Qwen3.8-Omni-Flash: Qwen's multimodal model for long-horizon agent tasks
Omni-modal models are shifting from perception demos to executing multi-step agent work on audio and video, a capability most Western agent stacks still lack. Builders can plug Qwen-MM-Plugins into existing harnesses or use Qwen-Live-Harness for real-time pipelines without building memory and tool routing from scratch. As an open release from Alibaba (Qwen), it gives developers in Southeast Asia and beyond a free alternative to closed multimodal APIs.
The Qwen Team released Qwen3.8-Omni-Flash, a natively multimodal model trained for long-horizon agent tasks across text, audio and video, including video editing and long-form audio and video translation.
The model uses the sparse mixture-of-experts design of Qwen3.8-Next with a one million token context window.
A co-training strategy preserves text performance while transferring agent skills to audio and video work.It ships with two open-source frameworks: Qwen-MM-Plugins, which adds audio and video support to existing agent harnesses, and Qwen-Live-Harness, which handles real-time multimodal interaction with context and memory management, tool use and sub-agent delegation.
The era of omni agents is upon us.
This is a great report by the Qwen Team on their omni-modal agents.
They present Qwen3.8-Omni-Flash, a natively multimodal model trained for long-horizon agent tasks across text, audio, and video, such as video editing and long-form audio and video translation.
It uses the sparse mixture-of-experts design of Qwen3.8-Next with a context window of one million tokens. A co-training strategy keeps text performance while carrying agent skills over to audio and video tasks.
Two open-source frameworks come with it. Qwen-MM-Plugins adds audio and video support to existing agent harnesses, and Qwen-Live-Harness handles real-time multimodal interaction with context and memory management, tool use, and sub-agent delegation.
Paper: https://t.co/PxFrmGby1t
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Qwen3.8-Omni-Flash, Qwen, open-source models, multimodal.
Source attribution: curated from DAIR.AI (@dair_ai).
