Release Notes

xDeTECH v2

The xDeTECH v2 and subsequent releases contain improvements focused on providing a more accurate response earlier in a call. This is achieved by:

  • Reducing the number of audio segments that are rejected due to quality checks. xDeTECH 2.0 now accumulates speech across multiple audio segments to reach minimum aggregated speech for a call sooner

  • Processing results will be returned earlier in a call due to aggregating speech and a NO_ANOMALY_DETECTED decision will be returned if the first processed audio segment is found to be acceptable.

  • New clone detection models and updated thresholds offer enhanced detection and lower BPCER

Info

For Release Notes for xDeTECH 1.x, please refer to Release Notes Archive.

Warning

VCDx 2.0.x is compatible with the VGSx 2.0.x. Both VCDx and VGSx must be upgraded to version 2.0.x

VCDx 2.2.1.0

Released: Sep 2026

Container Release Tags: sentinel-vcdx:3227124

Component Compatibility and Availability: Version 2.2.1.0 is not available as an on-premises release and is supported only within the Daon-hosted TrustX cloud environment.

What's New

  • Improved snapin configuration XML processing to ensure thread-safe access and loading.

  • Enhanced statistics logging with more detailed information regarding metrics.

  • Added support for forwarding snapin logs to standard console output, enabling integration with log aggregation platforms such as DataDog. This feature can be enabled by setting the SNAPIN_CONSOLE_LOGGING environment variable to true.

  • Added startup logging for build version, snap-in version, and the effective default snapin configuration to improve diagnostics and troubleshooting.

  • Extended the /ping endpoint to include the default snapin configuration for enhanced visibility and operational monitoring.

VCDx 2.2.0.0

Released: May 2026

Container Release Tags: sentinel-on-prem:vcdx-gpu-9d5059d

Algorithm Versions: DaonVoiceQC 2.0.2.2, DaonVoiceReplayTelephony 3.0.0.0, DaonCloneTelephony 2.1.0.0

Component Compatibility: VCDx 2.2.0.0 is compatible with VGSx 2.1.0.1 and VGSx 2.1.0.0.

What's New

  • Enhanced Voice Cloning Detection with an updated algorithm and optimized default thresholds for models v1, v2, v3, and v4, improving detection accuracy and overall reliability.

  • Enhanced Replay Attack Detection with an updated algorithm and refined thresholds for models r1 and r2, strengthening protection against audio replay fraud.

  • Introduced the new version of the Quality Control (QC) algorithm, delivering improved audio quality assessment and processing consistency.

  • Updated the TrustX Statistics API to return processed statistics in the response, ensuring backward compatibility with existing integrations.

  • Improved JWT token management through asynchronous processing, reducing dependency on TrustX for individual requests and improving overall service efficiency and scalability.

  • Enhanced JWT token handling by:

    • Increasing the default grace period from 5 seconds to 120 seconds to improve resilience in distributed environments.

    • Introducing configurable token management settings:

      • arthr.jwt.gracePeriod

      • arthr.jwt.refreshInterval

  • Improved system stability in multi-instance deployments by addressing Redis synchronization issues and eliminating the impact of phantom reads during metric processing.

  • Applied security hardening updates, including remediation of relevant Common Vulnerabilities and Exposures (CVEs).

VGSx 2.1.0.1

Released: Apr 2026

Container Release Tags: sentinel-on-prem:vgsx-c0f8534

What's New

  • Added the new property to disable threshold override analysis.service.thresholds.override with a false as a default.

VGSx 2.1.0.0

Released: Apr 2026

Container Release Tags: sentinel-on-prem:vgsx-f25db26

What's New

  • Default thresholds for models v1, v2, v3, and v4 are updated in the service default property file.

  • Default thresholds for models r1 and r2 are updated in the service default property file.

  • Applied security hardening updates, including remediation of relevant Common Vulnerabilities and Exposures (CVEs).

VCDx 2.0.2.1

Released: April 2026

Container Release Tags: sentinel-on-prem:vcdx-gpu-86dcad5

Algorithm Versions: DaonVoiceQC 2.0.1.0, DaonVoiceReplayTelephony 2.2.0.1, DaonCloneTelephony 2.0.0.1

What's New

  • Log severity for expected qc responses has been updated to reduce false error signals, improving operational clarity.

  • Metrics processing and delivery to TrustX Cloud has been decoupled and made asynchronous, improving system resilience and analysis completion times.

  • JWT validation has been optimized to occur once per token lifecycle, reducing authentication overhead while maintaining security and improving overall system performance.

  • Metrics handling has been enhanced with finer configurability, additional value ranges, and performance optimizations to enable more accurate, scalable, and flexible analytics.

VGSx 2.0.1.5

Released: Mar 2026

Container Release Tags: sentinel-on-prem:vgsx-83cddee

What's New

  • Added support for DataDog log format.

  • Updated default streaming URL properties orcx.live_streaming_url_name and orcx.live_streaming_url_localhost .

VGSx 2.0.1.4

Released: Mar 2026

Container Release Tags: sentinel-on-prem:vgsx-ad8f26d

What's New

  • Added localhost as a fallback for streaming request URL with the new property orcx.live_streaming_url_localhost .

