Google makes Gemini Omni 1.2 Flash generally available with longer clips and lower pricing

Google released Gemini Omni 1.2 Flash to general availability on November 5, 2026, extending native video generation to 15 seconds, adding multi-turn conversational editing, and cutting 720p pricing by 30% to roughly $0.07 per second. The update matters for production teams because the longer runtime fits complete social ads and product explainers into a single generation, while the editing tools allow targeted revisions without starting from scratch.

The model generates synchronized video and native audio from text, image, and video inputs. Developer documentation supports whole-second durations from 3 to 15 seconds, compared with a 10-second maximum in the previous version, with 10 seconds as the default. Output defaults to 720p at 16:9 landscape, though 9:16 portrait is also supported. Teams can draft at 360p or 720p and upscale selected results to 1080p or 4K.

Conversational editing and multi-turn context

Conversational editing lets users replace a product or background, alter lighting or weather, or switch aspect ratio while preserving unmentioned elements. A previous-interaction identifier maintains context between API requests, so the prior video does not need to be uploaded again. Each request can use up to six reference images, including up to three images per character for a maximum of two characters.

Video extension operates separately from native generation. It appends 3 to 10 seconds per turn, using the final 10 seconds as context, up to a 30-second total. The feature cannot prepend footage or insert material mid-clip, and first-to-last-frame interpolation remains limited to outputs of 3 to 10 seconds.

Pricing and migration timeline

On the paid Gemini API, pricing sits at $12 per million video-output tokens, metered at 5,792 tokens per second of 720p video. That works out to approximately $0.70 for a 10-second clip and $1.04 for 15 seconds. Text, image, and video input costs $1.50 per million tokens. The model is not available on the free tier.

Gemini Omni 1.1 Flash remains available during a four-week transition. On December 3, 2026, API requests to 1.1 will automatically route to 1.2 without code changes and adopt the lower 1.2 rates. Existing integrations get a defined migration date with no immediate rewrite required.

Quality claims and known limits

Google said the update better preserves faces, garments, packaging typography, and brand colors across camera angles and transitions, with less visual drift or morphing. It also delivers clearer lip-sync, more natural dialogue, distinct conditioning for multiple speakers, and continuous camera movement with fewer unwanted jump cuts.

Google DeepMind's side-by-side evaluations give Omni 1.2 a 62% visual-consistency win rate against 38% for Omni 1.1 in text-to-video testing. The reference-to-video comparison shows a 63% multi-reference identity-consistency win rate for 1.2 against 37%.

Explicit technical limits remain. Development continues on fast sports action, rapid script changes, and complex physics. The API fully supports English but has not evaluated other languages. Voice editing, uploaded audio inputs, and audio references are unsupported in the current API. Generation time varies with duration, resolution, and API load, and safety filters apply to both prompts and generated video. Every video generated through the API carries an invisible SynthID watermark detectable programmatically for provenance verification.

Production access and early adoption

Developers can prototype in Google AI Studio and use the paid Gemini API. The broader rollout covers Flow for scene direction and multi-turn edits, longer clips in Google Vids at no additional cost with a Google account or Workspace subscription, a Gemini app rollout to Google AI Ultra subscribers, and campaign creation in Google Ads.

Photoroom chief executive Matt Rouif said the longer generation limit was a top user request and that general availability with service-level agreements would let the company rely on Gemini Omni Flash in production for sellers and enterprise customers. The model powers Photoroom's Video Ad Maker and Product Animator.

Google Cloud's general-availability announcement adds console and API access, enterprise infrastructure and security, and Provisioned Throughput, with audio references gated behind allowlisting. The release ties lower pricing to a changed production loop: targeted revisions can replace full regenerations, and higher-resolution rendering can be reserved for selected outputs.

Why this matters for marketing and creative teams

The 15-second ceiling and conversational editing change the production economics. Instead of regenerating an entire clip to fix a product color or background, teams can issue a targeted edit and keep everything else intact. That makes the 30% price cut meaningful only if the consistency gains hold up in practice - because preserving characters, products, and scenes across revisions is what makes iterative editing a practical alternative to starting over. For teams building text to video AI courses or ad creative workflows, the SynthID watermarking also provides a built-in provenance layer that matters for client delivery and platform compliance.