GlmVoiceDialogueTurn

Models & Types · AiDotNet.TextToSpeech.MultiModal

One conversational turn for GLM-4-Voice’s supervised fine-tuning (§4.2): the user’s speech or text, and the reply’s text and speech tokens.

Constructors

Constructor Summary
GlmVoiceDialogueTurn()

Properties

Property Summary
int[] ResponseSpeechTokens { get; set; } The reply’s speech tokens (A_s).
int[] UserSpeechTokens { get; set; } The user’s speech tokens (Q_s); when null, UserText is the input.
string ResponseText { get; set; } The reply’s text (A_t).
string UserText { get; set; } The user’s text (Q_t), used when there are no speech tokens.