News in Short

• Google Gemini Omni 1.2 Flash can generate and edit AI video clips up to 15 seconds long.
• The model supports 360p and 720p generation, with pricing starting at $0.07 per second for 720p.
• Google says the new model costs 30 percent less than Gemini Omni 1.1.
• Conversational editing lets users refine clips without generating the entire video again.
• Developers can access the model through the Gemini API and Google AI Studio.

Google has launched Gemini Omni 1.2 Flash, its latest AI video generation model. The update raises the maximum video length to 15 seconds and adds more flexible editing tools. It also reduces generation costs compared with the previous version.

Gemini Omni 1.2 Flash targets developers, businesses and content creators who need to create videos at scale. Google says users can generate clips at 360p or 720p. The model also supports conversational edits, so creators can change parts of a video instead of starting over.

Gemini Omni 1.2 Flash supports 15-second AI videos

The new model can generate continuous video clips of up to 15 seconds. Gemini Omni 1.1 Flash supported clips of up to 10 seconds. Users can now set the duration in one-second increments, from three seconds to 15 seconds.

Google says creators can guide video generation with a combination of reference images, short motion clips and audio cues. The model can use character, product or style images, along with motion references of up to three seconds. This helps maintain consistency in faces, clothing, packaging text and brand colours across different camera angles.

Google cuts Gemini Omni 1.2 Flash video generation costs

Gemini Omni 1.2 Flash is priced at $0.07 per second for 720p video generation. That works out to roughly Rs. 6 per second. Google says the new pricing represents a 30 percent reduction compared with Gemini Omni 1.1.

Users can generate videos at 360p or 720p and then upscale the results to 1080p or 4K. The lower entry cost could make repeated drafts and creative testing more accessible. However, the final cost will depend on the duration and resolution of the generated video.

Conversational editing can change videos without starting over

One of the main additions is multi-turn conversational editing. Creators can ask the model to make targeted changes to an existing clip. These edits can include replacing a product or background, changing lighting or weather, and switching the aspect ratio.

Gemini Omni 1.2 Flash aims to preserve the rest of the video while applying the requested changes. This can help creators produce multiple versions of an advertisement without rebuilding every scene. Google also says the model offers better consistency across frames.

The update also improves audio generation. Google says it delivers more natural dialogue, clearer lip-sync and distinct multi-speaker conditioning. The model supports complex camera movements, including FPV-style flythroughs, zoom-outs and orbital shots.

Gemini Omni 1.2 Flash availability and supported tools

Developers can access Gemini Omni 1.2 Flash through the Gemini API and Google AI Studio. Google has also made the model available to enterprise customers through Google Cloud. The company says its video generation capabilities are also coming to supported Google applications, including Flow, Gemini for business and Google Vids.

The update builds on Google’s earlier Gemini Omni 1.1 Flash launch. With longer clips, lower generation costs and conversational editing, the new version focuses on making AI video production more flexible for professional workflows.

Google has shared the rollout and technical details in its official Gemini Omni 1.2 Flash announcement.