Skip to main content

Gemini Video Generation

Generate and edit videos using Google’s Veo 2 / Veo 3 / Veo 3.1 models. Supports text-to-video, image-to-video, duration extension, reshoot, and object insert/remove.

Supported Models

Features

Text-to-Video

Create videos from text prompts with action: "text2video"

Image-to-Video

Use 1-2 reference images (start frame / start+end) with action: "img2video"

Ingredients-to-Video

Use 1-3 reference images to compose a scene with action: "ingredients2video"

Upsample & Extend

Upscale to 1080p/4K, generate GIFs, or extend video duration

Reshoot

Re-generate with different camera motion (15 motion types)

Object Edit

Insert or remove objects from videos using mask-based editing

How to Use

1

Generate a video

Call POST /gemini/video/generate with your prompt and model. You’ll receive a taskId.
2

Poll for results

Use GET /gemini/task/result?taskId=xxx to poll until status is completed. The result contains the video URL.
3

Enhance (optional)

Use the returned videoId to upscale, extend, reshoot, or edit objects in the video.

Available Endpoints

Generation

Post-Processing

Object Editing

Task Management

Video and Image share the same polling endpoint — see Get Task Result.

Explore the API Documentation