Alibaba Qwen3.5-Omni Launches with Native Audio Visual Vibe Coding

Mar 31, 2026 · Updated Apr 25, 2026

Alibaba Cloud's Tongyi Lab launched Qwen3.5-Omni, the latest generation of its foundation model series. This version is natively omni-modal, meaning it processes text, image, audio, and video inputs through a single, end-to-end architecture. It achieves state-of-the-art performance across all four modalities simultaneously.

The release marks a shift toward real-time, multi-sensory interaction. By integrating audio-visual understanding directly into the core model, Qwen3.5-Omni can perform complex tasks like automatic video segmentation and script generation that accounts for character relationships. It maintains high performance across all modalities while advancing real-time interaction.

You can now use Qwen3.5-Omni for workflows requiring fine-grained video analysis or real-time conversational agents. The standout Audio-Visual Vibe Coding feature introduces a multi-sensory approach to development. The model is available for online serving via the vLLM Python client, supporting query types for audio and video.

View the full update on qwen.ai

Qwen

@Alibaba_QwenMar 30

🚀 Qwen3.5-Omni is here! Scaling up to a native omni-modal AGI. Meet the next generation of Qwen, designed for native text, image, audio, and video understanding, with major advances in both intelligence and real-time interaction. A standout feature: 'Audio-Visual Vibe Coding'. https://t.co/6YOpqOFxG1

4083.2k

View on X