Interface defining voice configuration settings for text-to-speech generation

interface VoiceSettings {
    similarity_boost: number;
    speed: number;
    stability: number;
    style: number;
    use_speaker_boost: boolean;
}

Properties

similarity_boost: number

Similarity boost to original voice (0-1), higher values make the voice more similar to the original

speed: number

Speed of speech (0-1), higher values result in faster speech

stability: number

Stability of the voice (0-1), higher values result in more consistent/stable voice output

style: number

Style parameter (0-1) affecting the speech style characteristics

use_speaker_boost: boolean

Whether to enhance speaker clarity and target voice characteristics