Jovo today announced the public availability of its open-source voice app development framework. Company founders Jan König and Alex Swetlow recognized that the rise of voice assistants like Amazon Alexa and Google Assistant would cause usability problems around enforcing a consistent, continuous and complementary user experience across devices. At the same time, they also recognized that along with the usability problems there was the challenge that developers had to maintain separate code bases for voice apps on the various voice assistant platforms. These ideas led to the founding of Jovo that is targeting two key benefits for voice apps:
- Framework: Developers will be able to write code once and run it every voice assistant platform making the experiences consistent for users and efficient for developers.
- API: User experience can be made continuous and complementary across multiple modes of use such as smart speakers, mobile devices, televisions or other interfaces.
Developers Offer Praise for Jovo
Today’s announcement focuses on that first benefit, the framework. Early developer reaction has been positive.
“I think the Jovo Tech framework has massive potential to increase the efficiency of developers in the voice space. Most developers tend to start out building for Alexa and then look to port their Skills to the Google Assistant. Learning a whole new framework for Google Assistant using either API.AI or the Actions SDK can be very time consuming and in my opinion is one of the reasons we see less Google Actions compared to Alexa Skills. The appeal of Jovo is that you can have one code base that works for both Alexa and Google. Jan and Alex have put a lot of hard work in building an excellent framework with a very clear syntax that builds upon what people liked and didn’t like about the popular Alexa SDK for nodeJS. I think developers will really like it and encourage them to try it out for their next project,” said Oscar Merry, CTO and co-founder, Life Bot.
“Jovo gives us the ability to develop cross-platform for Alexa and Google Home without having to maintain separate code bases, and we can continuously improve our skills because of the easy integration with tracking and analytics platforms like VoiceLabs and Dashbot,” said Matthew Wood, Director of Starmark Innovation Lab.
Step 1 in Implementing Jovo’s Vision
Jan König from Jovo likened today’s launch to a good start in implementing the company’s vision. The framework makes it easier for developers to quickly replicate an experience across device platforms. The next step involves the API, which König says will complete the solution.
Our goal is multimodal experiences that aren’t only replicated, but also continuous and complementary.
The company starts from the fundamental thesis that voice experiences will increasingly become multi-modal and incorporate visual and text elements alongside voice. We see some of this today with Amazon Echo Show, Echo Spot and notably on Google Assistant on mobile where text is complementary to voice interaction. However, these are limited use cases today and they all stay within a single technology platform. Over time the interactions will be multi-modal and multi-platform which requires new tooling that is platform agnostic. Jovo is intent on building that agnostic solution for developers with the framework now and eventually the API.
The framework is available today and König says it will always be free to use. When the API is launched in the future it will have some paid elements. You can find out more about Jovo here:
- Website: https://www.jovo.tech
- Framework Repository: https://github.com/jovotech/jovo-framework-nodejs/
- Beginner Tutorials: Google Actions, Alexa Skills