
【#Tech24H】On March 30, Alibaba's Qwen announced the release of its full-modal large model, Qwen3.5-Omni. The Qwen3.5-Omni series includes Instruct versions in three sizes: Plus, Flash, and Light, supporting a long context of 256k tokens. The model can handle over 10 hours of audio input and more than 400 seconds of 720P (1 FPS) audio-video input. Qwen3.5-Omni supports speech recognition in 113 languages and dialects and speech generation in 36 languages and dialects. It is currently available for trial via Offline API and Realtime API.
