Models/Veo 3.1
MODEL · VIDEONEWPOPULAR

Veo 3.1

Google DeepMind Veo 3.1 — the highest realism in the suite, and the only model that generates synced audio with the visuals. Picked by the router when the prompt asks for "cinematic", "live action", names a real-world camera move, or needs sound.

Try in chatSee community works

Selected works.

8 OF MANY · GENERATED BY THE COMMUNITY
Veo 3.1 sample 1▶ 0:08
Veo 3.1 sample 2▶ 0:08
Veo 3.1 sample 3▶ 0:08
Veo 3.1 sample 4▶ 0:08
Veo 3.1 sample 5▶ 0:08
Veo 3.1 sample 6▶ 0:08
Veo 3.1 sample 7▶ 0:08
Veo 3.1 sample 8▶ 0:08

CAPABILITIES

What it can
do well.

  • ✓Text-to-videosupported
  • ✓Image-to-videosupported
  • ✓Clip lengthup to 8 seconds
  • ✓Output resolution1080p
  • ✓Audio generationnative, synced to the visuals
  • ×Lip-syncuse Lip Sync tool

Prompts that hit.

1 PATTERNS · COMMUNITY-SOURCED
PATTERN · CAMERA

"Slow dolly forward on [subject]. [Light condition]. [Mood]. [Ambient sound]."

Naming the camera move and the sound is the biggest unlock for Veo.

If you like this, try…

All models →
Veo 3.1 Fast sample
Veo 3.1 Fast1080p · 8s
cinematic · fast · audio
Kling v3 sample
Kling v31080p · 10s
motion · physics · i2v
Seedance 2.0 sample
Seedance 2.01080p · 12s
reference · audio · versatile

Compare Veo 3.1.

All comparisons →
vs
Kling v3
compare
vs
Seedance 2.0
compare

ABOUT THIS MODEL

FAQ.

Q.01

When does the auto-router pick Veo 3.1?

When the prompt requests video output and the requested duration / resolution falls within Veo 3.1's capabilities.

Q.02

Can I pin this model as default?

Yes. The model picker in any chat lets you pin per-turn or per-session. Set as default in /settings.