@misc{arxiv_2609_16514v1,
  title = {The Evolving Bottleneck in Speech Generation: Interface Co-design and Staged Alignment from CosyVoice to Qwen-Audio-3.0-TTS},
  author = {{Qian Chen} and {Xiangang Li} and {Xiang Lv} and {Han Zhao} and {Tianyu Zhao}},
  eprint = {2609.16514v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.16514v1}
}