Alibaba’s Qwen-Audio 3.1 launch expands its audio-model lineup with Qwen-Audio-3.1-TTS, a speech synthesis model that Qwen presents as giving developers more control over how generated voices sound and behave. Traditional text-to-speech systems generally work from a relatively simple instruction: provide text, select a voice, and generate speech. Qwen-Audio-3.1-TTS takes a more controllable approach, allowing users […]
English