Voice Configuration
Configure the voice synthesis parameters for characters
Voice configuration determines the experience of the character’s voice responses that users can hear when engaging in dialogue with the character using voice synthesis. You can choose a voice that closely resembles the character’s.
Voice Engine
The voice engine is the service provider that offers voice synthesis functionality. Currently, LobeVidol integrates the voice synthesis capabilities of Edge, while other voice service engines have not yet been integrated.
Language
The languages available for voice synthesis may vary depending on the different voice engines. Currently, several mainstream languages are supported. If you need additional languages, please contact us for inclusion.
Voice
Different combinations of voice synthesis engines and languages will produce varying voice effects. You can experiment with different combinations based on your needs and preferences to find the voice that suits you best. For example, in the Chinese language, you can choose from the following voices:
Speech Rate
The range is from 0 to 3. When the speech rate is set to 0, the voice synthesis is at its slowest; when set to 3, it is at its fastest. The default value is 1, which represents a moderate speed. You can adjust the speech rate according to your needs, such as slowing it down for better clarity when learning a language, or speeding it up for efficient information browsing.
Pitch
The range is from 0 to 2. The pitch affects the tone and emotional expression of the voice. The default value is 1, which represents a medium pitch. Users can adjust the pitch according to their preferences; a higher pitch may make the voice sound more lively and cheerful, while a lower pitch may convey a more calm and serious tone.
Preview
The preview feature allows you to listen to the voice effects under different languages, engines, and parameter settings before making a selection. This can help you better understand the characteristics of various options, enabling you to make a more suitable choice. The preview scripts will vary based on the language, ensuring that you can hear voice samples that match your desired language.