Veo 3.1
Text-to-video and image-to-video with optional end frame control. Native audio generation, cinematic realism, and consistent subjects. Supports 4/6/8 seconds at 720p or 1080p.
Added Oct 11, 2025
Details
- Starting Price
- From $1.60 per video
- Model type
- both
Final price depends on the selected settings and is shown before generation.
Settings
Generation controls available for this model.
Output Format
Default Duration
8
3 duration options
Aspect Ratio (T2V)
Default
16:9
Options (2)
Landscape (16:9), Portrait (9:16)
Applies to text-to-video
Duration
Default
8
Options (3)
4 seconds, 6 seconds, 8 seconds
4/6/8 seconds
Generate Audio
Default
Yes
Enable native audio generation
Resolution
Default
720p
Options (2)
720p, 1080p
Output resolution
Seed
Default
-1
Use -1 for a random seed. Each video keeps the seed it used, so you can reuse it.
Benchmarks
Benchmarks
Human preference benchmarks sourced from LMArena.
Text to Video
#14 / 50
Arena Score
1363.1
Votes
13,819
Confidence Interval
1348.7 - 1377.4
Image to Video
#15 / 50
Arena Score
1398.6
Votes
25,283
Confidence Interval
1388.1 - 1409.0
Published 2026-11-06 · Matched as Veo 3.1 (Audio)
LMArena DatasetExamples
Loading examples…