Key Info
Qwen announced Qwen3.8-Omni-Flash, its first omni-modal model built around agentic capabilities, combining native audio-video understanding, reasoning, and tool use in one model.
Highlights
- Jointly reasons over what it sees and hears, then plans tasks and executes them with tools to deliver results.
- Handles long, multi-step workflows such as auto-editing vlogs, translating short videos, and turning movies into recaps.
- Designed for agent-style operation: understand the content, plan the task, execute with tools, and produce the final output.
