Glonce

Google's Gemini Omni 1.2 Flash goes GA with 15-second video clips and 30% lower price

modelsThe Glonce editorsThe Decoder🔥67Glonce rating67Impact60Novelty55Relevance100Surprise35Players85Credibility75
Google's Gemini Omni 1.2 Flash goes GA with 15-second video clips and 30% lower price

Google Deepmind is making its Gemini Omni 1.2 Flash video-generation model generally available. The updated model creates clips up to 15 seconds long, supports conversational editing, and costs 30 percent less than its predecessor, according to Google's announcement as reported by The Decoder.

Google says the model is rolling out through the Gemini API, Google AI Studio, the Google Cloud Console, Flow, Google Vids, the Gemini app for Google AI Ultra subscribers, and Google Ads. Every generated video carries an imperceptible SynthID watermark to indicate its origin.

Clips can now run between three and 15 seconds, up from a maximum of 10 seconds previously. Pricing drops 30 percent to $0.07 per second for 720p video.

The standout feature is what Google calls "Conversational Editing." Users can tweak a generated clip step by step, changing the background, lighting or aspect ratio without regenerating the entire clip. Google says this works across the full 15-second length. Paired with a tiered workflow, the feature is supposed to cut costs: drafts are first created at 360p or 720p, individual details are corrected with a follow-up edit, and only the final result is upscaled to 1080p or 4K.

Google also promises significantly better reference adherence. According to the announcement, the model can take character images, product photos, short motion clips of up to three seconds, and audio cues as inputs. Faces, clothing, packaging typography and brand colors are supposed to stay consistent across different camera angles. As an example, Google shows a virtual try-on clip: from a single model photo and product shots of three outfits, the model generates a 15-second sequence with 360-degree turns while preserving the model's identity and each garment's cut and drape.

Overall visual consistency is said to have improved too. Google says there is less visual drift or morphing across motion and camera transitions than with the predecessor.

Gemini Omni 1.2 Flash is also supposed to produce more fluid, natural-sounding dialogue with clearer lip-sync and the ability to distinguish between multiple speakers. The model handles complex, continuous camera movements such as FPV drone flights or dramatic zoom-outs, with significantly fewer unwanted jump cuts.

Key facts

  • Gemini Omni 1.2 Flash is going generally available; clips can now run between three and 15 seconds, up from a 10-second maximum.
  • Pricing drops 30 percent to $0.07 per second for 720p video.
  • "Conversational Editing" lets users change background, lighting or aspect ratio step by step without regenerating the clip; Google says it works across the full 15 seconds.
  • Inputs can include character images, product photos, motion clips of up to three seconds, and audio cues, with faces, clothing, packaging typography and brand colors supposed to stay consistent across camera angles.
  • It is rolling out in the Gemini API, Google AI Studio, Google Cloud Console, Flow, Google Vids, the Gemini app (Google AI Ultra subscribers) and Google Ads; every video carries a SynthID watermark.

Why it matters

Two practical limits of AI video move at once: clips get longer, from a 10-second maximum to 15 seconds, and the price per second falls 30 percent to $0.07 at 720p. The editing approach matters too. Instead of regenerating a whole clip to fix one detail, users can adjust background, lighting or aspect ratio in a running conversation. Google pairs this with a tiered workflow, drafting at 360p or 720p and upscaling only the final result to 1080p or 4K, which is supposed to cut costs.

Who it affects

Google lists the Gemini API, Google AI Studio and the Google Cloud Console, so developers and cloud customers are covered. Flow, Google Vids and Google Ads put the model in front of video creators and advertisers. The Gemini app gets it for Google AI Ultra subscribers. The product-photo inputs and the virtual try-on example point at brands and e-commerce teams that want consistent faces, garments, packaging typography and brand colors.

How to use it

Access runs through the Gemini API, Google AI Studio, the Google Cloud Console, Flow, Google Vids, Google Ads, or the Gemini app for Google AI Ultra subscribers. Inputs can be character images, product photos, short motion clips of up to three seconds, and audio cues. The suggested workflow: create drafts at 360p or 720p, fix individual details with follow-up edits in conversation, then upscale only the final result to 1080p or 4K. The only price given is $0.07 per second for 720p video.

How solid is it

The facts here come from Google's announcement as relayed by The Decoder. The quality claims are Google's own: better reference adherence, less visual drift or morphing than the predecessor, more natural dialogue with clearer lip-sync, and fewer unwanted jump cuts are all phrased as promises or as "supposed to." No independent benchmarks or third-party tests are cited. The price and clip-length figures are concrete and stated plainly.

Risks and caveats

No release date is given, and the predecessor is not named. The previous price in dollars is not stated, nor are prices for resolutions other than 720p, so the real cost of a finished 1080p or 4K clip cannot be worked out from the report. Consistency of faces, clothing and branding across camera angles is described as an intended outcome, and the virtual try-on clip is Google's own demonstration. Every generated video carries an imperceptible SynthID watermark to indicate its origin.

“Users can tweak a generated clip step by step, changing the background, lighting, or aspect ratio without regenerating the entire clip.”

— The Decoder, describing Google's "Conversational Editing" feature