view post Post 4890 š Update: We release the technical report of MGM-Omni. Moreover, we introduce Long-TTS-Eval, a benchmark for long-form and complex case TTS evaluation.š Arxiv: https://arxiv.org/abs/2509.25131š benchmark: wcy1122/Long-TTS-Eval-------------------------š Introducing MGM-Omni, an omni-chatbot capable of processing text, image, video, and speech inputs, and can generate both text and speech responses.š MGM-Omni support hour-level audio understanding.š£ļø MGM-Omni support 10-minute speech generation and voice cloning.For more details, please check:š Blog: https://mgm-omni.notion.site/MGM-Omni-An-Open-source-Omni-Chatbot-2395728e0b0180149ac9f24683fc9907 š Code: https://github.com/dvlab-research/MGM-Omni š¤ Model: wcy1122/mgm-omni-6896075e97317a88825032e1 š® Demo: wcy1122/MGM-Omni See translation š 8 8 š„ 3 3 + Reply