Latest models
- Veo 3.1 Current
Google's video model, producing 8-second clips at 720p, 1080p or 4K with native audio, plus a lower-cost Lite tier. Available in the Gemini app, Flow, YouTube Shorts, Vids, the Gemini API and Vertex AI. Source: Google DeepMind ↗
Checked October 7, 2026. See the full AI model tracker.
What we like
- Text-to-video, image-to-video and audio generated together
- Clips at 720p, 1080p or 4K
- Available in several Google products, including Gemini, Flow, YouTube Shorts and Vids
Watch out for
- Clips are 8 seconds, so longer videos need extending or editing together
- Access and limits vary by product and plan
- Expect to regenerate to get the shot you want
Veo is Google DeepMind’s family of video generation models. Google describes Veo 3.1 as a cinematic engine for creative storytelling, producing 8-second videos at 720p, 1080p or 4K with natively generated audio.
What is current
Veo 3.1 is Google’s leading video model, with a lower-cost Veo 3.1 Lite tier aimed at high-volume applications. You can try it in the Gemini app, Flow, YouTube Shorts and Google Vids, or build with it through the Gemini API and Vertex AI. See the model tracker for sources.
How prompting works
Describe one shot: the subject, the camera movement, the light and the sound. Because Veo generates audio with the video, mention ambient sound or spoken lines in the prompt.
Who should use it
Creators who want short, polished clips with sound and are comfortable working inside Google’s tools. Compare it in Veo vs Kling.