Alibaba Qwen launches the Qwen3.5-Omni full-modal model, supporting 113 speech recognition languages

Gate News message, March 30, Alibaba Qianwen announced the launch of the all-modal large model Qwen3.5-Omni. This series includes Instruct versions in three sizes: Plus, Flash, and Light. It supports a 256k long context window. The model supports audio input of more than 10 hours and video-and-audio input of over 400 seconds of 720P (1FPS). The model is natively multimodal pre-trained on large-scale text, vision, and more than 100 million hours of video-and-audio data, demonstrating outstanding all-modal perception and generation capabilities. Compared with the previous-generation Qwen3-Omni, Qwen3.5-Omni has greatly improved multilingual capabilities, enabling speech recognition in 113 languages and dialects and speech generation in 36 languages and dialects.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments