Model Releases

Gemini Omni multimodal AI model launched

Original title:Introducing Gemini Omni

AI summary

Google launched Gemini Omni, a native multimodal AI model that can integrate multiple inputs such as video, images, audio, and text to generate high-quality video content. Its core capability is video editing through natural language conversation, while maintaining character consistency, physical laws, and scene coherence. The first model, Gemini Omni Flash, is now available, with image and audio output to follow. Gemini Omni combines intuitive understanding of the physical world with a rich knowledge base, supports creative generation from realistic to narrative, and enables continuous video editing through multi-turn conversations without losing the original scene context.

Key Takeaways

  • Google launched Gemini Omni,a native multimodal AI model that can integrate multiple inputs such…
  • Its core capability is video editing through natural language conversation,while maintaining…
  • The first model,Gemini Omni Flash,is now available,with image and audio output to follow.
  • Gemini Omni combines intuitive understanding of the physical world with a rich knowledge…

Quick Facts

Published
Updated
Source
Google DeepMind:Blog(RSS)
Category
Model Releases
AI score
83
Read the original Read the full article at the original source
Why it matters

Gemini Omni 把视频生成从画面堆砌推到了物理世界叙事,多轮自然语言编辑和世界知识融合是真正的代际升级,做视频内容的该重新理解工具的定义了。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Gemini Omni multimodal AI model launched. May 18, 2026. https://new.nat6.net/en/news/cmpcxg3ae00yzsljlcn3lr3hf/

View all →