BREAKING
Qwen3-TTS Arrives in ComfyUI
0
Languages
0
Preset voices
0s
Max reference
Two Model Sizes
1.7BHigh quality
Best fidelity
More VRAM
0.6BLightweight
Lower resource use
Faster
How Voice Cloning Works
1Reference clip
2Whisper transcribe
3Clone voice
4Generate speech
Watch the Setup Limits
Cloning Meets Local Workflows
AI NEWS BLITZ
Alibaba's open-source Qwen3-TTS now runs inside ComfyUI with voice cloning.