Google DeepMind 發表 Gemini Omni：全新原生全模態模型，實現超低延遲即時影音與語音互動
Original: Introducing Gemini Omni
Google DeepMind has officially unveiled its latest flagship AI model, "Gemini Omni." This model represents a major breakthrough by Google…
Google DeepMind 發表新一代「Gemini Omni」模型，採用原生端到端全模態架構，能同時處理並輸出文字、音訊與視覺資訊。該模型顯著降低了互動延遲，實現如同真人般的流暢對話與即時視訊引導，未來將深度整合至 Android 系統與 Google 生態系，並透過 API 開放給開發者。
Google DeepMind has officially unveiled its latest flagship AI model, "Gemini Omni." This model represents a major breakthrough by Google in the field of multimodal AI, designed to deliver a fully native, end-to-end omni-modal interactive experience.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Google DeepMind Blog →Summaries are AI-generated; the original article is authoritative.