Develop
Develop
Select your platform

TTS Voice Customization

Voice SDK’s TTS service provides multiple options for voice customization. The simplest is to use the Voice Preset that comes with Voice SDK. You can also add your own Voice Preset for more customization.
The following settings are used for the TTS Voice Preset Data Asset:
  • Voice: Name of the voice to be used, such as Charlie or Rebecca. This setting contains the following parameters as well:
    • Locale: Locale and language used by the voice. For example, en_US for American English.
    • Gender: Gender of the voice.
    • Style: Style of speaking, such as soft or formal. The same styles are not available for every voice.
  • Speed: How fast the text is spoken, indicated using percentages of the voice speed as originally recorded. Values range from 50% to 200%, with 100% as the default.
  • Pitch: The pitch of the voice audio, using percentages of the original voice. Values range from 25% to 400%, with 100% as the default.
  • Gain: The audio gain, in percentages from 1% to 100%, with 50% as the default.
    "Audio Gain"
Did you find this page helpful?
Thumbs up icon
Thumbs down icon