ComfyUI Node: Qwen3 TTS Voice Clone
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
Qwen3_TTS
Inputs
model QWEN_TTS_MODEL
text STRING
ref_audio AUDIO
ref_text STRING
language
- Auto
- Chinese
- English
- Japanese
- Korean
- German
- French
- Russian
- Portuguese
- Spanish
- Italian
seed INT
x_vector_only BOOLEAN
max_new_tokens INT
temperature FLOAT
top_p FLOAT
repetition_penalty FLOAT
Outputs
AUDIO
Extension: ComfyUI-QWEN3_TTS
Fast and efficient Text-to-Speech nodes for ComfyUI based on Qwen3-TTS.
Authored by PGCRT
Looking for a different node?
Also provided by 1 other extension
- Qwen3 TTS (Voice Clone) β Qwen3 Triton TTSQwen3-TTS-Triton
Qwen3-TTS voice cloning using qwen3-tts-triton. Provide a reference audio clip to clone its voice characteristics. Advanced generation and model parameters are in the optional inputs.
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.