ComfyUI-QwenTTS
A clean, efficient ComfyUI custom node pack for Qwen3-TTS. It provides CustomVoice, VoiceDesign, and VoiceClone workflows with strict ComfyUI compatibility and practical controls for quality, speed, and stability.
Audio
Qwen3
TTS
Voice Cloning
1
64
https://github.com/1038lab/ComfyUI-QwenTTS
Features
Custom Voice TTS: Generate speech using preset speakers.
Voice Design: Create voices from natural-language descriptions.
Voice Clone: Clone voices from reference audio + transcript.
Multi-Device: CUDA / MPS / CPU with auto device selection.
Local-First Loading: Prioritize
ComfyUI/models/TTS/Qwen3-TTS/when available.Fine Controls: Sampling knobs and max tokens (Advanced nodes).
Model Overview (Qwen3-TTS)
Languages: Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian.
Instruction control: Supports voice style control via natural-language instructions.
Tokenizer: Uses Qwen3-TTS-Tokenizer-12Hz for speech encoding/decoding.
Read more
N