VeriSpeak SDK.

The software component VeriSpeak SDK is intended for developers of application systems that use the biometric "voice" modality.

Contact Us

Features of the VeriSpeak SDK.

VeriSpeak's voice identification technology allows biometric systems developers to ensure security by verifying the authenticity of the voice and phrase, and the ability to compare voice prints in 1-to-1 and 1-to-many modes on different platforms.

VeriSpeak 13.0 Standard SDK - 339 euros.

VeriSpeak 13.0 Extended SDK - 859 euros.

The project cost is calculated upon request. 

VeriSpeak SDK capabilities.

  • Performance and platforms
    Development platforms

    VeriSpeak as a speaker recognition algorithm ensures the system's security by verifying the authenticity of both the voice and the phrase. Voiceprint patterns can be matched in 1-to-1 (verification) and 1-to-many (identification) modes.

    Available as a software development kit that allows you to develop stand-alone and networked solutions on Microsoft Windows, Linux, macOS, iOS, and Android platforms.

    More details
  • Text-dependent algorithm
    Text-dependent algorithm

    Text-dependent speaker recognition is based on speaking a single phrase for registration and verification. The VeriSpeak algorithm determines whether a voice sample matches a pattern extracted from a particular phrase. During registration, the person registering is asked for one or more phrases. Later, that person may be asked to say a certain phrase for verification. This method protects against the use of this person's secretly recorded random phrase.

    More details
  • Two-factor authentication using a passphrase
    Two-factor authentication using a passphrase

    VeriSpeak's voiceprint matching algorithm can be configured to work in a scenario where each user records a unique phrase (such as a passphrase or answer to a "secret question" that only the registered person knows). Later, the person is recognized by their specific phrase with high accuracy. The overall security of the system is increased because the authenticity of the voice and the passphrase are verified.

    More details
  • Text-independent algorithm
    Text-independent algorithm

    Phrase-independent speaker recognition uses different phrases to register and recognize users. This method is more convenient, as it does not require each user to remember a passphrase. It can be combined with a text-based algorithm for faster text-independent searching followed by phrase validation using a more robust text-based algorithm.

    More details
  • Live voice detection
    Live voice detection

    The system may require each user to register a set of unique phrases. Later, the user will be prompted to say a specific phrase from the registered group. In this way, the system can guarantee the verification of a live person (as opposed to an impostor who uses a voice recording).

    More details
  • Possibility of identification
    Possibility of identification

    VeriSpeak functions can be used in 1-to-1 (verification) and 1-to-many (identification) mapping modes.

    More details

Product advantages

  • Text-dependent algorithm
    prevents unauthorized access by secretly recording the user's voice.
  • Two-factor authentication
    by verifying voice biometrics and passphrase authenticity.
  • For voice recording
    ordinary microphones and smartphones are suitable for users.
  • Available as
    a cross-platform SDK that supports multiple programming languages.

Contact Us

Have questions or want to share your thoughts?
Contact us image