KokoroOptions
Options & Configuration · AiDotNet.TextToSpeech.EndToEnd
Options for Kokoro (lightweight StyleTTS2-inspired TTS with style tokens and ISTFTNet decoder).
Inheritance: ModelOptions → TtsModelOptions → EndToEndTtsOptions → KokoroOptions
For Beginners
These options configure the Kokoro model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
KokoroOptions() |
Initializes a new instance with default values. |
KokoroOptions(KokoroOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
bool UseNativeEnglishFallback { get; set; } |
Explicitly opts into the repository’s approximate English frontend. |
double Speed { get; set; } |
Duration scaling used by the released model: sum(sigmoid(duration logits)) / speed. |
int StyleDim { get; set; } |
Gets or sets the width of the style vector that conditions synthesis. |
int? SynthesisSeed { get; set; } |
Optional per-call seed for reproducible native excitation; null keeps the advancing random stream. |