Google's Veo 2 text-to-video model. Highly censored, we get >50% prompt refusals. We issue refunds for content policy rejections. Creates 720p resolution videos (5-8 seconds) from detailed text descriptions. Image to video also supported. Supports both 16:9 (landscape) and 9:16 (portrait) aspect ratios. For best results, prompts should be descriptive and clear. Include the subject, the context, the action, and the style. A Google model, so unfortunately relatively censored.
Approx. Price
$3.40 per video
Model Type
both
Preview Examples
2
Generation controls available for this model.
Resolution/Aspect Options
2
Default Duration
5s
4 duration options
Tunable Settings
2
Aspect Ratio
Default
16:9
Options (2)
Landscape (16:9), Portrait (9:16)
Choose between landscape (16:9) or portrait (9:16) orientation
Duration
Default
5s
Options (4)
5 seconds, 6 seconds, 7 seconds, 8 seconds
Length of the generated video in seconds
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#49 / 83
ELO
1124.0
Appearances
5,695
95% CI
-8/8
Image to Video
#63 / 76
ELO
1094.0
Appearances
5,070
95% CI
-10/10
Release Date 2024-12 · Matched as Veo 2
Artificial Analysis APIA confident woman in her 40s stands on a stage with a microphone. The background shows a large LED screen with abstract visuals. She smiles and begins speaking to the audience.
A young man sits still on a subway train, surrounded by blurred figures moving rapidly. Close-up of his eyes, barely blinking, intensifying the sense of loneliness.
