StepAudioSpeaker<T>

Models & Types · AiDotNet.TextToSpeech.MultiModal

A speaker Step-Audio’s TTS speaks as (the release’s speakers_info entry): the name, the prompt recording’s transcript and dual-codebook ids, its 22.05 kHz mel [frames, 80] and CAM++ x-vector.

Constructors

Constructor Summary
StepAudioSpeaker()

Properties

Property Summary
Tensor<T> Embedding { get; set; }
Tensor<T> PromptMel { get; set; }
int[] PromptCode { get; set; }
string Name { get; set; }
string PromptText { get; set; }