Voice Model definition

Voice Model means a computer-generated AI model or electronic creation or recreation of a voice or voices created using new or existing sound recordings or anonymized data files of one or more individual(s) regardless of media or source, that can be used to synthesize speech. “Digital Voice Replica” (or “Fine-Tuned Model”) means a Voice Model trained on recordings of specific individual(s) that has individually-identifiable unique characteristics (such as sound, tone, rhythm, or cadence) that remain consistent and recognizable when used to synthesize speech.
View Source

Examples of Voice Model in a sentence

  • In addition to ▇▇▇▇▇▇▇▇’s termination rights set forth herein and without prejudice to any other rights of Veritone at law or in equity, Veritone may suspend its performance under this Agreement and any other agreement with Customer, and Customer’s access to the VaaS Solution and any Custom Voice Model, if Customer fails to comply with any part of its payment obligations set forth herein.

  • In consideration for the license granted hereunder and Customer’s access and use of the VaaS Solution, Customer shall pay the license fees, Custom Voice Model fees, and any processing, storage and/or other fees for the Services, as applicable, in the amounts and on the payment terms set forth in the License Agreement (collectively, the “Fees”).

  • Payment of the Session Fees as set forth herein entitles Developer, during the term of this Agreement, to use the Recordings to create a Foundational Voice Model.

  • In exchange for revenue-sharing payments made by Developer to each Performer (as set forth below) for the use of their Recordings in the underlying data set that comprises the Foundational Voice Model, the Performer consents to the use of their Recordings in the Foundational Voice Model for the entire duration of time in which the Foundational Voice Model is used by Developer.

  • If Developer sells, transfers, or assigns its rights to license and/or use the Foundational Voice Model, Performers’ consent to use of the Recordings expires until such time as the buyer, licensee, or transferee signs, and SAG-AFTRA accepts (in its complete and sole discretion),an Assumption Agreement as detailed below at Section 6(b).

  • With respect to payments made pursuant to Section 7.a) of this Agreement, Developer shall furnish to SAG-AFTRA a complete list of Performers, including each Performer's full name, Social Security number, dates of employment, and revenue share percentage, not more than sixty (60) calendar days following inclusion of a covered performance in the Foundational Voice Model.

  • Developer may engage Performer(s) for a recording session in connection with the creation of the Foundational Voice Model at no less than the minimum compensation set forth in the then-current Co-Ed (“Session Fee”), and the corresponding contributions to the SAG-AFTRA Health Plan and AFTRA Retirement Fund (the “Plans”).

  • Concurrently with making such payments, Developer shall furnish to SAG-AFTRA written reports showing the quarterly gross revenue sources and amounts from the sale, lease, license and distribution of the Foundational Voice Model.

  • Company may not assign or otherwise transfer any IPRs in the Voice Model to any third party.

  • As part of the TTS Service, Company will, during the Term, use the Voice Model to generate Audio Assets.