The first all-in-one solution that allows developers to simply and securely build an offline voice assistant
Get started with the Voice Development Kit, a solution by developers for developers.
Choosing the Voice Development Kit
We provide a solution that will solve everyone of your problems
Our technologies are 100% reliable
It works anywhere, anytime. VDK’s technologies will run offline with 100% of their capacities in remote locations and areas with poor to no connectivity.
We strive to ensure security and privacy
VDK’s technologies run locally and on-device, with no end-user voice data transferred or analyzed in the cloud. Our privacy safeguards at the product, algorithm, and business-model level enable compliance with the strictest data regulations.
Our technical stack is scalable
All-in-one doesn’t only mean that the range is exhaustive. It also means that every technology is compatible and complementary with each other. You can pile up technologies one at a time, following your needs.
We design everything for simplicity
Who said enabling voice in a product or service was hard? It doesn’t have to be. We put our know-how in the VDK so that anyone can build complex voice features without hurdles.
We are compatible with most frameworks
Our algorithms are small enough to provide advanced capabilities while requiring the minimum footprint available. You don’t have to sacrifice features for space, requirements, or device’s compatibility.
Specifications & Requirements
What you need to check before developing with the VDK
| Language count | 41 |
| Model + Resource Size | 6 to 15MB |
| SDK Code Size | 10 to 65MB |
| Platform supported |
Windows – x86_64 Linux – x86_64 | armv7hf | armv8 Android 6.0 (API 23) |
| Hardware supported | MPU |
| Language count | 41 |
| Model + Resource Size | 6 to 15MB |
| SDK Code Size | 10 to 65MB |
| Platform supported |
Windows – x86_64 Linux – x86_64 | armv7hf | armv8 Android 6.0 (API 23) |
| Hardware supported | MPU |
| Language count | 5 |
| Model + Resource Size | 30 to 50MB |
| Platform supported |
Windows – x86_64 Linux – x86_64 | armv7hf | armv8 Android 6.0 (API 23) |
| Hardware supported | MPU |
| Language count | 65 |
| Model + Resource Size | <1MB up to 500MB per voice depending on the quality |
| SDK Code Size | 5 to 65MB |
| Platform supported |
Windows – x86_64 Linux – x86_64 | armv7hf | armv8 Android 6.0 (API 23) |
| Hardware supported | MPU |
| Language count | Agnostic |
| Model + Resource Size | <1MB to 20MB |
| SDK Code Size |
<1MB = 50KB / User registered 20MB = 5KB / User registered |
| Platform supported |
Windows – x86_64 Linux – x86_64 | armv7hf | armv8 Android 6.0 (API 23) |
| Hardware supported | MPU |
| Language count | Agnostic |
| Model + Resource Size | None |
| SDK Code Size | 3MB |
| Platform supported |
Windows – x86_64 Linux – x86_64 | armv7hf | armv8 |
| Hardware supported | MPU |
Voice Development Kit Interface
A quick interface walkthrough
Start by defining your project's scope
Download resources and start developing
Prototype, test, repeat... until 100% satisfied
Export and embed to voice-enable your device
For developers, by developers
Try our voice solutions now
1
Sign up first on the Console
Before integrating with VDK, test our online playground: Vivoka Console.
2
Develop and test your use cases
Design, create and try all of your features.
3
Submit your project
Share your project and talk about it with our expert for real integration.
Use Cases & Projects
What other developers created with the Voice Development Kit
Adopting voice solutions in your business starts here
Get in touch with our team to shift your company in the Voice First world! Or try it now!
Technologies
Discover all the voice technologies in our stack
Wake Word
A unique word or sentence that allows users to trigger the speech recognition process.
Automatic Speech Recognition
A speech recognition solution to transform human voice into text even with complex vocabulary.
Natural Language Understanding
A flexible solution to comply with any voice commands, whatever the way your users wants to speak.
Voice Biometrics
A solution to identify and/or authenticate users with a voice print that is made by extracting the pattern of the voice.
Text-to-Speech
A synthetic voice generator to produce life-like voices able to humanize products and give audio feedbacks.
Audio Enhancement
An audio enhancing solution to make sure that the sound signal from voice is crystal clear to boost recognition's accuracy.
It's always the right time to learn more about voice technologies and their applications
Large Language Models and ChatGPT
Since its launch in November 2022, ChatGPT has become a hot topic and has taken up more and more space in the media sphere. More domains are integrating Large Language Models (LLM) as part of their...
NLU model best practices to improve accuracy
The future of Warehousing: Voice Directed Warehouse Operations
5 business applications to leverage embedded NLU in your products & services
Natural Language Processing – An Overview on what makes an AI “conversational”
