Google Gemini Omni 1.2 Flash Launched With Support for Clips Up to 15 Seconds Long

Google DeepMind has introduced Gemini Omni 1.2 Flash. This latest video generation model introduces native 15-second video creation and new editing capabilities. Google says the new model brings a 30 percent price reduction compared to Gemini Omni 1.1. It lets users draft content at 360p or 720p for just $0.07 per second. It supports generating and editing continuous video clips up to 15 seconds long and enables Conversational Editing.

Google Announced Gemini Omni 1.2 Flash

Google announced the rollout of Gemini Omni 1.2 Flash through a blog post on Thursday. Developers can access the model through the Gemini API and start using Google AI Studio. The company has also made it available to enterprise customers through Google Cloud.

The Gemini Omni 1.2 Flash is priced at $0.07 (roughly Rs. 6) per second for 720p video generation, representing a 30 percent reduction over Gemini Omni 1.1. Google says users can generate videos at 360p or 720p, with a follow-up edit instead of re-generating the entire clip, and then upscale to 1080p or 4K.

The Gemini Omni 1.2 Flash lets users generate and edit videos natively up to 15 seconds long. For comparison, the Gemini Omni 1.1 Supported video generation of up to 10 seconds. Users can specify the duration in one-second increments, from three seconds to 15 seconds. The new model also allows creators to guide generation by combining character, product, or style images, short motion clips of up to three seconds, and audio cues. It is designed to keep Faces, garments, packaging typography, and brand colours consistent across camera angles.

Gemini Omni 1.2 Flash is claimed to offer better consistency across frames. It allows users to swap a product or background, change the lighting or weather, or switch the aspect ratio instead of generating an entirely new video to make changes. Multi-turn conversational editing also works with videos of up to 15 seconds, allowing creators to produce multiple versions of advertisements without starting from scratch.

Google has additionally improved the model's audio generation capabilities. Gemini Omni 1.2 Flash is claimed to produce more natural-sounding dialogue, fluid, natural-sounding dialogue, clearer lip-sync, and distinct multi-speaker conditioning. These improvements are expected to benefit users creating videos through Flow, Gemini for business, and Google Vids. The model also supports complex camera movements, including FPV-style flythroughs, zoom-outs, and orbital shots.

Google says the Gemini Omni 1.2 Flash is designed for developers, businesses, and content creators who need to produce videos at scale. Developers can start using the model through Google AI Studio and the Gemini API documentation. Enterprise customers can access it through the Google Cloud console. Google confirmed that users can explore its video generation capabilities through Google's applications as the rollout expands.