Veo is Google DeepMind’s state-of-the-art video generation model. Veo 3 introduces expanded creative controls, including native audio, and improves realism and prompt adherence. Veo 3.1 is the latest Veo update, with a focus on stronger image-to-video consistency, vertical video, and higher-resolution upscaling.
What is Veo 3?
Veo 3 is Google DeepMind’s third‑generation Veo video model. It is designed as a high‑end video generation system that turns text and images into short cinematic clips. In this version, Google emphasizes stronger realism, better prompt adherence, and expanded creative control.
One of the most important upgrades in Veo 3 is native audio generation. That means it can create sound effects, ambient sound, and even dialogue together with the video, so the final output feels more complete and cinematic.
What is Veo 3.1?
Veo 3.1 is the latest Veo update. It improves “Ingredients to Video” so characters, backgrounds, and objects stay more consistent across clips when you use reference images. It also adds native vertical (9:16) output and supports upscaling to 1080p and 4K for higher-quality results.
Updates to Veo 3.1 📹 in the Gemini API and AI Studio:
— Logan Kilpatrick (@OfficialLoganK) January 13, 2026
- We now support upsampling to 1080p and 4K
- Improved ingredients (image reference) to video consistency
- Vertical video support for ingredients to video
So much Veo progress in the last few months, lots to build : )
Veo 3.1 vs Veo 3: Key upgrades
1) Better consistency from images
Veo 3.1 strengthens the Ingredients to Video workflow to keep identity, backgrounds, and textures more consistent when you build clips from reference images.
2) Native vertical video
Veo 3.1 can generate vertical 9:16 videos directly, which is ideal for Shorts-style platforms.
3) Higher-resolution upscaling
Veo 3.1 supports upscaling to 1080p and 4K for sharper output. Google notes these options are available in Flow, the Gemini API, and Vertex AI.
4) Audio stays a core strength
Veo 3 introduced native audio (sound effects, ambient noise, and dialogue). Veo 3.1 keeps that foundation and builds on it.
Which one should you choose?
- Choose Veo 3 if you want strong realism, good prompt adherence, and native audio—and you do not need vertical output or advanced image-to-video consistency.
- Choose Veo 3.1 if you need consistent characters and backgrounds from images, native vertical video, or higher-resolution upscaling for production workflows.
Where can you access Veo 3.1?
Google says the Veo 3.1 updates are rolling out across the Gemini app, YouTube Shorts, Flow, Google Vids, the Gemini API, and Vertex AI.
Try Veo 3 or Veo 3.1 now, create your first video.
