We are thrilled to announce that our latest AI voice model Vox-1, is now available. With Vox-1 we have unlocked a new realm of possibilities for audio applications with more realistic and higher clarity voices than ever before.
One of the biggest improvements thatVox-1 brings to Replica voices is the ability to export audio in 44.1kHz quality. With audio quality to support the highly emotive characters as well as improved performance of effects such as speech rate and pitch, Vox-1 offers AI character voices that are second to none for video games, film and animation.
As we roll out Vox-1 in the initial stages, which we are calling ‘preview mode’, Vox-1 will be available for a limited selection of voices. Preview mode will remain active while additional voices are added each month in preparation for the full catalogue release early in the new year. All Vox-1 voices will be available with their base emotional styles, with style morphing features to be introduced post full release.
During preview mode, usage of Vox-1 will be completely free!
This will allow users to explore and experiment with the capabilities of Vox-1 without any cost. Whilst we work to streamline servers and prepare for full release, use of voices in preview mode will be rate limited. We will update users on the payment model early in the new year which will coincide with the full release of the Vox-1 library.
Experiencing Vox-1 is easy, simply toggle between Classic and Vox-1 in sandbox or filter the whole voice library to only show Vox-1 capable voices.
Join us on this exciting journey as we unleash the power of Vox-1. Experience the future of voice synthesis with unparalleled emotive capability and stunning audio quality.
Stay tuned for further updates and get ready to embark on a new era of audio creation.