Setting Up Your Avatar
To create your AI model we'll need the following:
- 1.A video recording of you reading the short consent script below (this gives us permission to create your AI model).
- 2.10 to 15 minutes of training footage (requirement details below).
I hereby verify that I, <>, am currently recording this video, and I provide Windsor the permission to create an AI avatar that can replicate parts of my likeness and voice. I understand that this AI avatar can be used to edit videos recorded by me while maintaining that they will look and sound like I recorded the video myself.
Since Windsor partners with Descript to generate audio that sounds like my voice, I will now provide explicit consent to Descript to use this recording: I hereby verify that I, <>, am currently speaking, and that I’d like Descript to create an Overdub version of my voice. I understand that this Overdub Voice can be used to create speech that sounds like my voice.
We require a 10 to 15-minute audio/video recording to create the AI model.
The audio of this recording must match the audio of your template videos (same mic, distance from the mic, same speaking volume, tone, speed, etc.)
- 2.Try to pronounce most words correctly. To that effect, aim for slower and more accurate instead of rushing it. Take as many breaks as needed, we'll edit the file afterward and cut things correctly.
- 3.Disable any software compressors, equalizers, noise suppression, etc. We perform our own sound processing after recording - any additional processing can cause issues.