Google adds photo-to-video tool to Gemini as Veo 3 rollout expands
David Sharon, Multimodal Generation Lead for Gemini Apps, said, "We launched our state-of-the-art video generation model Veo 3 in May - and last week, we expanded access to Google AI Pro subscribers in over 150 countries. Now, with a new photo-to-video capability in Gemini, you can now transform your favourite photos into dynamic eight-second video clips with sound."
Describing the process, Sharon added, "To turn your photos into videos, select 'Videos' from the tool menu in the prompt box and upload a photo. Then, describe the scene and any audio instructions, and watch as your still image transforms into a dynamic video. You can get creative by animating everyday objects, bringing your drawings and paintings to life or adding movement to nature scenes. Once your video is complete, tap the share button or download it to share with friends and family."
According to Google, the reception from users has been swift and enthusiastic. "The explosion of creativity from users has been truly remarkable, with over 40 million Veo 3 videos generated across the Gemini app and Flow over the last seven weeks. From reimagining fairy tales through the eyes of a modern influencer, to ASMR videos exploring what it would sound like to cut through a piece of cooling lava, your imagination is the limit when you create videos with Gemini," Sharon said.
The new photo-to-video feature is being rolled out alongside broader access to Veo 3, Google's latest iteration in text-to-video artificial intelligence. Veo 3 is already recognised for its ability to produce high-definition video clips with synchronised sound and lifelike motion, generated entirely from user prompts. The model delivers results in eight-second clips, integrating both visuals and audio without the need for post-production editing.
Google is positioning Veo 3 as both a creative and enterprise solution, with businesses able to access the technology through the Google Cloud Vertex AI platform. Creative professionals and app developers have begun using Veo 3 to accelerate workflows, generate marketing assets, and prototype video content in a fraction of the time previously required.
The company also emphasises its commitment to responsible AI development and safety. "When you use our video generation tools, we want you to feel confident in the results. That's why we take significant steps behind the scenes to make sure video generation is an appropriate experience," Sharon explained. This includes what Google describes as "extensive 'red teaming,' in which we proactively test our systems and aim to fix potential issues before they arise," as well as "thorough evaluations to understand how our tools might be used and how to prevent any misuse."
Safety measures extend to content labelling, as Sharon detailed: "All generated videos include a visible watermark to show they are AI-generated and an invisible SynthID digital watermark." Users are also encouraged to provide feedback on generated content, with Sharon stating, "Use the thumbs up and down buttons on your generated videos to give us feedback, which we'll use to make ongoing improvements to our safety measures and overall experience."
Access to the new photo-to-video capability begins rolling out today for Google AI Pro and Ultra subscribers in select countries. The same functionality is also available in Flow, Google's AI filmmaking tool, with the company continuing to expand availability to additional regions.
"Your imagination is the limit when you create videos with Gemini," said Sharon.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
1News
3 days ago
- 1News
First skydiver to fall faster than the speed of sound dies
Extreme athlete Felix Baumgartner, the first skydiver to fall faster than the speed of sound during a 24-mile leap through the stratosphere more than a decade ago, died in a crash along the eastern coast of Italy, according to an official where the crash occurred. He was 56. Italian firefighters who responded said a paraglider crashed into the side of a swimming pool in the city of Porto Sant Elpidio. The city's mayor, Massimiliano Ciarpella, confirmed Baumgartner's death in a social media post. 'Our community is deeply affected by the tragic disappearance of Felix Baumgartner, a figure of global prominence, a symbol of courage and passion for extreme flight," the mayor said. ADVERTISEMENT Baumgartner, known as 'Fearless Felix', stunned the world in 2012 when he became the first human to break the sound barrier with only his body. He wore a pressurised suit and jumped from a capsule hoisted more than 24 miles 39 kilometres above Earth by a giant helium balloon over New Mexico. The Austrian, who was part of the Red Bull Stratos team, topped out at 1357.6km/h — the equivalent of 1.25 times the speed of sound — during a nine-minute descent. 'When I was standing there on top of the world, you become so humble, you do not think about of breaking records anymore, you do not think of about gaining scientific data. The only thing you want is to come back alive,' he said after landing in the eastern New Mexico desert. The morning's headlines in 90 seconds, including a Wellington house fire, the UK lowers the voting age, and the Obamas joke about divorce rumours. (Source: 1News) The altitude he jumped from also marked the highest-ever for a skydiver, shattering the previous record set in 1960 by Joe Kittinger, who served as an adviser to Baumgartner during his feat. Baumgartner's altitude record stood for two years until Google executive Alan Eustace set new marks for the highest free-fall jump and greatest free-fall distance. ADVERTISEMENT In 2012, millions watched YouTube's livestream as Baumgartner coolly flashed a thumbs-up when he came out of the capsule high above Earth and then activated his parachute as he neared the ground, lifting his arms in victory after he landed. He later said travelling faster than sound is 'hard to describe because you don't feel it.' 'Sometimes we have to get really high to see how small we are,' he said.
