MoshiVariant
Enums · AiDotNet.TextToSpeech.MultiModal
The delay between Moshi’s text and audio streams (§3.4.4, App. C).
Fields
| Field | Summary |
|---|---|
MoshiVariant Asr |
The streaming ASR model: the text TextAudioDelaySeconds behind the audio, so the audio dictates the text. |
MoshiVariant Dialogue |
The dialogue model: text and audio aligned (delay 0), acoustic delay τ. |
MoshiVariant Tts |
The streaming TTS model: the audio TextAudioDelaySeconds behind the text, so the text dictates the speech. |
int value__ |