Nuance Releases Voice Recognition IoT Development Platform

Nuance Communications has launched Nuance Mix, a new developer platform for mobile and consumer electronics. Currently available as a limited release beta via the Nuance Developers program, the development platform gives device makers and developers the ability to create customized voice and natural language Internet of Things (IoT) segments such as smart home, gaming, robotics, and consumer health and fitness. 

 

Nuance Mix provides a new natural language understanding development tool which offers voice recognition and text-to-speech. Developers can use the Mix web interface to create custom voice and natural language models within minutes that are fully optimized to work together to deliver precise accuracy for a set of tasks defined by the developer. 

 

The platform lets developers define their use cases, concepts and parameters, and the variety of ways consumers will interact with their device or app through voice. Then Nuance Mix creates a customized and intelligent speech and natural language model for the project that is then instantly integrated into their app or device. As a result, every voice interaction is defined and created by the developer – providing even more control over the user experience.  

 

Developers also have more freedom of choice in how much or how little support they need based on the level of customization, and will have the option to engage with Nuance directly on design, integration, and speech and natural language development needs.  

Nuance Mix also provides developers with an automated workflow to roll anonymized speech data back into their models to continuously improve accuracy.  The can facilitate the improvement of the user experience continues to improve over time providing behavioral insights into new features that can or should be powered by voice.

 

Mix is an open platform offering cross operating system and cross platform support through open internet protocols like WebSockets. And SDKs for iOS and Android, as well as for sample applications in popular languages including Python, C, Javascript, and more.

 

Currently the Mix voice recognition and text-to-speech toolkits allows developers to create customized voice interaction for consumer devices and mobile apps in more than 40 languages, and choose from more than 80 distinct voices for text-to-speech.