Skip to main content
Skip table of contents

VDK 5.6.0 - 25th March 2024

Summary

We are excited to announce the release of VDK 5.6.0, a feature release that marks a significant advancement in our voice recognition technology suite. With this latest version, we unveil an enhancement to our dictation capabilities, designed to meet the evolving needs of our users more effectively.

What's New in VDK 5.6.0?

  • Enhanced Dictation: Our latest innovation introduces a more sophisticated version of dictation that we are proud to present as Dictation. This new feature brings the power of rich text formatting to your voice recognition tasks, incorporating punctuation and linguistic nuances seamlessly into the transcription process. The dictation is ideal for users requiring high-fidelity text transcriptions, making it a perfect tool for detailed note-taking, content creation, and comprehensive documentation.

  • Continuous Recognition: We have also refined our existing dictation technology, now rebranded as Continuous Recognition, to cater to a different set of user needs. Continuous recognition, formerly known under our dictation umbrella, offers streamlined, unformatted transcription, providing a raw, continuous output of spoken words. This feature is particularly suited for applications requiring a lightweight solution for voice to text conversion, including voice-controlled commands and real-time speech transcription, especially when paired with Natural Language Understanding (NLU) for enhanced voice control intent-based commands.

Why the Distinction?

This delineation between Enhanced Dictation and Continuous Recognition is driven by our commitment to providing tailored solutions that match our users' specific requirements. Whether you're seeking high-quality, formatted text transcriptions or efficient, unformatted speech recognition, VDK 5.6.0 delivers with precision and flexibility.
We understand the importance of clear communication and have made these changes with both new and existing customers in mind. For those who have been utilizing our previous Dictation feature, the transition to Continuous recognition will be seamless, offering the same reliability you've come to expect, now with a title that more accurately reflects its capabilities.

Explore further

Here are the specification details for Dictation and Continuous.

Additional minor updates and improvements have been implemented across various components of the VDK, enhancing overall performance and user experience. We invite you to check these details below.

As always, we are committed to evolving our technology in ways that support and anticipate the needs of our diverse user base. We believe that VDK 5.6.0 represents a significant step forward in this journey and look forward to hearing your feedback.

Versions

Studio

Component

Version

Studio

5.9.0 UPDATED

Dictionary manager

2.1.4 UPDATED

Free-speech

5.3.0 UPDATED

Grammar editor

5.2.4 UPDATED

Phonetic editor

5.1.4 UPDATED

Project editor

2.4.0 UPDATED

Simple assistant maker

5.2.2 UPDATED

TTS manager

5.2.3 UPDATED

Voice biometrics

4.4.5 UPDATED

Nlu Editor

2.1.5 UPDATED

Speech Enhancer

1.1.2 UPDATED

Vsdk-daemon

1.15.0 UPDATED

Samples

Component

Package name

Version

Technologies

Chained grammars

chained-grammars

5.1.2

VOICE RECOGNITION (GRAMMAR)

Dynamic grammar

dynamic-grammar

5.1.2

VOICE RECOGNITION (GRAMMAR)

Simple application

simple-application

5.1.1

VOICE RECOGNITION (GRAMMAR) VOICE SYNTHESIS

Tts

tts

5.1.1

VOICE SYNTHESIS

Voice biometrics

voice-biometrics

5.1.2

VOICE BIOMETRICS

Voice Commands Language Understanding

voice-commands-language-understanding

2.1.1

VOICE RECOGNITION (CONTINUOUS)

Speech Enhancement

speech-enhancement

1.0.1

VOICE RECOGNITION (GRAMAR) SPEECH ENHANCEMENT

VSDK (C++)

Component

Version

Vsdk

9.1.1

Vsdk-vasr

5.3.0 UPDATED

Vsdk-csdk

5.1.6 UPDATED

Vsdk-tnl

3.2.1

Vsdk-baratinoo

4.2.1

Vsdk-vtapi

3.2.2

Vsdk-idvoice

4.3.1

Vsdk-tssv

3.3.2

Vsdk-vnlu

2.2.1

Vsdk-audio-portaudio

3.5.2

Vsdk-s2c

1.1.2

VSDK (JAVA)

Component

Version

Vsdk

5.3.0

Vsdk-csdk

5.1.3 UPDATED

Vsdk-tnl

2.5.0

Vsdk-baratinoo

4.0.0

Vsdk-vtapi

3.1.0

Vsdk-idvoice

2.5.0

Vsdk-tssv

2.6.0

Vsdk-vasr

2.2.1

Vsdk-vnlu

1.0.2

Vsdk-s2c

1.1.0

Details

Studio

Studio

Features:
  • Support of Punctuation and other linguistic nuances for Voice Recognition technology (Dictation)

Project Editor

Bug-fixes:
  • In some cases, some sdk weren’t selectable for the Voice Recognition (Continuous) technology

VSDK (C++)

Vsdk-vasr

Features:
  • New voice recognition model type: Dictation to have linguistic nuances corrections over Continuous voice recognition

JavaScript errors detected

Please note, these errors can depend on your browser setup.

If this problem persists, please contact our support.