Voice Biometrics Release Notes

The following sections list every released version of Voice Biometrics, newest first. Each section comes from the monthly OCP® Release Notes page named in its Released line.

Voice Biometrics 1.18.2

Released: November 2026

This is a targeted hotfix patch release for BioStore for Frankfurt environment.

Voice Biometrics 1.18.0

Released: September 2026

This release focuses on multi-region deployments. Voice Biometrics now reads from a local regional database replica instead of routing every query back to the primary region, which removes the latency and timeouts previously seen on Console and API requests in secondary regions. It also introduces optional plain user ID export for analytics, IAM authentication for Kafka, and a set of API and reliability fixes.

New Features

Regional Database Reads - Voice Biometrics now directs write operations to the primary database and read operations to a replica in the local region, substantially reducing response times and removing timeouts previously affecting Console pages and profile, session, verification, blocklist, and fraudster API calls.

Optional Plain User ID in Analytics Events - events sent to the analytics stack carry a hashed user ID by default. This release adds a per-group option (disabled by default, requires a support request and written authorisation) to send the plain identifier instead, in the existing user_id field.

Blocklist File ID - the Blocklisting page now shows the ID of the uploaded audio file for each entry.

Improvements

• Kafka authentication: Kafka connections now support AWS IAM authentication as an alternative to unauthenticated access (existing unauthenticated connections are unaffected unless the new configuration is supplied).

• API protection: batch_size on the V2 sessions and fraudster voiceprint queue endpoints is now validated against both a lower and an upper bound. See Upgrade Notes.

• Error handling: Storage service failures with no error payload are now reported as a controlled upstream error instead of a generic 500.

• Documentation: the published API spec, endpoint collections, and reference pages have been regenerated.

Voice Biometrics 1.17.6 (Hotfix)

Released: September 2026

This is a targeted hotfix release for BioStore & BioService. It addresses a high CPU usage affecting the Frankfurt environment.

Voice Biometrics 1.17.5 (Hotfix)

Released: August 2026, September 2026

This is a targeted hotfix for BioStore, addressing a database schema configuration issue and a startup issue affecting certain environments.

Voice Biometrics 1.17.1

Released: June 2026

This release addresses high-severity vulnerabilities identified in third-party library dependencies. The affected libraries have been updated to remediate the findings and reduce exposure to potential security risks. Also contains a bug fix regarding the handling of large audio files by enrollment server.

Voice Biometrics 1.17.0

Released: May 2026, June 2026

Cross-Group VB Operations

Enrollment, verification, and opt-out operations can now be triggered across multiple groups within the same organization. This enables deployments where a single user is enrolled under different groups, using a profile-based group resolution model.

New API Endpoints

Three new versioned endpoints have been added to support multi-group operations:

• POST /api/v2/enrolments - supports group-specific audio download via a new application_group field.

• POST /api/v3/users/optout - supports profile-based group resolution via a new profile_id field.

• POST /api/v3/users/info/search - supports profile-based group resolution via a new profile_id field.

All endpoints remain backward compatible - existing fields continue to work unchanged.

Improvements

• Error handling: TokenService errors are now correctly propagated with the original HTTP status code instead of returning a generic 500.

• Resilience: Voiceprints with missing or empty vector data are now gracefully skipped during processing instead of causing failures.

• Accessibility: The Voice Biometrics Console now supports full keyboard navigation (ARIA/WCAG compliant).

Bug Fixes

Security

This release includes dependency and container image updates to address known high and medium severity vulnerabilities across all components.

For more information go to Voice Biometrics API and Voice Biometrics Blocklists.

Upgrade Notes

Component Versions

Voice Biometrics 1.16.1

Released: May 2026

Fixes

• Voice Profile Migration for Legacy Sessions - Voice biometric profiles enrolled before the April 2025 deepVB® release are now correctly included when migrating to the latest voice model, ensuring all enrolled users retain their profiles and are not skipped during the upgrade process.

