Heads up: statuses are automated heuristics from commit dates, registry metadata and issue titles. "Stale" can mean "finished and stable"; "Error spike" means error-titled issues are unusually high for that pack lately — worth checking recent issues, not a verdict that it is broken. Always check the repo.

Qwen3-TTS - Voice Synthesis & Cloning Active

ComfyUI custom nodes for speech synthesis, voice cloning, and voice design based on Qwen3-TTS

Why: last commit 27 days ago

Repo	flybirdxx/ComfyUI-Qwen-TTS (default branch main)
Registry	qwen3-tts-comfyui · publisher flybirdxx · latest 1.0.7 (2026-04-11) · in Manager list: no
Popularity	rank #218 · 60,443 downloads · 1937 stars
Tags	Audio Loaders, quantization & speed Generic / any
Star velocity	collecting (nightly snapshots started 2026-10-19)
Error issues	1 error-titled issues opened in last 30 days (open+closed) · 1.65 per 100K downloads · baseline 1.0/month over prior 6 months (6 total) · 1.0× baseline (Error spike needs ≥3, ≥2× baseline, ≥0.5 per 100K)
Last commit	2026-09-22 (27 days ago)
Open issues	60 issues, 1 PRs (fetched 2026-10-19)
pyproject.toml	present · version 1.0.7 · requires-comfyui — · frontend — · requires-python >=3.9 · 10 deps
Registry ComfyUI req.

Error-titled issues, last 30 days

transformers 4.57.3 is broken by the v5 mask shim (create_causal_mask TypeError), and fine-tuning rejects any non-24 kHz audio 2026-09-19 · open

Open issues mentioning errors / breakage

#108 transformers 4.57.3 is broken by the v5 mask shim (create_causal_mask TypeError), and fine-tuning rejects any non-24 kHz audio 2026-09-19
#104 ❌ [Qwen3-TTS] Critical Import Error: No module named 'librosa' 2026-09-15
#97 Transformers 5.8.1 incompatibility 2026-06-13
#91 extra_model_paths.yaml doesn't work ? 2026-05-14
#85 RuntimeError: ❌ [Qwen3-TTS] Model class is not loaded because the 'qwen_tts' package failed to import. Please check the ComfyUI console for the detailed 'Critic 2026-03-27
#77 Generation failed: cannot access local variable 'parent' where it is not associated with a value 2026-02-24
#73 ❌ [Qwen3-TTS] Model class is not loaded because the 'qwen_tts' package failed to import. Please check the ComfyUI console for the detailed 'Critical Import Erro 2026-02-13
#72 Error : Invalid audio data generated 2026-02-09
#67 FB_Qwen3TTSVoiceDesign ❌ [Qwen3-TTS] Model class is not loaded because the 'qwen_tts' package failed to import. Please check the ComfyUI console for the detaile 2026-02-04
#65 RoM 7.2 and Pytorch 2-10 incompatibilty 2026-02-04
#55 一直报错：Generation failed: Expected size for first two dimensions of batch2 tensor to be: [16, 127] but got: [16, 1]. 2026-01-28
#35 Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory F:\ComfyUI_windows_portable\Com 2026-01-25
#26 ❌ [Qwen3-TTS] Model class is not loaded because the 'qwen_tts' package failed to import. Please check the ComfyUI console for the detailed 'Critical Import Erro 2026-01-24
#23 Error Nodo Voice Clone 2026-01-24
#5 Got 'docstring' error when loading by ComfyUI 2026-01-24

Recent commits

2026-09-22 [main] Merge pull request #109 from JWLHS/codex/xpu-adaptation
2026-09-20 [main] XPU support + training-node options and bug fixes
2026-09-18 [main] Merge pull request #106 from flybirdxx/symphony/issue-105-c66bdad6
2026-09-18 [main] ⚠️ [Qwen3-TTS] Failed with sdpa, falling back to default attention: CUDA error: no kernel image is available for execution on the device
2026-09-06 [main] Merge pull request #102 from Pililink/fix/leading-break-pause