Overview
- Google and DeepMind officially launched Gemini Omni 1.2 Flash on Nov. 5–6, rolling the model into the Gemini API, Gemini for Business and consumer channels.
- Omni 1.2 raises native clip length from 10 seconds to up to 15 seconds, with duration selectable in one‑second steps between 3 and 15 seconds.
- The model adds multi‑turn conversational editing, improved reference following to keep faces, clothing and branding consistent across shots, better lip‑sync and multi‑speaker control, and film‑style camera motion controls.
- Pricing is roughly 30% lower than Omni 1.1, with 720p generation priced at $0.07 per second, and Google recommends a draft-edit-upscale workflow (360/720p drafting, finalize to 1080p/4K) to cut production costs.
- Google opened access across Google AI Studio, Cloud console, Flow, Google Vids and a phased Gemini App rollout, and early third‑party reports place Omni 1.2 near the top of several video‑generation and editing leaderboards, signaling a shift in competition toward duration, editability and cost for commercial video use.