latest 6.4.0 6.3.1 6.3.0 6.2.0 6.1.0 6.0.0 5.9.1 5.9.0 5.8.0 5.7.0 5.6.0 5.5.0 5.4.0 5.3.0 5.1.1 5.1.0 5.0.0 4.4.0 4.3.0 4.2.1 4.2.0 4.1.1
Auto Light Dark
Auto Light Dark
latest 6.4.0 6.3.1 6.3.0 6.2.0 6.1.0 6.0.0 5.9.1 5.9.0 5.8.0 5.7.0 5.6.0 5.5.0 5.4.0 5.3.0 5.1.1 5.1.0 5.0.0 4.4.0 4.3.0 4.2.1 4.2.0 4.1.1

VDK Runtime 6.4.0 - 8th October 2026

Summary

We’re excited to announce the release of VDK Runtime 6.4.0, introducing an expanded selection of speech models and voices, along with improvements to logging and text-to-speech capabilities.

This release adds 8 new Neural ASR models and updates 15 existing Neural ASR models, providing expanded speech recognition capabilities. It also introduces 29 new voices and updates 68 existing voices across Neural, Embedded-Premium, Embedded-High, Embedded-Pro, Embedded-Compact, and Premium-High qualities.

The release also unifies the logging experience across the VSDK, CSDK, and VDK-Service components and introduces TTS watermarking for enhanced text-to-speech capabilities.


We’re excited to announce the release of VDK Runtime 6.4.0, which resolves issues caused by library linking conflicts.

This release improves dependencies integration to enhance exception handling and application stability. This change preserves detailed error information, resulting in more reliable error reporting and, on Android, resolves crashes that could occur in certain error scenarios.

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 6.4.0 is always welcome.

Versions

Vdk-Service

Component

Version

Vdk-Service

2.2.1 Updated

Samples (C++)

Component

Package name

Version

Technologies

Chained grammars

chained-grammars

8.0.0 Updated

Voice Recognition (Grammar)

Dynamic grammar

dynamic-grammar

8.0.0 Updated

Voice Recognition (grammar)

Simple application

simple-application

8.0.0 Updated

Voice Recognition (grammar) Voice synthesis

Tts

tts

8.0.0 Updated

Voice synthesis

Voice biometrics

voice-biometrics

8.0.0 Updated

Voice Biometrics

Voice Commands Language Understanding

voice-commands-language-understanding

5.0.0 Updated

Voice Recognition (continuous)

Speech Enhancement

speech-enhancement

4.0.0 Updated

Voice Recognition (graMmar) SPeech enhancement

Free Speech

free-speech

5.0.0 Updated

Voice Recognition (NEURAL)

VSDK (C++)

Component

Version

Vsdk

12.0.0 Updated

Vsdk-csdk-asr

3.0.0 Updated

Vsdk-vec-addon

3.0.0 Updated

Vsdk-csdk-tts

3.0.0 Updated

Vsdk-idvoice

7.0.0 Updated

Vsdk-tssv

6.0.0 Updated

Vsdk-vnlu

5.0.0 Updated

Vsdk-s2c

4.0.0 Updated

Vsdk-audio-portaudio

6.0.0 Updated

Samples (JAVA)

Component

Package name

Version

Technologies

Chained Grammars

chained-grammars

8.0.0 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

Speech Enhancement

speech-enhancement

4.0.0 Updated

Voice Recognition (graMmar) SPeech enhancement

Tts

tts

8.0.0 Updated

Voice synthesis

Voice Biometrics

voice-biometrics

5.0.0 Updated

Voice Biometrics

Free Speech

free-speech

6.0.0 Updated

Voice Recognition (NEURAL)

VSDK (JAVA)

Component

Version

Vsdk

8.0.0 Updated

Vsdk-csdk-asr

5.0.0 Updated

Vsdk-vec-addon

3.0.0 Updated

Vsdk-csdk-tts

5.0.0 Updated

Vsdk-idvoice

5.0.0 Updated

Vsdk-tssv

5.0.0 Updated

Vsdk-vnlu

1.1.0

Vsdk-s2c

5.0.0 Updated

Details

VSDK & VDK-Service

Vsdk & Vdk-Service

Fixes & Improvements:
  • Unified the logging system across VSDK, CSDK, and VDK-Service.

  • Consolidated logging into a single log file with unified configuration.

  • Logging settings can now be configured through vsdk.json. By default, logs are written to the console and to a default log file.

Voice Synthesis

Voice Synthesis

  • Added support for TTS watermarking.

  • Added 29 new voices, with the following voice qualities:

    • 27 Neural

    • 5 Embedded-Premium

    • 1 Premium-High

    • 5 Embedded-High

    • 1 Embedded-Pro

    • 1 Embedded-Compact

  • Updated 68 voices, with the following voice qualities:

    • 12 Neural

    • 18 Embedded-Premium

    • 49 Embedded-High

    • 41 Embedded-Pro

    • 28 Embedded-Compact

Voice Recognition

Voice Recognition

  • Added 8 new Neural ASR models.

  • Updated 15 Neural ASR models.