Google Launches Gemini Omni 1.2: 15-Second Videos and 30% Cost Reduction

Key Takeaways

1Gemini Omni 1.2 Flash is now generally available, supported by Google Cloud

2Video generation reaches 15 seconds, with multi-turn editing and fine-tuning options

3Google announces a 30% cost reduction and improved result consistency

Why it matters : This update expands the professional use cases for AI video generation, with immediate access across multiple Google products.

Gemini Omni 1.2 Flash is now generally available, backed by Google Cloud's infrastructure. The update is rolling out today across the API, Google Vids, the Gemini app, and other products, featuring clips up to 15 seconds long and multi-turn editing. Google also announces a 30% cost reduction and improved consistency in results.

General Availability and Access in Google Products

Gemini Omni is now available to everyone, supported by Google Cloud's enterprise-level infrastructure and security. Users can access the update starting today as it rolls out across Google's products and development platforms. Features are accessible via the Gemini API, Google Vids, and Gemini for businesses. In Google Vids, users can generate 15-second clips at no additional cost with a Google account or Google Workspace subscription. In the Gemini app, the creation of 15-second videos is being rolled out for Google AI Ultra subscribers, and scenes as well as multi-turn edits can be managed in Flow. Video campaigns can be developed in Google Ads. For developers, prototyping is possible in Google AI Studio, with interactive starter applications and documentation that includes pricing. Businesses can try the tool through the Google Cloud console and build solutions with the API.

Extended to 15 Seconds and Finer Duration Adjustments

Video generation now extends to 15 seconds, up from 10 seconds with Omni 1.1. Users can select the duration in one-second increments, between 3 and 15 seconds. Multi-turn conversational editing applies to complete 15-second clips, aligning editing capabilities with the new maximum length.

Le brief IA que lisent les pros

Le brief IA que les pros lisent chaque soir

Les 7 actus IA du jour, décryptées en 5 min. Gratuit.

Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.

Choisissez votre rythme

Gratuit · Pas de spam · Désabonnement en 1 clic

Better Adherence to References and Increased Creative Control

Generation can be guided from images of characters, products, or styles, short motion clips up to three seconds, and audio cues. Reference elements, such as faces, outfits, packaging fonts, or brand colors, remain consistent throughout the sequence and across different shots, while limiting drift or transformation. Complex and continuous camera movements, such as FPV flyovers or accentuated zooms, become easier to control with fewer unwanted cuts, ensuring a sharper output. Sequences with dialogue benefit from smoother speech, improved lip-syncing, and clear differentiation between multiple speakers.

Multi-Turn Editing and Cost Promises

Conversational editing allows users to refine the same clip turn by turn without starting from scratch, for example, by changing the product, background, lighting, weather, or aspect ratio. Google highlights the facilitated production of advertising variants for different audiences and locations without rephrasing or regeneration. The company announces a 30% cost reduction and claims better consistency for professional projects. According to Google, companies, startups, and creators are already integrating this tool into their workflows, with the company presenting it as designed for large-scale video productions. Development efforts continue to optimize scenarios such as fast sports movements, instant script changes, and the management of complex physical phenomena. The arrival of Gemini Omni 1.2 Flash marks this new milestone.