Overdub Voices can speak the same line of audio in many different tones of voice, or Styles.
A Style is simply the way your Overdub voice delivers a line. This includes different tones of voice or emotions. When you edit existing audio, the Style is created automatically to ensure it matches the delivery of the edited audio.
If you are generating standalone audio, you may select the Style from the available Style pallet.
Creating a Style
To create a style, open any Descript project which contains recordings of your own voice with a speaking style you’d like to duplicate:
- Select 1 or 2 full sentences of the relevant text. Style source material cannot contain any Overdub-generated audio.
- Make sure that the total length of the corresponding audio is between 5-25 seconds.
- Right-click on top of the selected text.
- Select Overdub, and select “Create new Voice Style.”
Now, your unique style will be ready to use when creating audio from scratch!
Improving Voice Style Quality
Styles work best when created using audio you recorded to train your Overdub Voice. You can access this audio by going to Overdub > Your voice > Open training.
Selecting a Style
When creating audio from scratch, select a Style by hovering over the associated speaker label in the speaker label editor, and then choosing an existing Style from the drop-down.
Frequently Asked Questions
Can I select the Voice Style when editing existing audio?
No. When editing existing audio, Overdub automatically creates a custom style based on the audio surrounding the edit to ensure that that it blends seamlessly with your existing audio.
How many Voice Styles I can have for a single Overdub Voice?
You can create as many Voice Styles as you'd like for each Overdub Voice.