Setting things up…
AI video model
Veo 3.1 Fast
Google Veo 3.1 Fast creates text-to-video with native 1080p and synchronized audio, delivering high-quality videos for creators. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
video outputfrom 60 creditsrefunded on failure
What you'll need
- Prompt — Text prompt for generation; Positive text prompt.
About Veo 3.1 Fast
Veo 3.1 Fast is an AI video model you can run directly in the Percify playground — fill in the inputs and generate right in your browser, or call it programmatically through the Percify API. Each run returns a ready-to-download video hosted on our CDN, and credits are only charged for successful results.
More AI video models
View the full catalogInfiniteTalk FastFast lip-sync — animate a portrait to speak any audio in seconds.InfiniteTalkLip-sync any portrait to any audio for a natural talking-avatar video.P-VideoP-Video — fast, efficient image-to-video generation.Seedance V1.5 Pro I2VSeedance 1.5 Pro — high-fidelity image-to-video.Sora 2 I2VSora 2 — turn an image into a coherent, high-quality video.Sora 2 Pro I2VSora 2 Pro — premium image-to-video with longer, sharper results.Kling v2.6 Standard Motion ControlKling 2.6 — animate a subject with motion control for cinematic video.Kling v3 Motion ControlKling 3.0 motion control: transfer motion from a reference video to any character image with improved consistency and quality.Grok Imagine Video EditGenerate videos using xAI's Grok Imagine Video modelWan 2.2 Animate ReplaceUse Wan 2.2 Animate to replace a character in a video sceneSeedance 2.0 Image-to-VideoSeedance 2 — image-to-video with smooth, dynamic motion.Seedance 2.0 Text-to-VideoSeedance 2 — generate video from a text prompt.