The Voice Layer – Jan König, Jovo – Voice Tech Podcast ep.068

Jan Konig Jovo

Episode description

Today on the show, we welcome Jan König, co-founder of Jovo. Jovo is an open source layer that lets you build and run voice experiences across multiple devices and platforms including, Amazon Alexa, Google Assistant, Samsung Bixby, mobile phone and web apps, and many more!

In this episode, we get an inside look into Jovo’s architecture and business model, as well as the latest and greatest version of the build-once deploy-everywhere solution for voice. Jovo version 3 has just been released, and it expands the number of channels you can build for, which now includes Twilio, Facebook Messenger, and even Samsung Bixby. The product has significantly matured and is used by many top brands to build world-class apps today.

Not only do we dig into all the new Jovo v3 features, but we speak about the challenges involved with building an open source startup. On the dev side, we take a look at standards, software patterns, and the design considerations between voice bots versus chat bots. On the industry side, we explore best practices, where the voice market is going beyond the big platforms, and much, much more.

Jan is a highly concentrated source of information, and the insights per minute in this episode is off the charts! So, if you’re looking to have your mind-blown, in multiple directions, then take a listen!

Highlights

  • Discover why Jovo was built and the types of problems companies are using it to solve.
  • Request, Interpretation, Dialogue, and Response: Learn more about Jovo’s RIDR concept.
  • The difficulty with tracking down data and users with an open source program like Jovo.
  • Why many developer beginners are using Hello World and Jovo to build their voice apps.
  • Learn more about Jovo’s local developer environment, debugger, and language model.
  • Best practices in the voice industry today and establishing Germany’s Din standard.
  • Jan’s thoughts on component architecture and the future of voice design patterns.
  • Discover the key differences between Jovo Version 2 and Jovo Version 3.
  • Find out how Jovo differs from other open source platforms such as Rasa.
  • How to convince businesses and contributors to invest in an open source startup.
  • Ensuring startup survival under Jovo Studios and the professional services sector.
  • Learn more about the Jovo Enterprise Suite and how it differs from Jovo v3.
  • The importance of building tools to bridge the gap between design and development.
  • How Jovo was initially accelerated with the help of Beta Works’ Voice Camp program.
  • Parity with existing open source platforms and the challenge of building across platforms.
  • Building a horizontal tool versus a vertical tool and Jovo’s lack of specificity.
  • Working with Samsung Bixsby and the process of integrating this platform into Jovo.
  • 2020 and beyond: The Jovo vision and predictions for the future of voice platforms.
  • Top tips for handling the code base for voice bots versus chat bots.
  • How far are we in creating one experience that can be shared across devices?
  • Testing the “happy path” and other advice for beginners in voice development.

Quotes from the show

[05:17] For us, voice is not just an afterthought.

[15:50] We’re already seeing companies adopt our component features.

[16:15] There’s not a lot of best practices out there in the voice space.

[24:00] Voice is a niche right now, which makes it difficult for an open source voice startup.

[27:55] The really good experiences are built by cross-functional teams.

Links from the show

About the author

Carl Robinson
Carl Robinson

Carl is the host of the Voice Tech Podcast. Since launching in April 2018, Carl has conducted scores of in-depth interviews with voice industry experts, building one of the most well known media brands in the voice AI space.

He also publishes Voice Chops Tuesday, the number 1 voice technology newsletter, enjoyed by thousands of voice tech fans each week.

Carl is a startup founder, product manager and data scientist, and recently presented a model for voice emotion conversion at ICASSP 2019.

To contact Carl, use the links in this box to send an email, tweet or message.

Share this article

If you found value in this article, please consider helping others by sharing to your network. Just click one of the links below.

What do you think?

0 replies

Leave a Reply

Want to join the discussion?
Feel free to contribute!

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Related Posts

Yaki Dunietz Conversational Components
Rumble Studio Audio Content Marketing
Yannick Oswald Mangrove Capital

Get notified about new articles

Upcoming Events


Featured Products