Glossary · AI Video
Quick answer
VEO 3.1 is Google DeepMind’s flagship video generation model, known for cinematic realism, strong physics and motion coherence, and native audio generation — it can produce dialogue, ambient sound, and effects synchronized with the visuals. It handles both text-to-video and image-to-video. VEO 3.1 is available inside VdoBloom alongside Runway, Kling, Wan, Seedance, and PixVerse.
VEO’s standout trait is treating video and audio as one generation problem: a clip of a person speaking comes out with matching voice and lip movement, and a street scene arrives with believable ambient noise.
Creators reach for VEO 3.1 when realism matters — product ads, talking scenes, nature footage, and anything where wrong physics or silent video would break the illusion.
In VdoBloom, VEO 3.1 is selectable inside the text-to-video and image-to-video tools, drawing from the same credit pool as every other model.
VdoBloom starts you with 10 free credits — enough to put this into practice with no card required.
Open Text to Video tool