






All voice technologies inside one software development kit
The Voice Development Kit (VDK) is a multifunctional software development kit combined with an intuitive graphical user interface specialized for voice use cases. It allows any company and any developer to configure an offline voice solution composed of one or more voice-based technologies (transcription, synthesis, biometrics…) in record time.
For many years, Vivoka developed custom voice solutions for its customers. Each project was a real challenge since they required multiple technologies from many companies. Aggregating multiple solutions, partners and proprietary, is the aim of the Voice Development Kit.
The Voice Development Kit is the combination of a powerful SDK and an intuitive graphical user interface, the Studio. Resources from the engine can be used through smart widgets and tutorials to create any kind of embedded voice solution.
Companies and developers will fill their expectations using the Voice Development Kit. It allows its user to build from scratch (code-only) going in depth or to be guided with the Studio’s tutorials and user-friendly tools.
TECHNOLOGIES
LANGUAGES
NATURAL VOICES
WIDGETS
An easy workflow to produce any kind of
embedded voice solution
Rapidly iterate and update your voice assistant using the Voice Development Kit, the unique to 360° tool to produce voice solution for business and developers.
CREATE
Use the Voice Development Kit to create your own voice assistant based on edge voice technologies.
2
DEPLOY
Test your code in the Voice Development Kit Studio and integrate your voice solution into hundreds of devices.
CONVERSE
Enjoy reliable, intuitive and embedded voice commands, synthesis or biometrics inside your products.
Technologies inside the Voice Development Kit
The Voice Development Kit contains a complete range of voice technologies, from voice commands to biometrics through synthesis or speech signal modification. Pick one or more technologies to begin with.
Wake-up Word
Easy tool to generate multilingual wake word to embed in devices for system activation
Speech-to-Text
Continuous and multilingual voice transcription to automaticaly turn voice into text
Automatic Speech Recognition
Grammar-based voice commands for voice interactions that contains specific vocabulary
Text-to-Speech
Automatic generation of multilingual and customizable voices that runs offline on device
Voice Biometry
Authenticate and/or identify users with light and reliable on-device voice biometrics models
Audio Front End
Technology to evaluate the speech signal quality and apply specific sound filters to improve it