Techday NZ
3 days ago
- Techday NZ
Exclusive: How APAC hotels are adopting AI & automation for growth
Hotels across Asia Pacific are urgently rethinking their digital strategies in response to the prominence of online travel agencies (OTAs) and mobile-first consumers. According to Klaus Kohlmayr, Chief Evangelist and Chief Development Officer at IDeaS, the market is seeing unprecedented competition and a technological arms race as properties strive to stand out in an increasingly digital world. "There's a real danger when you have too much reliance on your OTAs or OTA channels," he warned, during a recent interview with TechDay. Kohlmayr observes that many hotels, especially independent operators and those outside global distribution networks, may find themselves trapped in a dependency on OTAs because their primary markets are often far away. "It's all about having the right balance between your indirect channels, your direct channels, and your direct sales and marketing efforts for your own people," he adds. The imperative, he argues, is to invest in technology that allows for direct engagement with guests-platforms with modern booking engines and seamless connectivity across systems. The pressure to adapt is intensifying as mobile devices become travellers' primary planning and booking tools. Yet, Kohlmayr believes the next disruption is right around the corner. "Mobile is the dominant way of searching and exploring and dreaming right now, and also booking in many places. I think that's going to be replaced through AI chat bots fairly quickly." With the rise of generative AI, from tools like Gemini to ChatGPT, the hotel discovery process is starting to shift; consumers are now asking AI assistants for travel recommendations, and hotels need new strategies to ensure they appear in these AI-driven results. "For hotels, it's really, really critical to be AI optimised, not just search engine optimised or mobile optimised. The next wave of conversations... is about how do you AI optimise your business?" This transition requires a major rethink of hotel technology architecture. The traditional patchwork of systems-property management (PMS), central reservations (CRS), customer relationship (CRM), marketing platforms, and revenue management (RMS)-too often fails to operate as an integrated ecosystem. Kohlmayr points to a common mistake: "Sometimes decisions are made based on price, maybe, and on other factors than how well [systems] connect and how well they're future-proofing the hotel… Sometimes decisions are being made in isolation, and it's actually moving the business backwards instead of forwards." The consequences of this fragmentation are immediate and costly. Competitive hotels now expect fully connected tech stacks; lack of integration translates into missed opportunities and an inability to react to market shifts. "A typical hotel needs to make about 5 million pricing decisions, for example. And those pricing decisions need to happen all the time, day and night, weekends and weekdays." When systems aren't properly connected, not only is the guest experience undermined, but revenue lags behind competitors with more modern infrastructure. "We've seen people that had the right technology ecosystem in place were able to react much, much faster to changes in booking markets than people that didn't have that in place, and maybe were not even focused on if their rates aligned with current booking conditions because something changed on the weekend or during periods when people were not at work." Evidence points to the business case for integrated, automated revenue management technology. Kohlmayr references BYD Loft Hotel in Thailand, which has reported a 15% increase in revenue since adopting revenue management technologies. More broadly, research indicates system-driven approaches can lift net operating profits for owners by 4% to 15%. "There is a lot of data out there that proves that having the right technology in place and having the right tech stack in place that's connected... can significantly increase not just the top line, but also the bottom line." Beyond the back-office, automation is transforming the guest journey. With consumer expectations shaped by mobile-first brands and digital-native platforms, hospitality is under pressure to deliver speed, convenience and personalisation at every stage. "Automation enables me to select my room and enables me to bypass the front desk. It enables me to go through my entire journey without actually