Agent-readable docs index: /llms.txt. Full docs in one file: /llms-full.txt. Download /docs.zip to grep all markdown files locally.

video

Generate videos from a text prompt (or image+text prompt for models that support image-to-video). Uses AI SDK experimental_generateVideo under the hood.
Agent note: video generation can be slow. When invoking this command from automation, use a command timeout of at least 5 minutes.

Usage

egaki video <prompt>

Arguments

ArgumentRequiredDescription
<prompt>Yesprompt

Options

OptionDefaultDescription
-m, --model [model]-Video model ID for generation. If omitted, shows an interactive picker (or uses default in non-TTY mode)
-o, --output [path]egaki-output.mp4Output file path (index suffix added when generating multiple)
-n, --count [n]1Number of videos to generate
--aspect-ratio [ratio]-Video aspect ratio in WIDTH:HEIGHT format (e.g. 16:9, 9:16)
--resolution [resolution]-Video resolution. xai: 480p, 720p (default: 720p). bytedance: 480p, 720p, 1080p. Google: 720p, 1080p, 4k
--duration [seconds]-Video duration in seconds. Veo: 4-8s. xAI Grok: 1-15s. Kling: 5-10s. Wan: 2-15s
--fps [fps]-Frames per second for video models that support fps override
--seed [seed]-Seed for reproducible video generation (model support varies)
-i, --input [file]-Input file for video generation. For i2v: a reference image. For edit-video/extend-video: a source video. Accepts local file paths or URLs
--mode [mode]-Video operation mode. xai: edit-video, extend-video, reference-to-video
--reference-images [path]-Reference images for R2V generation, repeatable. xAI: 1-7 images. Seedance: 1-9 images (use @Image1 etc. in prompt)
--negative-prompt [text]-Describe what to avoid in the generated video (Fal models)
--json-Output result metadata as JSON to stdout (model, usage, warnings, file paths)
--stdout-Write raw video bytes to stdout instead of saving to a file. Useful for piping to other tools

Global Options

OptionDefaultDescription
-h, --help-Display this message
-v, --version-Display version number

Examples

# Generate a video
egaki video "A paper airplane gliding through clouds" -o airplane.mp4
# Generate with Veo model + duration
egaki video "cinematic rainy street at night" -m veo-3.1-fast-generate-001 --duration 6
# Route through Vertex AI (Google Cloud billing)
egaki video "storm over mountains" -m vertex/veo-3.1-fast-generate-001 --duration 6
# Image-to-video (model support required)
egaki video "animate subtle camera pan" --model luma-ray-2 --input frame.png -o animated.mp4
# Generate multiple videos
egaki video "waves crashing on cliffs" -n 2 -o waves.mp4