Google makes Gemini Omni 1.2 Flash generally available

Google DeepMind announced Gemini Omni 1.2 Flash on Thursday. The model is generally available through the Gemini API and Gemini for business. 720p video costs $0.07 per second, 30% less than Omni 1.1. This is the first time any Gemini Omni model has reached general availability. Google says the release comes with Google Cloud's enterprise infrastructure, Provisioned Throughput and SynthID watermarking on every output.

As we reported earlier, Omni 1.1 Flash pushed video length further. Version 1.2 raises the native generation and editing limit to 15 seconds, up from 10, and lets users set duration in one-second steps from 3 to 15 seconds.

Multi-turn conversational editing is the main workflow change. Users can change a product, background, lighting or aspect ratio on a full 15-second clip without generating it again. Google pitches a cost-saving loop: draft at 360p or 720p, fix details with follow-up edits, then upscale the best clips to 1080p or 4K.

Google also lists these improvements:

• References: better adherence to character, product and style images, motion clips up to three seconds, and audio cues
• Consistency: less drift between first and last frames
• Speech: more natural dialogue and lip-sync, with conditioning for multiple speakers
• Camera: fewer unwanted jump cuts during complex camera moves

Google backs these claims with demos, not published benchmarks. It says work is still ongoing on fast sports action, rapid script changes and complex physics. The model is rolling out to Google AI Studio, the Google Cloud console, Flow and Google Vids.