You can use Gemini Omni Flash in three main ways: in the Gemini app (open the sidebar, choose Create video, type a prompt), through the Gemini API and Google AI Studio with the model ID gemini-omni-1.1-flash, or on a multi-model platform such as Kenerate's Video Studio. The Gemini app needs a Google AI plan and is for adults 18+; the API needs a Gemini API key; Kenerate needs a free account. Here is how each route works, step by step.

Ways to access Gemini Omni Flash compared

RouteWho it suitsWhat you needNotes
Gemini app (web, Android, iOS)Anyone who wants chat-based videoGoogle AI Plus, Pro or Ultra plan, or a qualifying Workspace license; 18+Multi-turn editing, avatars, download or share to YouTube
Google FlowFilmmakers assembling shotsGoogle AI Plus, Pro or Ultra planGoogle's AI filmmaking tool
YouTube Shorts and YouTube CreateShorts creatorsA YouTube accountIncluded at no cost
Google VidsWorkspace and business videoA Google or Workspace accountUses Gemini Omni 1.1 Flash at 1080p
Google AI StudioTesting before you codeA Google accountBrowser playground for the API model
Gemini APIDevelopers and pipelinesAPI key, SDK or RESTFull control: resolution, aspect ratio, editing, extension
Adobe FireflyAdobe usersAn Adobe accountFirefly site, Boards and iOS app; up to 10 s at 720p
Kenerate Video StudioComparing models and finishing clipsA Kenerate accountOmni Flash next to Veo 3.1, Kling, Seedance, Ken 1 and more

Availability and plan details come from Google's launch post, the Gemini Apps help page, the Gemini Omni 1.1 Flash announcement and Adobe's Gemini Omni page.

A dark desk with a laptop, a phone and a tablet arranged side by side, each screen glowing with the same cinematic video frame of a waterfall, soft teal ambient light
A dark desk with a laptop, a phone and a tablet arranged side by side, each screen glowing with the same cinematic video frame of a waterfall, soft teal ambient light

How to use Gemini Omni Flash in the Gemini app

The Gemini app is the simplest way in if you already have a Google AI plan.

Before you start

  • Plan: a personal account needs a Google AI plan; work or school accounts need a qualifying Workspace license.
  • Age: video creation is not available to users under 18.
  • Region: editing an uploaded video (video-to-video) is unavailable in the EEA, Switzerland, the UK and some US states.

Step by step on desktop

  1. Go to gemini.google.com and sign in.
  2. Click Open sidebar, then Create video.
  3. Optionally pick a template.
  4. Type your prompt. To add media, use Add image (up to five images) and/or Add video (one video).
  5. To appear in the video yourself, set up an avatar and mention it with the @ syntax described in Google's help page.
  6. Submit and wait. Generation can take a few minutes; you can start other chats meanwhile.

On Android or iPhone, open the Gemini app (or gemini.google.com), tap Menu, then Videos.

Edit, extend and export

  • Edit by chatting: in the same conversation, ask for one change at a time, for example "change the background to a rainy street, keep everything else the same." Each turn can include new image or video references.
  • Aspect ratio: text-only prompts default to landscape; when you upload references, the video matches their shape. You can change the ratio before generating.
  • Extend: Google says scene extension is available in the Gemini app for Plus, Pro and Ultra subscribers on the 1.1 model.
  • Export: under the video, choose Share, then Download video or Share on YouTube.

Google Flow, YouTube and Google Vids

  • Google Flow is Google's AI filmmaking tool. Gemini Omni 1.1 Flash is available there for Google AI Plus, Pro and Ultra subscribers.
  • YouTube Shorts and the YouTube Create app include Gemini Omni Flash at no cost, which is handy if Shorts is your main channel.
  • Google Vids added Gemini Omni 1.1 Flash in September 2026 for anyone with a Google or Workspace account, with 1080p generation, scene extension and templates, according to Google's Vids announcement.

How to use Gemini Omni Flash with the Gemini API

The API gives you the most control and is the route for apps, automation and batch work. Everything below follows the official Gemini Omni Flash API guide.

Model IDs and where to try them

  • Stable: gemini-omni-1.1-flash (released August 2026)
  • Preview: gemini-omni-flash-preview (the June 2026 developer preview)

Start in Google AI Studio to test prompts in the browser, then move to code. If you built against the preview ID, check the model page and plan a move to the stable ID.

Step 1: get a key and install the SDK

Create an API key in Google AI Studio, then install Google's Gen AI SDK for Python (pip install google-genai). SDKs also exist for JavaScript, Java and Go. Omni uses the Interactions API (client.interactions.create() in Python), not the older video endpoints.

