Gemini Omni Flash Preview Released for Video Generation and Conversational Editing via API
English summary
Google has released a preview of Gemini Omni Flash (gemini-omni-flash-preview) to developers via the Gemini API and Google AI Studio. The model natively supports high-quality video generation and conversational editing from combinations of text, image, and video inputs. No further details on performance, pricing, or wider availability were provided.
Chinese summary
谷歌通过 Gemini API 和 Google AI Studio 向开发者发布了 Gemini Omni Flash 预览版（gemini-omni-flash-preview）。该模型原生支持从文本、图像和视频输入组合生成高质量视频，并提供对话式编辑功能。公告中未提供有关性能、定价或更广泛可用性的进一步细节。
Key points
Gemini Omni Flash preview (gemini-omni-flash-preview) is now available via Gemini API and Google AI Studio.
Gemini Omni Flash 预览版（gemini-omni-flash-preview）现已通过 Gemini API 和 Google AI Studio 提供。
The model natively supports high-quality video generation and conversational editing from text, image, and video inputs.
该模型原生支持从文本、图像和视频输入生成高质量视频，并结合对话式编辑。
No specific performance benchmarks, pricing, or release timeline were mentioned in the announcement.
公告中未提及具体的性能基准、定价或发布时间表。