Qwen3.8-Omni-Flash
Omni model with a 1M-token context for audio and video agent tasks, such as editing and live conversation.
Qwen3.8-Omni-Flash connects text, image, audio, and video understanding with planning and tool use, bringing native omnimodal perception into audio-visual creation and real-time interaction.
Official source
Qwen3.8-Omni-Flash: Omni Senses. Agentic Delivery.qwen.ai · published