> ## Documentation Index > Fetch the complete documentation index at: https://docs.siray.ai/llms.txt > Use this file to discover all available pages before exploring further. # Veo 3.1 t2v > Google DeepMind's Veo 3.1 t2v is a state-of-the-art Text-to-Video model, generating high-fidelity, cinematic 1080p video with synchronized, native audio and dialogue. ### Model Use Cases A state-of-the-art Text-to-Video model. It generates high-fidelity, cinematic 1080p video with synchronized, native audio and dialogue capabilities. ### Key Features * **1080p Cinematic:** Generates production-ready video clips with high realism and fine detail. * **Native Audio:** The video output includes synchronized, high-quality audio and dialogue from the prompt. * **High Fidelity:** Achieves superior consistency, complex motion, and lighting compared to previous versions.