A thousand questions release Qwen-Audio-3.0-TTS

Qwen announced: Today we officially release the large-scale voice synthesis model Qwen-Audio-3.0-TTS, which includes a Flash version for real-time interaction and a Plus version for high-quality generation. The new model has achieved systematic improvements in fine-grained label control, freestyle command compliance, multi-language and dialect coverage, and complex acoustic robustness, allowing synthesized speech to move from "being able to speak" to "being able to express".