having to, if I don't want to, talk to a person when I'm on a business trip," says Kohlmayr. He believes that contactless check-in and mobile key access are "no longer futuristic and are becoming standard among global brands", further raising the bar for digital guest experience. This expansion of digital guest touchpoints brings a new challenge: personalisation across the many stages of the customer journey, from pre-booking to post-stay. Successful hotels, according to Kohlmayr, are those that map expectations to distinct phases-dreaming, decision, pre-arrival, arrival, in-stay, and post-stay-and use data to anticipate needs. "The best example of that is if you arrive at a hotel and you're walking through the doors, and when you come to the front desk, somebody greets you by name and already knows who you are before you have even mentioned your name, right?" However, he acknowledges that the industry is still catching up, particularly in delivering robust recognition and tailored service for loyal guests. Looking ahead, Kohlmayr highlights three forces set to redefine the industry: merchandising beyond room sales, the next generation of integrated tech stacks, and the infusion of artificial intelligence throughout the guest experience. "Everyone wants to merchandise and retail more than just the room... becoming more of a retail experience, not just a room stay experience, is a key objective. Digitising that and making it available online to pay and book these services online is going to be critical. And then, how do you infuse that with AI? How do you generate an experience that is enabled or enhanced through AI?" The convergence of digital integration, data-driven automation and artificial intelligence is reshaping not just competition, but customer expectations across hospitality. "If we're not able as an industry to cater to that, then guests will just vote with their feet and select the company or the hotel company that enables them to meet their expectations in digital journeys."
Scoop
5 days ago
- Scoop
Unlocking Cinematic AI Video: The Power Of Google Veo 3 API With Veo3API.ai
Article – Hugh Grant Unlike traditional video tools that require separate audio work, the Veo 3 API generates videos with natural, perfectly-timed sound. Dialogue, ambient noise, and even subtle audio cues are built directly into the outputlip-synced and immersive from the very first frame. Veo 3 is Google's next-generation AI video generation model, designed to revolutionize how we create cinematic content. Leveraging the power of multimodal generative AI, Google Veo 3 can turn simple text or image prompts into ultra-realistic 4K videos with synchronized audio, advanced lighting effects, and dynamic camera movements. Whether you're crafting a battlefield scene, an animated explainer, or a dramatic short film, Veo 3 understands physics, character consistency, and visual storytelling—making it a powerful tool for content creators, marketers, and filmmakers. To unlock the full creative power of Veo 3, developers and content creators can now use Veo 3 API —a seamless, programmatic way to generate high-quality videos directly within their platforms, apps, or automation tools. Whether you're producing short-form content, educational visuals, or marketing assets at scale, the Veo 3 API gives you direct access to advanced video generation features with speed, precision, and flexibility. Thanks to platforms like it's now easier and more affordable than ever to integrate Google Veo 3 into your workflow—with prices starting as low as $0.40 per video and support for fast, high-volume production. What Makes Veo 3 API a Game-Changer for AI Video Creation? Native Synchronized Audio Generation Unlike traditional video tools that require separate audio work, the Veo 3 API generates videos with natural, perfectly-timed sound. Dialogue, ambient noise, and even subtle audio cues are built directly into the output—lip-synced and immersive from the very first frame. Text-to-Video and Image-to-Video Support The API accepts both written prompts and reference images, making it easy to bring any concept to life. Describe a setting, emotion, or action—and the Veo 3 API responds with rich visual storytelling that feels hand-crafted. It's fast, flexible, and ready for everything from ads to short films. Advanced Scene Understanding What sets Google Veo 3 apart is how well it understands physical space. With built-in awareness of motion, lighting, and object interaction, it can simulate