Qwen3.8-Omni-Flash targets long-horizon multimodal agent tasks
Shipping agent harnesses and plugins with the model means developers can wire real-time audio and video into existing frameworks without building the plumbing themselves. The one-million-token context window makes long-form video and audio workloads practical for teams building editors, translators or live assistants. Builders comparing open multimodal options against closed APIs should benchmark Qwen3.8-Omni-Flash's agent performance on their own tasks.
The Qwen Team released Qwen3.8-Omni-Flash, a natively multimodal model trained for long-horizon agent tasks spanning text, audio and video, including video editing and long-form audio and video translation.
It builds on the sparse mixture-of-experts design of Qwen3.8-Next and offers a context window of one million tokens.
A co-training strategy preserves text performance while transferring agent skills to audio and video tasks.Two open-source frameworks ship alongside it: 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.
A technical paper accompanies the release.
Era of the omni models is upon us.
This is a great report by the Qwen Team on their omni model.
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/PxFrmGc5R1
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, multimodal, agents.
Source attribution: curated from DAIR.AI (@dair_ai).
