【#Tech24H】On December 24, Alibaba upgraded its voice model family, Qwen3-TTS, releasing two new models: Qwen3-TTS-VD (VoiceDesign) for voice creation and Qwen3-TTS-VC (VoiceClone) for voice cloning. The new Qwen3-TTS models enable DIY voice design and pixel-level voice imitation, even allowing animals to “speak” human language naturally. With natural timbre, stable performance, and efficient generation, these models can accelerate the adoption of large voice models in professional fields such as audiobooks, AI-generated comic series, and film and television dubbing.