- Google Veo 3.1 will be available through AI video generation services
- Up to 1080p quality, improves character consistency and multi-shot generation
- Rumors suggest Veo 3.1 will support clips up to one minute long
Veo 3.1, the latest version of Google’s popular AI video generation tool, is starting to become available through third-party AI video generation services, and it looks like it will be able to support multiple requests for multi-shot effects, as well as generate 1080p videos up to one minute long.
What made Google’s Veo 3 different from previous AI video generators was its ability to sync audio with characters in the video. In Veo 3, the lip sync, voiceovers, music and effects were perfectly aligned in a single video. Veo 3 was quickly added to Google’s Gemini Flash 2.5, which is its current model, so that Gemini users could create AI videos from the chatbot’s text message.
While the latest Veo 3.1 goes even further, it is not yet available on Gemini. However, you can access it through third-party AI video generation services like Higgsfield, Imagine Art, and Envato.
Clips longer than 30 seconds
Higgsfield’s website says: “Whether starting from text to video or picture to video, Veo 3.1 ensures that characters stay consistent every frame, environments change naturally, and camera angles change with the precision of a real production studio.”
This sounds much more complicated than the simple eight-second clips that Veo 3 produces. Higgsfield’s website also lists “30+ second” video clips as a benefit of Veo 3.1.
Imagine Art’s website says: “With Google I Spy 3.1, you don’t have to look twice to ensure consistency between characters and scenes. It captures the interaction between characters and scenes perfectly.”
I Veo 3.1 also comes with cinematic presets. These give you full control of the narrative of your visual storytelling, so you can easily incorporate complex effects without having to do all the hard work yourself. Presets include drone shots, slow or fast pans, zoom in and out, tracking shots, and more. Lighting and tone presets are also available.
Multiple messages
A social media post by AI filmmaker Volodymyr Cherner claims that Veo 3.1 will be able to generate minute-long video clips.
Listing all the benefits of I Spy 3.1, Cherner writes: “Among the key features intended to justify the ‘.1’ in the name are: Character consistency. Now, the generated hero won’t change eye color or number of fingers from scene to scene. At least, that’s the promise.”
It also states that there will be support for more types of images. “The model has been trained to work not only with photographs, but also with illustrations and cartoon characters,” he writes. “Video length up to 1 minute. 1080p native resolution. Multiple messages for multiple shots (you can write multiple messages to generate multiple scenes based on a single photo).”
From the details leaking online, Veo 3.1 already looks like it could be a great rival to OpenAI’s recently released Sora 2. The ability to have multiple cues and multi-take videos opens up the possibility of directing much more complex scenes, and the longer video length would also help the process.
While we’re still waiting for Veo 3.1 to be added to Google Gemini, you can join the waitlist to get Veo 3.1 in Higgsfield and access it through the Envato and Imagine Art websites.
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
