On December 24, Ali upgraded the voice model family Qwen3-TTS and released two new models, Sound Creator Qwen3-TTS-VD and Sound Clone Qwen3-TTS-VC. The new QwEN3-TTS model enables DIY sound design and pixel-level sound imitation, and even allows animals to speak “natively”. The sound is natural, the effect is stable, and the generation is efficient, which can accelerate the implementation of large voice models in various professional fields such as audio novels, AI comics, and film and television dubbing.

On December 24, Ali upgraded the voice model family Qwen3-TTS and released two new models, Sound Creator Qwen3-TTS-VD and Sound Clone Qwen3-TTS-VC. The new QwEN3-TTS model enables DIY sound design and pixel-level sound imitation, and even allows animals to speak “natively”. The sound is natural, the effect is stable, and the generation is efficient, which can accelerate the implementation of large voice models in various professional fields such as audio novels, AI comics, and film and television dubbing.