ComfyUI-SopranoTTS

SopranoTTS

Generate speech from text. | Input | Type | Default | Description | |-------|------|---------|-------------| | model | SOPRANOMODEL | - | Model from SopranoLoader | | text | STRING | - | Text to synthesize | | temperature | FLOAT | 0.3 | Generation temperature (0.0-2.0) | | topp | FLOAT | 0.95 | Nucleus sampling parameter | | repetitionpenalty | FLOAT | 1.2 | Penalty for repeated tokens |

Audio/Tts · 1 Eingabe · 4 Parameter · 1 Ausgabe

SopranoTTSBatch

Process multiple texts (one per line) in a single batch. | Input | Type | Default | Description | |-------|------|---------|-------------| | texts | STRING | - | Multiple texts separated by newlines | | (other params same as SopranoTTS) | | | |

Audio/Tts · 1 Eingabe · 4 Parameter · 1 Ausgabe

SopranoTTSStream

Streaming generation with lower latency. Only works with lmdeploy backend. | Input | Type | Default | Description | |-------|------|---------|-------------| | chunksize | INT | 1 | Tokens per audio chunk | | (other params same as SopranoTTS) | | | |

Audio/Tts · 1 Eingabe · 5 Parameter · 1 Ausgabe