Step 2: generate a clip from text

This is the text-to-video example from Google's docs, with only the prompt changed:

python
import base64 from google import genai client = genai.Client() interaction = client.interactions.create( model="gemini-omni-1.1-flash", input="A paper boat drifting across a still pond at sunrise, single continuous shot." ) with open("boat.mp4", "wb") as f: f.write(base64.b64decode(interaction.output_video.data))

Step 3: edit the clip conversationally

To edit a video you just generated, pass the earlier interaction's ID as previous_interaction_id. There is no need to re-upload anything:

python
edit = client.interactions.create( model="gemini-omni-1.1-flash", previous_interaction_id=interaction.id, input="Add light rain falling on the pond. Keep everything else the same." )

To edit or extend your own footage, upload it with the Files API and pass it as a video input next to your text. Uploaded videos must be 10 seconds or shorter.

A developer's dark workstation with a code editor glow on one monitor and a rendered video frame of a paper boat on a pond on the other, soft blue desk light, photographic
A developer's dark workstation with a code editor glow on one monitor and a rendered video frame of a paper boat on a pond on the other, soft blue desk light, photographic

Useful settings

SettingOptionsWhat it does
response_format → aspect_ratio16:9 (default), 9:16Landscape or vertical output
response_format → resolution360p, 720p (default), 1080p, 4kDraft fast, render final at higher resolution
response_format → deliveryuriReturns a hosted file for videos over 4 MB; poll until the file is active, then download
generation_config → video_config → tasktext_to_video, image_to_video, reference_to_video, edit, extendForces a mode; Google suggests relying on the prompt first

API limits to know

  • Each output is 3 to 10 seconds at 24 fps; extension continues a clip in further 10-second steps.
  • Editing and extending uploaded videos is unavailable in the EEA, Switzerland and the UK.
  • Not supported: voice editing, audio reference uploads, multi-video referencing, system instructions, temperature and top_p, and YouTube links as media.
  • Every output carries an invisible SynthID watermark.
  • English is fully supported; other languages have not been evaluated.

For billing, see Google's Gemini API pricing page.

How to use Gemini Omni Flash on Kenerate

If you don't have a Google AI plan, don't want to write code, or want to compare Omni Flash with other video models, you can run it on Kenerate.

  1. Create a Kenerate account. New accounts get 25 free credits, and credits never expire.
  2. Open the Video Studio and pick Gemini Omni Flash from the model list.
  3. Choose text-to-video, or upload an image to animate.
  4. Write your prompt using the shot-by-shot approach in our Gemini Omni Flash prompt guide.
  5. Generate, then try the same prompt on Veo 3.1, Kling v3 Pro, Seedance 2.5 or Ken 1 to see which take you prefer.
  6. Finish in the same account: run the video upscaler, add an ElevenLabs voiceover in the Voice Studio, or score the clip with Ken Music.

Open the Video Studio

A creator's dark editing suite with a large monitor showing four versions of the same mountain lake scene in a grid, warm amber key light and cool blue background glow
A creator's dark editing suite with a large monitor showing four versions of the same mountain lake scene in a grid, warm amber key light and cool blue background glow

Tips for a usable first clip on any route

  • Pick the route first. App for quick chat edits, API for automation, Kenerate for model comparisons and finishing tools.
  • Write one scene. Subject, action, framing, camera, light and sound in a few sentences; add "single continuous shot" if you don't want cuts.
  • Draft cheaply. In the API, test at 360p and render the keeper at 720p or higher.
  • Edit small. One change per turn, with "keep everything else the same."
  • Check the output. Look closely at hands, on-screen text and audio before you publish.

Troubleshooting

ProblemLikely causeWhat to try
No Create video option in the Gemini appNo Google AI plan, under 18, or a restricted accountCheck your plan and account type
Can't edit an uploaded videoRegional restrictionGenerate a fresh clip and edit that instead, where available
API returns no inline videoFile larger than 4 MBRequest delivery as uri and download the hosted file
Edit changed the whole sceneEdit prompt too longShorten it to one change per turn
Extension rejectedUploaded clip longer than 10 seconds, or a talking clip you want new dialogue forTrim the input; regenerate dialogue scenes instead

To understand the model itself, read what Gemini Omni Flash is. For other ways to start from a still or an existing clip, see image-to-video and video-to-video.

Bottom line

Use the Gemini app if you already pay for a Google AI plan and want the fastest path to a chat-edited clip. Use Google AI Studio and the Gemini API with gemini-omni-1.1-flash when you need resolution control, editing chains or automation. Use Kenerate when you want Omni Flash next to other leading video models and finishing tools in one account.