calls, proper visualization becomes very important. Without proper visualization, you can get lost in the mountains of data. So we spend a lot of time to come up with good visualizations to represent the data. Since we loved the cool way in which Arbor represented graph data, we could not wait to hook it up with Angular. Because of Angular's two way data binding, when you hook up Angularjs with Arbor.js you can get a dynamically updated visualization of graph data with cool animations. To give back to the community, we have put up the code online at Github . Basically we have created an Angularjs directive for Arborjs. Please feel free to fork the code and add extensions and use it for your own visualizations. The code is self explanatory with comments inline. Best way to get s

First Post

In this blog, I will be talking about my experiences in trying to build a cloud telephony platform , KooKoo . Along the way I will also be talking about different design choices I made, good programming practices and the IVR domain in general. For technoratti: NNFJW8EW86C3

KooKoo Contact Center integration with WhatsApp

WhatsApp announced the launch of their business API yesterday. This is a big deal. A lot of businesses have been asking for WhatsApp integration and now its a possibility. Twilio has already launched an integration . Won't be long before we see a lot more integrations pop up. The most obvious use case is for support chat bots, alerts and reminders. But we at Ozonetel believe one other use case will become the dominant use case, WhatsApp as a support channel with human agents. We believe WhatsApp will become a dominant channel in contact centers world wide. There are multiple reasons for this: WhatsApp is ubiquitous. Everyone has the app. WhatsApp interface is well known to all customers. It is feature rich. You can share audio, video, location etc in the app itself. You can integrate bots for repetitive tasks. Being the leaders in cloud contact center solutions, we at Ozonetel knew that we had to integrate with the WhatsApp channel as early as possible.