AI MODEL
VEO 3 Fast T2V
Veo 3 Fast supports text-to-video generation. It accepts natural language prompts and produces videos with synchronized sound (music and sound effects). It does not support image-to-video. The model supports aspect ratios 16:9 and 9:16, with resolutions in 720p and 1080p, and frame rate of 24 FPS. For each request, it can generate up to 4 videos, with lengths of 4, 6, or 8 seconds. Prompt rewriting is enabled to enhance prompt clarity and output alignment.
VEO 3 Fast T2V Prompts & Outputs
Compare outputs for COEY Vice
Compare outputs for Pug Robs Store
Compare outputs for How to Be Rich TED Talk
Compare outputs for Coffee Burrito
Latest Models Added