Voice Biometrics 1.16.0

Released: November 2025, March 2026

• Creation of a new Voice Biometrics Service with two components: Voice Biometrics Enrollment Service and Voice Biometrics Verification Service. These services aim to introduce a model that improves the KPIs and metrics of Voice Biometrics and Blocklisting. Initially, they will run parallel to BioBuilder before gradually replacing it.

• To support better performance and future feature enhancements, we have completed a significant upgrade to the data structure that manages your voiceprints. This modernization effort improves the efficiency and scalability of our voice recognition system, ensuring a smoother and faster experience as we introduce new capabilities.

• We have implemented a new, flexible data structure to support upcoming enhancements in our Liveness Detection and Voice Biometric (VB) services. This change allows us to manage feature configurations more efficiently, paving the way for advanced and customized security capabilities in future releases.

• To maximize the stability of our BioStore component, we have updated the startup procedure. The system will now perform a strict validation of all database changes (schema updates). If an error is detected during this process, the component will halt immediately, preventing it from operating with an unstable configuration. This guarantees a higher level of operational consistency.

• The method for submitting voiceprint data has been upgraded to support the next generation of our Voice Biometrics model. A new version of the voiceprint request endpoint is now available, featuring a refined data structure that prepares the system for more complex and accurate voice models in the future.

• To ensure the highest level of transactional reliability, we have enhanced the backend validation of all data modification operations. The system now enforces strict rules that prohibit the execution of update or delete requests lacking necessary parameters (empty or null), providing greater stability and safety for your stored information.

• Implementation of foundational enhancements to improve the reliability, security, and maintainability of our platform:

  • Enhanced Data Security and Validation: We have introduced strict validation across all modification and deletion endpoints. The system now requires necessary identifying properties to be explicitly provided, preventing accidental or improperly structured requests from altering your data.

  • Infrastructure Modernization: Our Continuous Integration/Continuous Deployment (CI/CD) pipelines have undergone a significant update. By standardizing registry and host references with dynamic environment variables, we ensure a more flexible, scalable, and highly reliable deployment process going forward.

• This release includes a foundational update to the BioStore component, focused on improving long-term stability:

  • Hardcoded test secrets were removed to enhance security.

  • Several logic issues were analyzed, fixed, and key code areas were refactored to improve reliability.

  • Deployment configurations were reviewed and optimized.

• The unused Recognitions database table has been decommissioned and removed from the schema. This action simplifies the underlying database structure and reduces overhead, ensuring that our data model remains focused and scalable.

• The organisation key was renamed back as group in the Billing request payload in Biostore Server to protect the seamless track of the Voice Biometrics events from Billing Service.

For more information, see Voice Biometrics.

Voice Biometrics 1.15.5

Released: March 2026

Features

• Added a custom socket endpoint to receive audio from the web plugin (browser extension).

Improvements

• Optimized Redis handling to improve performance.

Fixed

• Fixed an issue to limit the dispatch of Speech-to-Text transcriptions only when the session is an Agent Assist one. This resolves instabilities in the latest Insights deployment caused by the Agent VB Middleware sending transcriptions for all sessions.

Voice Biometrics v1.15.4

Released: November 2025

• An update was deployed to ensure full operational compatibility with recent changes to the GENESYS call flow procedure, specifically addressing the mechanism for stream pausing and resumption during call initiation. This resolves an issue where session identifiers were incorrectly tracked, guaranteeing the accurate and consistent performance of verification processes at the beginning of all calls.

Voice Biometrics v1.15.1

Released: October 2025

• Adjust the existing JWT and signature validation to meet NICE's new requirements, ensuring seamless integration with Omilia Voice Biometrics. Goal is to ensure that all APIs used by NICE enforce signature validation for client authenticity, based on the presence of the JWT and/or the session-driven flag.

• Launch of Agent-side File Enrollment through audio recordings from RingCentral - retrieved post call.

