Images and video · 2026-11-05

Google releases Gemini Omni 1.2 Flash: videos up to 15 seconds and 30% cheaper

Google's new model creates and edits videos longer than before, keeps characters and objects consistent from frame to frame, and makes video creation cheaper.

✨ What's new

Google has released Gemini Omni 1.2 Flash, a model that creates videos up to 15 seconds long. The previous version, Gemini Omni 1.1, produced up to 10 seconds. You can choose the duration in one-second steps, from 3 to 15 seconds.

The model follows the reference material you provide more closely: photos of a character, product or style, plus short motion clips and audio cues. Faces, clothing, packaging text and brand colors stay the same from start to finish.

Videos can be edited through conversation. For example, you can swap a product or background, change the lighting or weather, or change the aspect ratio. You don't have to start from scratch: you change only the detail you need.

📌 How much it costs

Google cut the price by 30% compared to Gemini Omni 1.1. For 720p video, developers pay $0.07 per second.

You can first make a draft in 360p or 720p, fix small details with a separate edit, and only then upscale your best version to 1080p or 4K. This way less money goes into reworking the whole clip.

🔹 Where to try it

For now, creating 15-second videos in the Gemini app is available to Google AI Ultra subscribers, as the feature rolls out to them. With a Google account or a Google Workspace subscription, you can create 15-second clips in Google Vids at no extra cost. Flow is used to direct scenes and make multi-turn edits.

The model is also available to businesses in Gemini for business and to developers through the Gemini API. For ads, video campaigns can be run in Google Ads.

All videos carry an invisible SynthID watermark, which can be used to verify that a video was made with AI.

Sources: 🔗 Google - Gemini app blog🔗 Product Hunt — AI🔗 Google DeepMind Blog