Skip to main content
Skip table of contents

VDK Runtime 6.2.0 - 14th April 2026

Summary

We’re excited to announce the release of VDK Runtime 6.2.0, introducing Voice Recognition User Words — a powerful new capability that lets you add custom, user-provided audio samples and associate them with specific words or phrases to be recognized.

This release also introduces Session Routes, a new set of endpoints that give you more control over how you create, manage, and interact with audio processing sessions and their pipelines.

What's New in VDK Runtime 6.2.0?

Voice Recognition User Words

With this feature, applications can capture a user saying anything and link that recording to a target word, enabling highly personalized and accurate voice recognition for names, jargon, acronyms, or domain-specific terms. Voice Recognition User Words improves recognition accuracy in challenging or customized scenarios, all without requiring changes to existing application code.

Session Routes

With the introduction of Session Routes, applications can now create, configure, and manage audio processing sessions more efficiently through dedicated API endpoints.

This feature allows developers to define session configurations upfront — including pipelines, producers, modifiers, and consumers — and control when those pipelines are actually initialized and executed.

Session Routes make it easier to:

  • Create and organize sessions as logical containers for pipelines

  • Load and start pipelines only when needed

  • Manage real-time communication through session-based WebSocket connections

  • Control the full lifecycle of audio workflows, from creation to deletion

By separating configuration from execution, Session Routes provide greater flexibility, improved resource management, and a more structured way to build complex audio processing systems.

Learn More

Additional updates and refinements have been made across the VDK ecosystem to enhance developer experience and performance.

We’re committed to improving usability, flexibility, and performance — and your feedback on VDK 6.2.0 is always welcome.

Versions

Vdk-Service

Component

Version

Vdk-Service

2.0.3 UPDATED

Samples (C++)

Component

Package name

Version

Technologies

Chained grammars

chained-grammars

7.0.0 UPDATED

VOICE RECOGNITION (GRAMMAR)

Dynamic grammar

dynamic-grammar

7.0.0 UPDATED

VOICE RECOGNITION (GRAMMAR)

Simple application

simple-application

7.0.0 UPDATED

VOICE RECOGNITION (GRAMMAR) VOICE SYNTHESIS

Tts

tts

7.0.0 UPDATED

VOICE SYNTHESIS

Voice biometrics

voice-biometrics

7.0.0 UPDATED

VOICE BIOMETRICS

Voice Commands Language Understanding

voice-commands-language-understanding

4.0.0 UPDATED

VOICE RECOGNITION (CONTINUOUS)

Speech Enhancement

speech-enhancement

3.0.0 UPDATED

VOICE RECOGNITION (GRAMMAR) SPEECH ENHANCEMENT

VSDK (C++)

Component

Version

Vsdk

11.0.1 UPDATED

Vsdk-csdk-asr

2.0.1 UPDATED

Vsdk-vec-addon

2.0.1 UPDATED

Vsdk-csdk-tts

2.0.1 UPDATED

Vsdk-idvoice

6.0.1 UPDATED

Vsdk-tssv

5.0.1 UPDATED

Vsdk-vnlu

4.0.1 UPDATED

Vsdk-s2c

3.0.1 UPDATED

Vsdk-audio-portaudio

5.0.1 UPDATED

Samples (JAVA)

Component

Package name

Version

Technologies

Chained grammars

chained-grammars

7.3.0 UPDATED

VOICE RECOGNITION (GRAMMAR)

Dynamic grammar

dynamic-grammar

6.3.0 UPDATED

VOICE RECOGNITION (GRAMMAR)

Free speech

free-speech

4.0.0

VOICE RECOGNITION (CONTINUOUS)

Simple application

simple-application

6.3.0 UPDATED

VOICE RECOGNITION (GRAMMAR) VOICE SYNTHESIS

Tts

tts

7.3.0 UPDATED

VOICE SYNTHESIS

Voice biometrics

voice-biometrics

4.2.0 UPDATED

VOICE BIOMETRICS

Voice Commands Language Understanding

voice-commands-language-understanding

1.0.1

VOICE RECOGNITION (CONTINUOUS)

Speech Enhancement

speech-enhancement

3.3.0 UPDATED

VOICE RECOGNITION (GRAMMAR) SPEECH ENHANCEMENT

Vdk service

vdk-android-sample-service

1.0.0

VSDK (JAVA)

Component

Version

Vsdk

7.3.0 UPDATED

Vsdk-csdk-asr

4.0.0 UPDATED

Vsdk-vec-addon

2.0.0 UPDATED

Vsdk-csdk-tts

4.0.0 UPDATED

Vsdk-idvoice

4.3.0 UPDATED

Vsdk-tssv

4.3.0 UPDATED

Vsdk-vnlu

1.1.0

Vsdk-s2c

4.0.0 UPDATED

Details

VSDK (C++)

Vsdk

Features:
  • Voice Recognition User Words

    • Introduced support for User Words in Voice Recognition.

    • Added a new Enroller component to create and manage user words.

    • User Words are supported only by Dynamic models.

  • File Producer
    Support async mode

  • Status Reporter
    New error type Exception this error is reported when an exception occurs in internal thread

VSDK (Android)

Vsdk

Features:
  • Voice Recognition User Words

    • Introduced support for User Words in Voice Recognition.

    • Added a new Enroller component to create and manage user words.

    • User Words are supported only by Dynamic models.

  • Pipeline

    • Added new methods to clear all consumers and producers.

  • ASR Post-Processor

    • Added a new overload to invoke commands without parameters.

VDK-Service

Vdk-Service

Features:
  • New routes to manage sessions and pipelines

  • New route to enroll user words

  • Update voice recognition and advanced recognition routes to support user words

  • Improve voice recognition chaining grammars

  • Support audio devices on Linux, Windows, and Android, limited to session-related routes.

JavaScript errors detected

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

If this problem persists, please contact our support.