• Optimization of dialog status error handling in Agent VB Middleware in order to track in a more robust way cases where ASR or any other Third Party component is unreachable

Voice Biometrics V1.14.0

Released: August 2025

Agent-side Voice Biometrics

• Enroll button can be removed from the agent widget for certain users, so that agents that are not authorized to enroll users are disabled from doing so

Voice Biometrics Core

• Inclusion of the Environment name as a variable in all billing events following the installation of Voice Biometrics in multiple OCP production environments

• Change variables to adapt the values to muti-region for Analytics purposes

Voice Biometrics v1.13.0

Released: March 2025, May 2025

Added

• Empty audio has incorrect voiceprint fail reason

• Crop info mismatch

• Deploy 5.4.3 biopack

• Create client-specific configuration for Dominant Speaker Detection

• Fetch (ocp) groups by (ocp) organization

• Change enrollment spelling on Enrollments Review Page

• Add profile_id field in get session by ID response

• Use multigraph grammar for agent middleware

New Features

• Make Blocklisting Configurable on a queue level

• Add aws-inspector in ci/cd

• Provide agent actions regarding users

Fixed

• VB Review is not refreshing when the Organization is changed

Improved

• Investigate Liquibase tags

• Allow search for opted out biouserID via console UI

• Compare voiceprint of re-enrollment request to existing voiceprint(s) of the user

Voice Biometrics v1.12.0

Released: February 2025

Voice Biometrics API

• Multi-region Support. For more information, go to Voice Biometrics API.

• Remove server-sent event endpoints

Agent-side widget

• Limited support for grey-listing. For more information, go to Voice Biometrics Agent Widget User Guide.

• Deprecate old widget

OCP Console

• Show plain bio user IDs in Verifications Review Tab for Maintainers and Owners

For more information, go to Voice Biometrics Tab.

Voice Biometrics v1.11.0

Released:

Agent-side widget

• Add option to have minimal ANI Anti-spoofing UI

Voice Biometrics API

• Add liveness detection results into session status endpoint

• Restructure response of session status endpoint

OCP Console

• Show top priority biokey column in Review Enrollments page

• Verifications will be shown up to one month in Review Verifications page

• Introduce Viewer, Developer, Maintainer, Owner roles

• Fix fraudster appearing as enabled whereas voiceprint creation has failed

Voice Biometrics v1.10.0

Released:

Agent-side widget

• Fix issue with opting out specific enrolled users

• Drop no-store request header from JS file so that widget load faster

• Prevent automatic search for biokeys that by definition return too many results if used exclusively

• Improve opt-out confirmation

OCP Console

• Link Enrollments review page dialog ID to Monitor for IVR calls

• Sort biousers in chronological order of creation

• Hide Recording ID and Voiceprint ID from fraudster list

• Harmonize font size of VB in OCP Console to align with the rest of the components

• Support internationalization for VB in OCP Console

Voice Biometrics Core

• Increase limit of Enrollment Audios to 50MB

Voice Biometrics v1.9.1

Released:

Fixed

• User ID is not accepted when having another key/name in batch enroll API - If only one biokey present then hitting Enter has unexpected behavior QA Testing - Verification is not working if user_id contains + character

Voice Biometrics v1.9.0

Released:

Agent-side widget

• Optimize async methods

• Prevent default date of birth from being submitted as a value when enrolling

• Replace server-sent events with websocket communication between front-end and back-end

• Show ANI Validation results on widget

Voice Biometrics API

• Provide websockets for getting verification results and dialog status updates

• Deprecate server-sent events API endpoints

OCP Console

• Display 0 seconds of clean speech in cases of failed enrollments with no speech frames

• Manage Blocklists through OCP Console

Voice Biometrics v1.8.0

Released:

Agent-side widget:

• Replace server-sent events with websocket communication between front-end and back-end

Voice Biometrics API:

• Provide websockets for getting verification results and dialog status updates

• Deprecate server-sent events API endpoints

• Add blocklist results to session status endpoint

Voice Biometrics Core:

• Introduce new enrollment fail reason for cases where no dominant speaker is found

OCP Console:

• Display 0 seconds of clean speech in cases of failed enrollments with no speech frames

Billing:

• Change method of billing for verifications