Google releases Gemini Omni 1.2 Flash with 15-second video clips at $0.07 per second

The update introduces multi-turn conversational editing across full 15-second clips, allowing users to swap backgrounds, lighting, products, or aspect ratios without regenerating from scratch. Google says reference adherence has improved: faces, garments, packaging text, and brand colors stay consistent across camera angles using character images, product photos, motion clips up to three seconds, and audio cues. Speech synthesis now handles more natural dialogue with clearer lip-sync and distinct multi-speaker conditioning. Camera control supports continuous FPV flythroughs, zoom-outs, and orbits with fewer unwanted jump cuts. Google acknowledges that fast sports action, rapid script changes, and complex physics still need work, and no benchmark scores for version 1.2 have been published.

Reporting is consistent across sources on specifications, pricing, and availability. The Decoder and Digital Trends emphasize the conversational editing workflow as a cost-saving feature, while Marktechpost notes that audio references remain allowlist-gated on Google Cloud and that earlier Arena rankings predate this release. Early partner feedback cited by Google includes positive comments from invideo and QuickFrame AI.