TLDR Tech / AI
Qwen3.5-Omni: Scaling Up, Toward Native Omni-Modal AGI
Qwen3.5-Omni is a comprehensive omnimodal large language model capable of understanding text, images, audio, and audio-visual content. It can process over 10 hours of audio and more than 400 seconds of 720P audio-visual input at 1 FPS. Trained on vast amounts of data, it supports speech recognition in 113 languages and dialects, and speech generation in 36 languages and dialects.
Read the full story