Pretty good for keyframe transitions and does a much better job than Seedance rendering text in green-screen lower thirds.
Google DeepMind's video generation model producing clips with natively generated audio, dialogue and sound effects.
Updated EU status checked Last shown
Veo 3.1 at a glance
- What is Veo 3.1?
- Veo 3.1 is a model from Google. Google DeepMind's video generation model producing clips with natively generated audio, dialogue and sound effects.
- Who makes Veo 3.1?
- Veo 3.1 is made by Google.
- Does Veo 3.1 work in the EU?
- Available in the EU. The provided pages contain no explicit EU restriction. From general knowledge, Veo is offered through the Gemini API and Google's apps in EU countries, though feature availability can vary by product and region. Last verified 14 Nov 2026.
- How much does Veo 3.1 cost?
- API pricing. Available through the Gemini API (usage-based) and Google consumer subscription products; check Google's pricing pages for current rates. Licence: Proprietary.
- Where was Veo 3.1 shown?
- In 1 creator video by Matt Wolfe. Most recently by Matt Wolfe on 8 Jul 2026, at 2:25 in “30+ AI VFX That Turn Simple Videos Into Magic”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Veo 3.1 is Google DeepMind's video generation model, an update to Veo 3. It generates video from text prompts and image inputs, and produces audio natively, including dialogue, sound effects and ambient noise, alongside the video. Google describes it as aimed at filmmakers and storytellers, with improved realism, prompt adherence and creative control compared with earlier Veo versions.
Prompts can specify camera movement, scene description, spoken lines and audio cues. A YouTube reviewer (Matt Wolfe) noted it works well for keyframe transitions and renders text in green-screen lower thirds better than Seedance.
Veo is accessed through Google products and the Gemini API, which has video generation documentation at ai.google.dev. It is a closed, hosted model with no downloadable weights. Exact pricing, clip length limits and plan details were not in the provided material and should be checked on Google's pages.
- Native audio generation: dialogue, sound effects and ambient sound
- Text-to-video and image-guided generation
- Improved prompt adherence and realism over Veo 3
- Keyframe-style transitions and in-video text rendering
- Available via the Gemini API
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Similar AI tools
Closest neighbours by meaning, not just by category.
Gemini Omni in Google Vids
App · Google
Google Vids' Gemini Omni feature generates and edits video clips with native audio and avatars inside Google Workspace.
FastH3
Model · Hao AI Lab
Open-weight 4-step sparse-distilled version of MiniMax H3 for fast text-to-video-and-audio generation on Blackwell GPUs.
Gemini Omni 1.2 Flash
Model · Google
Google's video generation model producing clips up to 15 seconds from text, image, video or audio input.
Grok Imagine 1.5
Model · xAI
xAI's Grok Imagine video generation model with dialogue support, offered through Grok plans.
Gemini Omni 1.1 Flash
Model · Google
Google's updated Omni Flash video model with 360p–4K output, first/last-frame control and video extension.
Gemini 3.8 Flash TTS
Model · Google
Google's Gemini 3.8 text-to-speech model for expressive, controllable speech generation via the Gemini API and AI Studio.