Text to video
Build a shot in words: describe the subject, action, setting and camera path, then add lighting and sound. Create a short clip for a storyboard or creative exploration without a starting image.
Not available on free credit — top up to unlock it.
Configure request
Generated result
Run the playground to see output here.
Current BeatAPI public retail rates for this model.
| Model | Specifications and pricing | Price |
|---|---|---|
| Gemini Omni 1.1 Flash | 8 sec · 720p | $0.48 |
| Gemini Omni 1.1 Flash | 8 sec · 1080p | $0.72 |
| Gemini Omni 1.1 Flash | 8 sec · 4K | $1.44 |
Turn a written scene, opening image or visual references into a video with sound. Gemini Omni 1.2 Flash gives dialogue, movement and camera direction up to 15 seconds to unfold, with 720p, 1080p and 4K output.
gemini-omni-1.2-flashGemini Omni 1.1 Flash video API: text, a first frame, first and last frames, or up to 10 reference images and 3 reference videos; 3–10 s at 720p, 1080p or 4K with audio.
gemini-omni-1.1-flash| Comparison | Gemini Omni 1.2 Flash | Gemini Omni 1.1 Flash |
|---|---|---|
| Inputs | prompt · images · frames · references | prompt · images · frames · references |
| Resolution | 720p | 1080p | 4k | 720p | 1080p | 4k |
| Billing | video | video |
| API | /v1/videos/tasks | /v1/videos/tasks |
Choose the input that gives your shot the right starting point and visual direction.
Build a shot in words: describe the subject, action, setting and camera path, then add lighting and sound. Create a short clip for a storyboard or creative exploration without a starting image.
One image sets the opening frame; two ordered images set the opening and ending. Describe the action and camera between them to turn storyboard frames or a product image into a moving shot.
Reference images provide visual direction for people, products or settings; reference videos guide movement or camera work. Combine up to 10 images and 3 videos, and describe each reference's role in the prompt.
Describe dialogue, ambient sound or effects in the prompt. Each video includes generated audio.
The V-Benchmark v2 overall score is 76.23 out of 100. Prompt adherence measures whether explicit instructions appear in the video: 88.28 across 35 videos. Scene consistency measures continuity of subjects, space and lighting: 88.56 across 36 videos. The samples were generated through Google and evaluated on August 28, 2026; the report was updated November 3.
An astronaut in a white spacesuit pours latte art into a floating cup inside a cozy moon-base cafe, Earth visible through a large window, steam swirling in low gravity, slow dolly-in, warm lighting, gentle ambient cafe sounds.
An origami paper whale swims gracefully through a stylized paper-craft ocean, paper waves folding and unfolding, paper seagulls gliding above, soft sunlight, camera slowly orbiting, calm orchestral score.
Use short generated clips as building blocks for product, storytelling and campaign workflows.
Use a product image as a reference and describe the orbit, lighting and background for a product-page reveal. Review the product shape and label across the finished shot.
Supply opening and closing frames and describe the action between them to create a bridge between two shots.
Reuse character and location references while changing the action, dialogue and aspect ratio for landscape and portrait clips. Review continuity and audio before editing the clips together.
Pair reference images with a reference video and describe which subject and camera movement to follow for a new shot.
Create an asynchronous video task and retrieve the finished file in your application.
Sign up or sign in to open the Dashboard. Check your balance and open the credits page if you need to add funds.
Open DashboardCreate short clips from the amount of visual direction your project already has.
Start with text, anchor a shot with frames, or combine reference images and video to guide the new output.
Generate a video with sound in the same task without a separate audio-generation request.
Choose landscape or portrait for the placement, then set the clip length and resolution. The requested duration and resolution determine the price.
Gemini Omni 1.1 Flash is Google's multimodal video generation and editing model. BeatAPI exposes video generation from text, frames and visual references through an asynchronous API.
Choose a prompt alone, one first frame, first and last frames, or 1–10 reference images with up to 3 optional reference videos. Choose one input mode for each task and pair reference videos with at least one reference image.
Yes. Every output includes generated sound. Describe dialogue, ambient sound or effects alongside the visual action in your prompt.
Choose a whole-number duration from 3 to 10 seconds, 720p, 1080p or 4K, and 16:9 or 9:16. Defaults are 5 seconds, 720p and 16:9.
The price depends on requested duration and output resolution. Reference inputs and aspect ratio do not change the rate. See the pricing table above for current rates and the task usage for the actual charge.
Identify what each reference contributes, such as the product in one image and the camera movement in a video, then describe the new action and setting.
The create request returns a task ID. Poll the task or listen for a webhook, then download the media URL after success and store it yourself; result URL retention is not guaranteed.
The task response identifies the error and whether retrying may help. Failed tasks are refunded under the documented video task contract; correct invalid inputs before submitting again.
Choose Gemini Omni 1.1 Flash for a selectable 3–10 second clip or to guide a shot with reference images and video. On BeatAPI, Veo 3.1 produces fixed 8-second clips with Quality, Fast and Lite tiers. Check each page for its input options and pricing.
Connect Gemini Omni 1.1 Flash with other production-ready APIs in the BeatAPI catalog.
Guides and practical notes to help you get more from Gemini Omni 1.1 Flash.