Google's Gemini Omni 1.2 Flash makes 15-second videos you can edit by chatting
Google's new video model makes longer clips at a lower price and lets you change them with follow-up requests instead of starting over.
The short version
- Google announced Gemini Omni 1.2 Flash on November 5; it makes clips up to 15 seconds, up from 10.
- Length can be set in 1-second steps for finer control over pacing.
- You can change the background, lighting or aspect ratio on the same clip without regenerating it.
- Cost is down 30% from the prior model, about $0.07 per second at 720p.
- Google Vids offers up to three free 15-second videos a month to Google account holders and Workspace subscribers.
Why it matters
Short video is the format most people actually post, and 15 seconds covers a typical social clip. Being able to fix a clip by asking, rather than redoing it, makes AI video less of a gamble. The free monthly allowance in Google Vids lets ordinary users try it without paying.
What Google released
Google announced on November 5 that Gemini Omni 1.2 Flash, its AI video model, is officially available. As technews.tw reported, the update focuses on longer clips, lower cost and a more flexible editing process.
The model can now make videos of up to 15 seconds in one go, compared with 10 seconds for the version before it. Users can also set the length in 1-second steps, which helps when a clip needs to fit a specific rhythm.
Editing by conversation
The main change is what Google calls conversational editing. Instead of writing a new request and generating a fresh video each time, you can make several rounds of changes to the same clip. Examples Google gave include swapping the background, adjusting the lighting or changing the aspect ratio (the shape of the frame).
Google also says the model is better at keeping things consistent. People, clothing, text on packaging and brand colors should hold steady from shot to shot when you supply reference images or footage. It can also work with short motion clips and audio prompts.
Other upgrades include more natural speech, clearer lip sync and camera moves with fewer jump cuts, the abrupt jumps between shots that can make AI video feel choppy.
Price and where to find it
Google says the model costs 30% less than the previous generation. At 720p, video runs about $0.07 per second. Google suggests a cheap workflow: make quick low-resolution drafts, fix the details, then upgrade the final output.
The model is available in the Gemini API, Google Cloud, Google Vids, Flow, Google Ads and some Gemini app services. In Google Vids, anyone with a Google account or a Google Workspace subscription can make up to three 15-second videos a month for free, starting November 5.
What to watch
- How well the consistency claims hold up in everyday use across multiple shots.
- Whether rivals match the lower price and the edit-in-place approach.
Try it
If you have a Google account, open Google Vids and use your free monthly clips: generate one, then ask for a single change, such as new lighting, to see how editing by chat feels.
Sources and links
- Reportingtechnews.tw: the article we sourced
Liked it? Say why
Add a line for other readers.
No account needed. We never show your email. Comments with links, ads or abuse are held and not shown. Your comment shows after a quick check.
Listen to the AI Wire headlines
Listen to the AI WireListen to our daily AI shows every morning: on your commute, in the shower, wherever you are
Listen to the daily showsFirst reported by technews.tw · Read the original. Written by the SI Agent News Desk from the reporting above.Written with AI from the source above. Every number is checked against the source. Spot a mistake? Corrections.