Nodes/ComfyUI-GGUF-Loader/Qwen3-TTS Custom Voice ⚡
ComfyUI Node

Qwen3-TTS Custom Voice ⚡

Generate speech with a Qwen3-TTS CustomVoice model's built-in named speakers.

By ChrisColeTech·Created 13 days ago·Updated about 3 hours ago· 6
Qwen3-TTS Custom Voice ⚡
  • qwen_tts_model
  • AUDIO
textHello world
speakerDylan
languageAuto
seed0
max_new_tokens2048
top_p0.80
top_k20
temperature1.00
repetition_penalty1.05
instruct
custom_speaker_name
unload_model_after_generatefalse
Category🤖 CCTech/Qwen TTS

Inputs (13)

NameTypeDefaultDescription
qwen_tts_modelQWEN_TTS_MODEL
textSTRINGHello world
speakerCOMBODylan9 options: Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, +3
languageCOMBOAuto11 options: Auto, Chinese, English, Japanese, Korean, German, +5
seedINT00–18446744073709550000
max_new_tokensINT20481–32768
top_pFLOAT0.800–1
top_kINT200–500
temperatureFLOAT1.000–2
repetition_penaltyFLOAT1.050.5–5
instructoptSTRINGVoice-design instruction. Ignored by 0.6B CustomVoice checkpoints (upstream behavior).
custom_speaker_nameoptSTRINGOverrides speaker with any string - for a fine-tuned checkpoint's own speaker names.
unload_model_after_generateoptBOOLEANfalse

Outputs (1)

NameTypeDescription
AUDIOAUDIO