AI Models
Explore available models and their capabilities
Google
Released December 2025
Veo 3.1 (Text)
Text-to-video with audio, up to 4K, lip-sync, 4-8s
Video Generation
About this model
Google DeepMind Veo 3.1 via Fal creates high-fidelity videos from text with cinematic realism, native audio generation (ambient sounds, dialogue, music), and realistic lip-sync. Produces 4-8 second videos at up to 4K resolution.
Input Cost
$0.20-0.60/s
Output Cost
$0.20-0.60/s
Input Types
Text