指令式多语言TTS，流式延迟低至97ms，9音色
- 部署
-
- pip pip install qwen-tts && python -c 'from qwen_tts import Qwen3TTSModel; model=Qwen3TTSModel.from_pretrained("Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice", device_map="cuda:0")'
- py qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --ip 0.0.0.0 --port 8000
- py modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --local_dir ./local_model