@@ -772,11 +772,12 @@ class ISettings(SerializableMixin):
772772 sparseStructure : Optional [Union [ISparseStructure , Dict [str , Any ]]] = None
773773 shapeSlat : Optional [Union [IShapeSlat , Dict [str , Any ]]] = None
774774 texSlat : Optional [Union [ITexSlat , Dict [str , Any ]]] = None
775- # Audio
775+ # Audio
776776 languageBoost : Optional [str ] = None
777777 turbo : Optional [bool ] = None
778- lyrics : Optional [str ] = None
779- guidanceType : Optional [str ] = None
778+ lyrics : Optional [str ] = None
779+ guidanceType : Optional [str ] = None
780+ textNormalization : Optional [bool ] = None
780781 # Video
781782 draft : Optional [bool ] = None
782783 audio : Optional [bool ] = None
@@ -1572,14 +1573,16 @@ class IAudioInference:
15721573 webhookURL : Optional [str ] = None
15731574 providerSettings : Optional [AudioProviderSettings ] = None
15741575 inputs : Optional [Union [IAudioInputs , Dict [str , Any ]]] = None
1575- speech : Optional [IAudioSpeech ] = None
1576+ speech : Optional [Union [ IAudioSpeech , Dict [ str , Any ]] ] = None
15761577 settings : Optional [Union [ISettings , Dict [str , Any ]]] = None
15771578
15781579 def __post_init__ (self ):
15791580 if self .settings is not None and isinstance (self .settings , dict ):
15801581 self .settings = ISettings (** self .settings )
15811582 if self .inputs is not None and isinstance (self .inputs , dict ):
15821583 self .inputs = IAudioInputs (** self .inputs )
1584+ if self .speech is not None and isinstance (self .speech , dict ):
1585+ self .speech = IAudioSpeech (** self .speech )
15831586
15841587
15851588@dataclass
0 commit comments