  • Enhanced Call ID sanitization with the new property callid.sanitize.enabled with a false as a default.

VCDx 2.0.1.0

Released: February 2026

Container Release Tags: sentinel-on-prem:vcdx-gpu-c471993

Algorithm Versions: DaonVoiceQC 2.0.1.0, DaonVoiceReplayTelephony 2.2.0.1, DaonCloneTelephony 2.0.0.1

What's New

  • Addressed Tomcat High CVE.

  • Adjusted internal default thresholds for audio quality metrics min_stoi, min_pesq, min_si-sdr and clone detection V1 .

  • Adjusted default operating mode to WHOLE_CALL mode.

VGSx 2.0.1.0

Released: February 2026

Container Release Tags: sentinel-on-prem:vgsx-13f6112

What's New

  • Updated threshold for the quality control metrics: min_stoi, min_pesq, min_si-sdr when calling VCDx.

  • Updated threshold for clone detection (V1) when calling VCDx.

  • Addressed Tomcat High CVE.

  • Allow duplicate phone numbers when analysis was not requested.

  • The following fields were removed that were incorrectly included as part of the previous VGSx response:

    • audioSampleLimit

    • audioSampleSizeMB

    • audioSampleCount

    • speechSampleSizeMB

    • speechSampleCount

VCDx 2.0.0.0

Released: October 2025

Container Release Tags: sentinel-on-prem:vcdx-gpu-4373248

Algorithm Versions: DaonVoiceQC 2.0.1.0, DaonVoiceReplayTelephony 2.2.0.1, DaonCloneTelephony 2.0.0.1

Warning

VCDx 2.0 is compatible with the VGSx 2.0. Both VCDx and VGSx must be upgraded to version 2.0.

What's New

  • A new Voice Cloning Detection Algorithm has been introduced and includes the following improvements:

    • Enhanced presentation attack detection with improved accuracy and reduced BPCER. Presentation attack detection now offers robust protection against synthetic speech through expanded coverage of 150 voice cloning systems.

    • Optimized the decision-making process by reducing the number of audio chunks required, resulting in faster and more efficient evaluations.

    • Detection now triggers only after sufficient speech has been collected, ensuring more accurate and consistent results.

    • In xDeTECH 1.x, voice quality assessment was performed in parallel to clone and replay detection. With xDeTECH 2.0, voice quality assessment is performed ahead of the clone/replay detection and will lead to longer processing times.

  • Cache changes:

    • To handle the aggregation of audio data, speech template data is persisted in cache until sufficient audio is collected and that speech is processed (or time expires). This results in higher Redis cache usage.

Warning

Daon recommends a minimum Redis cache size of cache.t4g.medium for deployments with multiple VCDx instances. Customers handling more than 600 concurrent calls should consult Daon Support for Redis sizing guidance.

  • A new property has been added in the VCDx qc.template.inference.duration

  • Addressed CVEs:

    • High: CVE-2025-48988, CVE-2025-52999, CVE-2014-4043

    • Medium: CVE-2025-49125, CVE-2025-48924, CVE-2025-53864, CVE-2025-22227, CVE-2025-41234

  • API changes:

    • Additional model and changes to model names has resulted in minor API changes in the API response. Please refer to the separate section: The VCDx API.

VGSx 2.0.0.0

Released: October 2025

Container Release Tags: sentinel-on-prem:vgsx-9e5f0ea

What's New

  • Reduced the time that a call is kept in memory from 2 hours to 1 hour.

  • Limited the number of raw audio samples per call to 500, and introduced a new property to manage this value: audio.sample.per.call.limit property.

  • Updated the maximum number of attempts to 1000 to limit the number of audio samples sent to VCDx per call.

  • Updated endpoint to track the total count and size of raw audio and speech samples currently in memory.

All-In-One Container Release

Released: October 2025

Container Release Tags: sentinel-on-prem:98b989d

Algorithm Versions: DaonVoiceQC 2.0.1.0, DaonVoiceReplayTelephony 2.2.0.1, DaonCloneTelephony 2.0.0.1

What's New

  • Includes the above VCDx and VGSx 2.0.0.0 releases

  • Numerous CVE fixes have been made since the previous All-In-One release.

Known Issues

Key

Description

Impact

VGSV-196

When a Quality Check is performed and the entire audio chunk is labeled as speech, the Noise Energy will be 0, and the corresponding SNR score will be labeled as 1000. This score will not be added to Grafana but will be shown as an error in the logs related to the metrics only.

Low

Supported Platforms

VCDx is provided as a docker container with support for CPU and GPU deployments. Production systems are strongly encouraged to run on GPU. Daon validates and tests on Amazon AWS g4dn.xlarge instance types and recommends that instance size for production deployments. See Performance Testing and Scalability for more details.

Instance Size

GPU

vCPUs

Memory (GiB)

g4dn.xlarge

1

4

16

Info

The vcdx-gpu deployment requires nvidia-smi to be installed on the host machine.

VGSx is provided as a docker container with support for CPU deployments. 4 Cores and 16 GB RAM are recommended for VGSx.

Supported Browsers (Test Tool)

  • Google Chrome

  • Mozilla Firefox

  • Safari