natural environments and lifelike behaviors—no post-production tweaks required. Character and Scene Consistency No more inconsistent faces or shifting backgrounds. Veo 3 API preserves continuity across shots, ensuring that characters, locations, and key elements remain stable and coherent. Ideal for brand narratives, dialogue-driven scenes, and long-form content. Intuitive Cinematic Camera Controls Creators can guide the lens like a director. Using descriptive prompts, you can control pans, tilts, zooms, and angles—allowing for fluid transitions and dynamic framing that add depth to every scene. Google Veo 3 API Pricing Comparison: Redefines Cost-Efficient Video Creation As AI video tools continue to gain traction, pricing transparency and cost-efficiency are becoming critical factors for developers and content creators alike. From indie studios to enterprise teams, access to the Veo 3 API can mean the difference between experimental limitations and creative freedom. So how do today's leading platforms compare? Most providers—including Replicate, and AIMLAPI—charge around $6.00 for an 8-second video with audio, or $0.75 per second. These rates can quickly escalate when producing longer clips or running multiple renders—making large-scale deployment expensive and restrictive. That's where changes the game. By offering both Veo 3 Fast and Veo 3 Quality modes, this platform provides unmatched flexibility and value. An 8-second Veo 3 Fast video with audio costs just $0.40, while a high-fidelity Veo 3 Quality video comes in at $2.00—delivering more than 60% savings compared to competing platforms. Platform Price (8s Video with Audio) Price per Second Supports Veo 3 Fast API (Fast) $0.40 $0.05 Yes (Quality) $2.00 $0.25 Yes $6.00 $0.75 No $6.00 $0.75 No AIMLAPI $6.30 $0.79 No Meanwhile, Google's official Veo 3 access via Vertex AI requires a subscription: $19.99/month for the Fast mode or $249.99/month for full feature access, with direct API usage priced at $0.75 per second. For many users, this cost—combined with limited preview availability—makes third-party access a more attractive route. With affordable, transparent pricing and full support for Google Veo 3 Fast API, is positioning itself as the go-to solution for scalable, real-time AI video creation—whether you're rendering a short clip or building a platform powered by generative video. How to Use the Veo 3 API with Using the Veo 3 API through is designed to be seamless and intuitive, whether you're a developer building new features or a content creator looking to generate dynamic, AI-powered videos. Here's how to get started: Step 1: Create an Account on Begin by signing up for an account on This gives you access to the dashboard, where you can manage your projects and access the Google Veo 3 API. Step 2: Generate Your API Key Once logged in, go to the API Key section and generate a personal access key. This key is required to authenticate and authorize all your video generation requests. Step 3: Try the Interactive Playground Before full integration, explore the Playground tool to test video generation using text prompts or image references. This step helps you understand how your inputs affect output quality, camera movements, and scene behavior. Step 4: Integrate the API into Your Workflow With your API key ready, you can start making requests from your application. Simply structure your input with the desired prompt, video duration, and other optional settings like aspect ratio or audio sync. The API will return a secure link to your generated video. Step 5: Review and Deploy Your Video Once your video is generated, download or embed it directly. Whether you're creating marketing content, social media visuals, or part of a larger production pipeline, the Veo 3 API makes it easy to go from concept to screen with just a few steps. Conclusion: The Smartest Way to Access Veo 3 As AI video generation enters a new era, tools like Veo 3 API are transforming how we create, communicate, and captivate. Whether you're producing immersive narratives, dynamic marketing visuals, or experimental creative work, Google Veo 3 offers unmatched realism, flexibility, and scalability. And with that power is now more accessible—and affordable—than ever. From fast, synchronized audio generation to cinematic camera control, it's a solution built for the future of video. For creators, developers, and businesses ready to lead in visual storytelling, Veo 3 API via is the smartest way to bring ideas to life—frame by frame.
