松泉, 바라보기, 인생글, 좋은글, 취미생활

유용, Qwen3 TTS 사용법, 진행중

Songchoen 송천 2026. 4. 20. 16:09
728x90
반응형

 



경쾌하고 활기찬 어조로 말하다
50대 중저음 아나운서 어조로 말하다

 

speak in a cheerful and lively tone
speak in a low-to-mid-50s tone

 

신뢰감 있고 차분한 뉴스 앵커의 느낌입니다.

speak in a professional and calm tone
speak in a low-to-mid pitch tone


옵션 2. 무게감 있는 중저음 강조

울림이 깊고 권위 있는 목소리를 원할 때 적합합니다.

speak in a steady and authoritative tone
speak in a low-to-mid resonance tone


옵션 3. 지적이고 세련된 내레이션 톤

다큐멘터리나 격식 있는 프레젠테이션에 어울리는 톤입니다.

speak in a clear and polished tone
speak in a low-to-mid register tone

 

#클론한 보이스를 업로드하여 저장해두고 계속 쓴다.

 

 

 

 

 

 

 

 

 

 

https://github.com/QwenLM/Qwen3-TTS

 

GitHub - QwenLM/Qwen3-TTS: Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, support

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice...

github.com

 

 

#다운로드

https://huggingface.co/collections/Qwen/qwen3-tts

 

Qwen3-TTS - a Qwen Collection

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co

 

 

 

 

https://github.com/DarioFT/ComfyUI-Qwen3-TTS

 

GitHub - DarioFT/ComfyUI-Qwen3-TTS: A ComfyUI custom node suite for Qwen3-TTS, supporting 1.7B and 0.6B models, Custom Voice, Vo

A ComfyUI custom node suite for Qwen3-TTS, supporting 1.7B and 0.6B models, Custom Voice, Voice Design, Voice Cloning and Fine-Tuning. - DarioFT/ComfyUI-Qwen3-TTS

github.com

 

 

 

 

 

 

 

 

 

#결론...

짧은 문장은 잘된다.

20분 텍스트를 넣었더니 목소리가 섞인다.

긴 텍스트는 나누어서 하라고 한다. 하지만...잘 될지 모르겠다.

 

반응형