CSM Text-to-Speech with Context

CSMTextToSpeechWithContext

Pack: ComfyUI-CSM-Nodes

custom_nodes.ComfyUI-CSM-Nodes

Inputs (11)

Name	Type	Required
text	STRING	required
model_path	STRING	required
tokenizer_path	STRING	required
sample_rate	INT	required
audio_context	AUDIO	required
context_transcription	STRING	required
context_speaker	INT	required
speaker	INT	optional
max_audio_length_ms	FLOAT	optional
temperature	FLOAT	optional
topk	INT	optional

Outputs (1)

Name	Type
audio	AUDIO