Description
Video workflows in ComfyUI mean leaving to generate voiceovers elsewhere. ComfyUI-FL-Qwen3TTS brings Qwen3-TTS speech synthesis into ComfyUI as nodes, keeping narration in the workflow.
It supports voice cloning, voice design and a fine-tuning UI, cloning a voice from seconds of audio.
TTS:Qwen3-TTS.
Cloning:Seconds of audio.
Voice design:From descriptions.
Fine-tuning:Custom voices.
It supports voice cloning, voice design and a fine-tuning UI, cloning a voice from seconds of audio.
Features
TTS:Qwen3-TTS.
Cloning:Seconds of audio.
Voice design:From descriptions.
Fine-tuning:Custom voices.
