Voice components

VeriSpeak SDK includes the following biometric components for voiceprint template extraction, speaker verification and identification.

• Voice Client component
• Mobile Voice Client component
• Voice Extractor component
• Mobile Voice Extractor component
• Voice Matcher component
• Mobile Voice Matcher component
• Matching Server component

See Product Advisor to find out what specific components will be needed for your system.

The Voice Client component creates voice templates from audio samples on PC and Mac platform. It is intended for using on PC- and Mac-based clients of network-based biometric systems. The component can be configured to perform automatic voice activity detection, which allows to begin voice capture only when users start speaking, and finish capture when they stop speaking.

See technical specifications for the size of voice template and the requirements for voice record.

The Voice Client extracts a single voiceprint template in 0.6 seconds. The specified performance requires a PC or laptop with at least Intel Core i7-4771 processor.

Three licenses for the Voice Client component are included with VeriSpeak 2025.2 Extended SDK. The licenses can be used on Microsoft Windows, Linux x86-64 or macOS platform. More licenses for this component can be purchased any time by VeriSpeak 2025.2 Extended SDK customers.

The Mobile Voice Client component creates voice templates from audio samples. It is designed for using with Android-based or iOS-based devices on client-side of network-based biometric systems.

The component is designed to run on Android or iOS or ARM Linux devices. The Android devices should be based on at least Snapdragon S4 system-on-chip (Krait 300 processor with 4 cores running at 1.51 GHz).

The Mobile Voice Client component can be configured to perform automatic voice activity detection, which allows to begin voice capture only when users start speaking, and finish capture when they stop speaking.

See technical specifications for the size of voice template and the requirements for voice record.

Three licenses for the Mobile Voice Client component are included with VeriSpeak 2025.2 Extended SDK. The licenses can be used on Android, iOS or ARM Linux platform. More licenses for this component can be purchased any time by VeriSpeak 2025.2 Extended SDK customers.

Voice Extractor creates voice templates from audio samples on PC and Mac platform. The component can be configured to perform automatic voice activity detection, which allows to begin voice capture only when users start speaking, and finish capture when they stop speaking.

See technical specifications for the size of voice template and the requirements for voice record.

The component extracts a single voiceprint template in 1.34 seconds. The specified performance requires a PC or laptop with at least Intel Core i7-4771 processor.

One Voice Extractor license is included with VeriSpeak 2025.2 Standard SDK and VeriSpeak 2025.2 Extended SDK. The license can be used on Microsoft Windows, Linux x86-64 or macOS platform. More licenses for this component can be purchased any time by VeriSpeak 2025.2 SDK customers.

The Mobile Voice Extractor creates voice templates from audio samples and is designed to be run on Android or iOS or ARM Linux devices. The Android devices should be based on at least Snapdragon S4 system-on-chip (Krait 300 processor with 4 cores running at 1.51 GHz). The component extracts a single voiceprint template in 1.34 seconds.

The Mobile Voice Extractor component can be configured to perform automatic voice activity detection, which allows to begin voice capture only when users start speaking, and finish capture when they stop speaking.

See technical specifications for the size of voice template and the requirements for voice record.

One Mobile Voice Extractor license is included with VeriSpeak 2025.2 Standard SDK and VeriSpeak 2025.2 Extended SDK. The license can be used on Android, iOS or ARM Linux platform. More licenses for this component can be purchased any time by VeriSpeak 2025.2 SDK customers.

The Voice Matcher performs voice template matching in 1-to-1 (verification) and 1-to-many (identification) modes on PC and Mac platform. Also the Voice Matcher component includes fused matching algorithm that allows to increase template matching reliability by matching templates that contain fingerprint, face, voice and/or iris records (note that matching fingerprints, irises and faces requires to purchase Fingerprint Matcher, Iris Matcher and Face Matcher components correspondingly).

The Voice Matcher component matches 8,000 voiceprints per second and is designed to be used in desktop or mobile biometric systems, which run on PCs or laptops with at least Intel Core i7-4771 (3.5 GHz) processor.

One Voice Matcher license is included with VeriSpeak 2025.2 Standard SDK and VeriSpeak 2025.2 Standard SDK. The license can be used on Microsoft Windows, Linux x86-64 or macOS platform. More licenses for this component can be purchased any time by VeriSpeak 2025.2 SDK customers.

The Mobile Voice Matcher performs voice template matching in 1-to-1 (verification) and 1-to-many (identification) modes. It matches 100 voiceprints per second and is designed to be used in embedded or mobile biometric systems, which run on Android or iOS or ARM Linux devices. The Android devices should be based on at least Snapdragon S4 system-on-chip (Krait 300 processor with 4 cores running at 1.51 GHz).

One Mobile Voice Matcher license is included with VeriSpeak 2025.2 Standard SDK and VeriSpeak 2025.2 Extended SDK. The license can be used on Android, iOS or ARM Linux platform. More licenses for this component can be purchased any time by VeriSpeak 2025.2 SDK customers.

The Matching Server is ready-to-use software intended for building moderate size client-server and other network-based systems like local AFIS or multi-biometric identification system. The Server software runs on a server PC and allows to perform the biometric template matching on server side using:

• Voice Matcher component for voice template matching.

Client communication module that allows sending a task to the Matching Server, querying status of the task, getting the results and removing the task from server, is included with VeriSpeak 2025.2 SDK. This module hides all low level communications and provides high-level API for the developer.

The components and database support modules with source codes included for Matching Server component are listed in the table below. Custom modules for working with other databases can also be developed by integrator and used with the Matching Server software.

The table below shows what components are available with Matching Server software.

The Matching Server component requires a special license that allows to run the Matching Server on all machines that run the voice matching components obtained by an integrator. The Matching Server software is included with:

• VeriSpeak 2025.2 Extended SDK.