Automatic Speech Recognition (ASR) that works offline
Our professional Software Development Kit (SDK) to simply voice-enable products and services with bespoke understanding of any complex vocabulary.
Getting familiar with the technology
What is Automatic Speech Recognition?
Automatic Speech Recognition, often referred to as Speech-to-Text or simply Speech Recognition, is the main technology that makes voice a way to interact.
At the pinnacle of voice AI, it merges together complex solutions such as acoustic models, natural language understanding (NLU) or audio signal processing.
This technical stack allows ASR to turn human speech into normalized data (text, intent, values…) that can be processed by complex systems.
Use cases and existing applications
How to leverage ASR in the field?
Wearables
- Voice-enabled AR glasses
- VR voice typing
- Voice control in headphones
Industry 4.0
- Voice picking
- Field report dictation
- Voice-enabled quality control
Appliances
- Smart fridge, oven etc…
- Hands-free Industrial appliance
- Custom/branded voice assistant
Field services
- Maintenance assistant
- Voice reporting
- Voice assisted workforce
Robotics
- Voice-enabled robotics
- Hands-free medical tools
- Human-Machine Interface
Defense
- Hands-free military equipment
- Voice-based training solutions
- Specific MRO workflows
Features
How to use offline Automatic Speech Recognition
Grammar-based Recognition
Voice Dictation (FreeSpeech)
Benefits
Why should you choose our
Automatic Speech Recognition?
Internet Independent
No wifi or network are required to perform advanced speech recognition.
Superior Accuracy
Across different environments, user population or vocabulary complexity.
Data Privacy
User data stay in the device, unexposed to security issues and transfers.
Real-time Processing
Speech processing directly on the device reduces latency to 0.
Clear Pricing
Business models that adapt to yours, without any hidden-fees.
Easy-to-Integrate
Simple to develop and embed across all platforms (windows, linux, android…).
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!
Companies that have chosen our solution
Our customers' feedbacks regarding our solutions
“Vivoka’s technologies have been integrated into our solutions dedicated to Human Factors in industry, guaranteeing performance and data confidentiality.”
Guillaume Jégou
Head of the Human Factors Technology Laboratory
"Vivoka’s solutions can run offline, on-device, to operate anywhere, anytime and with a broad language support capability which is for our products a distinct competitive advantage."
Paul Travers
Chief Executive Officer (CEO)
"We partnered with Vivoka on several innovative projects on embedded Linux system, and delivered, in a very short time, multi-lingual natural voice interactions fully running “at the edge” to our customers."
Cédric Vincent
VP of Technology
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.
Requirements & Quick-Start
How to develop with our ASR engine?
– On the Device
Fully-embedded voice technology for brands seeking the convenience of a voice user interface without the privacy or connectivity concerns of the internet. Full access to custom commands and the ability to instantly update command codes during development make voice-enabling your product fast and easy.
– On Premise
Get the power of cloud connectivity combined with the reliability of embedded voice technology. On premise (or hybrid) solutions ensure that your device is always-on and responsive to commands. Seamlessly push product updates and deliver a broader voice experience with the level of cloud-connectivity that best matches your product and users.
The ASR we provide are grammar-based recognition engines. It means the recognition’s capabilities are based on a file that includes the different elements to be recognized (numbers, sentences, words, names…).
Our offline Automatic Speech Recognition supports both phonetic edition (changing the way words are understood by the engine) and dynamic data (having flexibility with the grammar content).
The engine currently supports 41 languages.
– Model & Resource Size: 6 to 15MB
– SDK Code Size: 10 to 65MB
– Supported Hardware: Microprocessor Units
– Supported Platforms:
- Windows – x86_64
- Linux – x86_64 | armv7hf | armv8
- Android 6.0 (API 23)
Complementary Technologies
Discover other technologies in our stack
Wake Word
Trigger speech recognition process by detecting a unique word or sentence.
Voice Biometrics
Seamlessly identify or authenticate users by recognizing their voice pattern.
Text-to-Speech
Automatically generate life-like voices from text data in multiple languages and aspects.
Audio Enhancement
Enhance the audio signal quality from voice to boost speech 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”
