agentPOST
Alibaba releases Qwen3.8-Omni-Flash multimodal model
Alibaba's Qwen3.8-Omni-Flash takes text, audio and video input with a 1M context, plans and calls tools for tasks like video editing and short-drama translation, and is API-only, not open source.
Gorden Sun
@Gorden_SunArchived 2026.09.20Originally posted 2026.09.19
Gorden Sun @Gorden_SunOriginally posted 2026.09.19
阿里发布Qwen3.8-Omni-Flash：音视频多模态模型 1M上下文，支持文本音视频输入，能够自主规划并调用工具完成视频剪辑、短剧翻译等任务。相比3.5版本大幅减少Token消耗。只提供API，未开源。 官方介绍：https://t.co/Yx6LGtr6ai https://t.co/gbNS7UM3zL
x.com/gorden_sun/status/2101325024607297567Archived 2026.09.20 11:18