Sensory Launches VoiceHub 2.0, Integrating Generative AI for the Development and Prototyping of Voice UIs

By Tiera Oliver

Associate Editor

Embedded Computing Design

July 20, 2023


Sensory Launches VoiceHub 2.0, Integrating Generative AI for the Development and Prototyping of Voice UIs

Santa Clara, Calif., - Sensory launched VoiceHub 2.0, a new version of the company’s web portal, now integrating generative AI-powered tools to enable the creation of custom voice UIs capable of understanding spoken commands and natural language.

VoiceHub is designed to help engineers develop high-performance wake words, voice control command sets, and grammar-based language models with flexible intents and entities. To further support the aforementioned features, VoiceHub 2.0 features new updates to the user interface, more platform integrations and language and regional dialects, and access to the latest versions of TrulyHandsfree and TrulyNatural.

"Speech recognition is important in many applications, but not all needs are the same. Our scalable VoiceHub voice UI development tools were created to provide developers a one-stop-shop for applications ranging from ultra-small footprint embedded wake words and command models to full-featured NLU voice UIs,” said Todd Mozer, CEO of Sensory.  

VoiceHub 2.0 integrates ChatGPT’s capabilities to enable a new “Task Explorer” feature that simplifies the creation of large vocabulary or natural language (TrulyNatural-based) voice UIs. By entering the domain type of the project, Task Explorer’s generative AI provides intents or commands, and relevant slots or categories for the project type via an interactive mapping tool or within the language model builder. Users can select all options that would be relevant to their product’s/project’s capabilities and features. Based on domain or product category, VoiceHub’s new Task Explorer feature can also generate a list of suggested phrases for the language model, which users can pick from to speed-up voice user interface development.

VoiceHub 2.0 also provides updates to the portal UI layout and is equipped with new features that enable the sharing and importing of projects in a drag and drop format. The VoiceHub mobile app for iOS and Android has also been updated to maintain compatibility.

TrulyHandsfree Micro 7.1.0 has been updated with speed improvements, and now supports more hardware platforms (see Sensory’s partner page), including ARM Cortex-M4, Silicon Labs Cortex-M33/M, Ambiq Apollo 4, Cadence Hifi5, Qualcomm, and Xmos TrulyHandsfree also supports Android, iOS, Linux, and Windows operating systems, and support for other operating systems can be added upon request. 

TrulyNatural 6.21.0 features a background model for US English that is designed to improve out-of-vocabulary rejection, which enables grammars created in VoiceHub to perform high accuracy in real world applications. According to Sensory, TrulyNatural SDK 6.21.0 now requires less RAM for recognizers on small, embedded platforms and adds Voice Activity Detectors for the SNSR-lite Large Vocabulary Continuous Speech Recognizer.

Also, VoiceHub generated grammars using this new version of TNL may be used on a wider range of devices and can run smaller on the STM32 chip. VoiceHub’s TrulyNatural tools will also include statistical language models designed to enhance flexibility and natural language accuracy.

VoiceHub 2.0 is available now with support for 25 languages and regional dialects.

For more information, visit

Tiera Oliver, Associate Editor for Embedded Computing Design, is responsible for web content edits, product news, and constructing stories. She also assists with newsletter updates as well as contributing and editing content for ECD podcasts and the ECD YouTube channel. Before working at ECD, Tiera graduated from Northern Arizona University where she received her B.S. in journalism and political science and worked as a news reporter for the university’s student led newspaper, The Lumberjack.

More from Tiera