GlmVoiceTtsFormat
Enums · AiDotNet.TextToSpeech.MultiModal
How Synthesize reads a text aloud.
Fields
| Field | Summary |
|---|---|
GlmVoiceTtsFormat ForcedTextThoughts |
The paper’s speech-and-text-to-speech subtask (§3.3) on the chat model: the text as the user’s turn and as the assistant’s text, which is fed rather than generated; the model writes the speech tokens around it in the Generation layout. |
GlmVoiceTtsFormat InterleavedBase |
A base model’s text-to-speech in the published interleaved pre-training format (Zeng et al. |
int value__ |