Google · Text to Video

Veo 3.1

The most advanced AI video model in the world, with photoreal motion and synchronized native audio.

text video
google/veo-3.1/text-to-video

Examples

representative generations · starting points to seed the playground

00:00 / 00:06
00:06

1:1, Ornate Art-Nouveau gilded painting in a Klimt-inspired style: a serene woman in profile in a robe of dense gold-leaf patterning, mosaic spirals, lapis-blue and emerald geometric ornament, holding a golden bowl. Flat decorative composition, shimmering gold-leaf texture over painterly skin, opulent jewel-tone palette. No text or logos. The gold leaf shimmers as light sweeps across the ornament, the figure's eyes slowly open, faint particle glints. Native audio: soft reverent drone, delicate chimes.

00:00 / 00:06
00:06

1:1 Surreal collage portrait: a young woman with a short dark bob, her face and torso rendered as a completed jigsaw puzzle with several pieces lifting away and floating, a few gaps revealing colorful mismatched pieces underneath. Muted sage-green background, soft even light, matte cardboard puzzle texture, conceptual editorial mood, subtle grain. No text or logos. keep the floating-pieces motion; restyle to matte cardboard-puzzle surface with sage-green backdrop, refined conceptual grade.

00:00 / 00:08
00:08

Deadpan mock-nature-documentary, 9:16 vertical. Handheld observational shot peering through office plants at a young woman slumped at a beige cubicle desk under fluorescent light, staring blankly at a monitor. A calm hushed nature-narrator voice speaks over ambient office hum: "Here we observe the modern woman in her natural habitat… conserving energy by avoiding all responsibility." She slowly sips cold coffee without breaking her stare. Muted corporate palette, dry ironic humor, subtle zoom, natural room tone and soft narration.

00:00 / 00:08
00:08

Simple deadpan single shot, 9:16 vertical. A young woman with a messy bun sits alone on the edge of a bathtub, still in last night's going-out clothes, holding a glass of water. She looks tiredly into the camera and deadpans: "I'm not hungover — I'm just emotionally located in the past." Soft morning bathroom light, muted tones, static locked shot, dry ironic web humor, quiet room tone and her flat calm voice.

00:00 / 00:06
00:06

A winding path curves through a dreamlike field of oversized pastel peony blooms towering on thick pale-green stems, soft blush-pink to lavender gradient sky at golden hour, delicate diffused light passing through translucent petals, extremely soft hazy atmosphere with minimal contrast, dreamlike pastel color grade, gentle breeze swaying the giant blooms, slow serene dolly forward down the path.

Per-model pricing

Transparent, usage-based rates for every Google model.

Veo 3.1 Lite

from $0.03 / sec
Image to Video

Nano Banana 2 Lite

$0.034 / image
Image to Image

Nano Banana 2 Lite

$0.034 / image
Text to Image

Nano Banana 2

from $0.045 / image
Image to Image

Nano Banana 2

from $0.045 / image
Text to Image

Lyria 2

$0.06 / request
Music

Veo 3.1 Fast

from $0.08 / sec
Text to Video

Veo 3.1 Fast Video Extension

from $0.1 / sec
Video Extension

Nano Banana Pro

from $0.134 / image
Image to Image

Nano Banana Pro

from $0.134 / image
Text to Image

Veo 3.1

Current
from $0.2 / sec
Text to Video

Veo 3.1 Video Extension

from $0.2 / sec
Video Extension

Gemini 3.1 Pro

$2 / $12 per 1M tok

Gemini Omni Flash Image To Video

$1.575 / $9.45 per 1M tok
Image to Video

Gemini Omni Flash Reference To Video

$1.575 / $9.45 per 1M tok
Reference to Video

Gemini Omni Flash Text To Video

$1.575 / $9.45 per 1M tok
Text to Video

Gemini Omni Flash Video To Video

$1.575 / $9.45 per 1M tok
Video to Video