{"slug":"qwen-2.5-omni","name":"Qwen-2.5-Omni","kind":"tool","kindLabel":"Tool","grade":null,"score":null,"tagline":"Vision-language-audio model with speech input and output plus document understanding.","description":"A vision-language-audio model with speech input and output, plus chart, document, and image understanding.","tags":["Voice","speech-to-text","text-to-speech","multimodal"],"url":"https://way.space/tool/qwen-2.5-omni","stars":"—","website":"https://huggingface.co/Qwen/Qwen2.5-Omni-7B"}