Google DeepMind Launches Gemini Omni 1.2 Flash with 15-Second Video Generation and 30% Price Cut

• Google DeepMind released Gemini Omni 1.2 Flash on November 5, 2026, extending native video generation and editing from 10 seconds to 15 seconds.
• The model offers a 30% price reduction compared to Gemini Omni 1.1, costing $0.07 per second for 720p video, and is generally available on the Gemini API and Google Cloud.
• New features include multi-turn conversational editing, improved reference adherence for characters and products, and support for complex camera movements like FPV fly-throughs without jump cuts.
• Availability spans developer tools (Google AI Studio), enterprise platforms (Google Cloud), and consumer apps (Flow, Google Vids, Gemini app, and Google Ads).

Technical Capabilities

• Reference adherence allows combining character, product, style images, and short motion clips to maintain consistency in facial features, clothing, and brand colors across camera angle changes.
• Multi-turn editing enables modifications to background, lighting, and aspect ratio in 15-second clips without full regeneration, reducing costs.
• Speech and lip-sync improvements support multi-speaker conditioning and more natural dialogue, while camera work controls reduce unwanted jump cuts.

Limitations and Availability

• The model is still improving in fast sports action, rapid script changes, and complex physics simulations.
• Developers can prototype via Google AI Studio, while enterprises access it through the Google Cloud console and Vertex AI Studio.
• General users can generate 15-second clips in Google Vids at no additional cost with a Google account or Workspace subscription.