# Hermoso: Gemini Omni 1.2 on Hermoso: 4–15s, 720p/1080p/4k, native sound > Machine-readable twin of https://hermoso.ai/models/gemini-omni-1-2/. Generated from the shipped page. Do not edit by hand. > Full agent guide: https://hermoso.ai/llms.txt · MCP: https://app.hermoso.ai/mcp [Models](https://hermoso.ai/models/) › [Video models](https://hermoso.ai/models/video/) # Gemini Omni 1.2 Newest Omni: sound included, up to 15s, up to six reference images Google · video model [Start free →](https://app.hermoso.ai/?src=model-gemini-omni-1-2#models/m/video:omni-1.2) **4–15s** clip length **4k** best resolution of 3 **Native sound** speech and world audio in the render **up to 6** reference images Gemini Omni 1.2 is one of 42 video models Hermoso can render a video ad, product sizzle or UGC clip with. Name it, or leave the model out and the router picks a sound default. The same catalog is available from the app, the [API](https://hermoso.ai/docs/api/), the [MCP server](https://hermoso.ai/mcp/) and the CLI, on one account and one credit balance; the exact price of every render is shown in the app before it runs. ## What people make with it - [UGC testimonials and talking creators](https://hermoso.ai/recipes/testimonial-video/) - [Product sizzles and packshot spins](https://hermoso.ai/recipes/orbit-360/) - [Cinematic brand films](https://hermoso.ai/recipes/cinematic/) - [Faceless product demos and explainers](https://hermoso.ai/recipes/explainer/) The linked formats are [creative recipes](https://hermoso.ai/recipes/) Hermoso plans and renders for your brand. ## About Google Google makes Veo, Gemini Omni, Imagen and the Nano Banana image models, strong on cinematic motion and text-accurate edits. ## Specs Lengths 4s 6s 8s 10s 12s 15s Longest single take 15s in one unbroken shot Resolutions 720p 1080p 4k Aspect ratios 9:16 16:9 Sound Native audio (can be switched off per render) Modes text to video, image to video, reference to video Reference images up to 6 per render in Hermoso (our fidelity cap, measured on paid renders; the model itself accepts more) Edit an existing video No Model id `omni-1.2` ## Where it fits Each aspect ratio Gemini Omni 1.2 renders maps to a placement: - **9:16** for Reels, TikTok, Shorts and Stories - **16:9** for YouTube, in-stream and display ## Gemini Omni 1.2 compared with other video models Model Lengths Top resolution Sound Refs **Gemini Omni 1.2** 4–15s 4k Native up to 6 [Veo 3.1 Fast](https://hermoso.ai/models/veo-3-1-fast/) 4–8s n/a Native up to 3 [Veo 3.1](https://hermoso.ai/models/veo-3-1/) 4–8s n/a Native up to 3 [Gemini Omni](https://hermoso.ai/models/gemini-omni/) 4–15s n/a Native up to 6 [Seedance Lite](https://hermoso.ai/models/seedance-lite/) 4–12s 1080p Silent n/a [Seedance 2.5 Draft](https://hermoso.ai/models/seedance-2-5-draft/) 4–30s 480p Native up to 9 [Hailuo 2.3](https://hermoso.ai/models/hailuo-2-3/) 6–10s n/a Silent n/a See [all 42 video models](https://hermoso.ai/models/video/) side by side. ## Just ask for it In Claude, ChatGPT, Cursor or any assistant connected to Hermoso, name the model in plain English. Or pick it from the model menu in the app. Make a 15 second UGC ad for our olive oil with Gemini Omni 1.2, kitchen at golden hour, 9:16. Render the packshot spin on Gemini Omni 1.2 and post it to TikTok and Reels. Redo yesterday's ad on Gemini Omni 1.2 with the new label. ## Getting the best out of Gemini Omni 1.2 - Describe one continuous camera move and where it ends. The model renders motion, not a shot list. - Attach the real product photo as a reference and ask for it matched exactly. Never describe a lookalike. - Name colours in words. A hex code turns into text on screen. - Keep spoken lines short. Roughly two words per second is what a clip can carry cleanly. - Ask for the placement's ratio up front (9:16 for Reels and TikTok) instead of cropping afterwards. Make a video ad with Gemini Omni 1.2. Start free with the full studio and up to 10 posts a month. [Start free →](https://app.hermoso.ai/?src=model-gemini-omni-1-2#models/m/video:omni-1.2) [See pricing](https://hermoso.ai/pricing) ## Frequently asked questions ### How long a video can Gemini Omni 1.2 make? Gemini Omni 1.2 renders clips from 4 to 15 seconds. Longer spots are built from several clips. ### Does Gemini Omni 1.2 make sound? Yes. Gemini Omni 1.2 renders native audio with the picture, so a talking creator or a voiceover is part of the same take. ### Can Gemini Omni 1.2 use my product photos? Yes. Attach up to 6 reference images of the product and Hermoso keeps the real product in the render. ### How much does Gemini Omni 1.2 cost? The exact credit price is shown in the app before every render and settled at cost. See pricing for what a credit is worth. ## Related video models Other Google models first, then the video models listed nearest to Gemini Omni 1.2 in the catalog. [Veo 3.1 Fast Faster · has audio 4–8s · native sound](https://hermoso.ai/models/veo-3-1-fast/)[Veo 3.1 Cinematic, with sound 4–8s · native sound](https://hermoso.ai/models/veo-3-1/)[Gemini Omni Fast and cheapest with sound. Start from text, an image or a video 4–15s · native sound](https://hermoso.ai/models/gemini-omni/)[Seedance Lite Fastest, cheapest video 4–12s · 720p / 480p / 1080p · silent](https://hermoso.ai/models/seedance-lite/)[Seedance 2.5 Draft A quick 480p draft of a Seedance 2.5 take at a fraction of the price; like it, then finish that same take at 1080p 4–30s · 480p · native sound](https://hermoso.ai/models/seedance-2-5-draft/)[Hailuo 2.3 Expressive human motion · great value 6–10s · silent](https://hermoso.ai/models/hailuo-2-3/)[Kling 4.0 The recommended Kling: up to 30s in one take with sound, takes a real person's face, 720p or 1080p 3–30s · 720p / 1080p · native sound](https://hermoso.ai/models/kling-4-0/)[PixVerse V6 Snappy social-first clips · audio 5–15s · 720p / 1080p / 540p · native sound](https://hermoso.ai/models/pixverse-v6/) See [all 42 video models](https://hermoso.ai/models/video/) or [every model Hermoso offers](https://hermoso.ai/models/).