Setting Up Your Avatar

/video

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).

Training Footage Requirements

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.)

Important Reminders For When Recording:
  1. Record yourself speaking into a camera. Here’s a good script we recommend. Just record yourself reading this. If you prefer, you can pick anything else from this website - or read your favorite book for 10 to 15 minutes.

  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.

  4. You may record using your phone as a webcam. Here are details on 3 good options.

  5. If recording on your own, check out Recording Software.

Last updated

Was this helpful?