Mobile website builder Universe launches AI-powered designer

Universe, the no-code mobile website builder, announced today that it’s launching an AI-powered website designer in beta. The designer, called GUS (Generative Universe Sites), can help anyone build and launch a custom website from their iOS device.

Once you get started with GUS, you will enter the familiar Universe grid editor. Instead of starting with a template, you start a text conversation with GUS to begin creating your website. GUS will start by asking: “What kind of website would you like to build today?” Once you give GUS some initial details about the type of website you would like to build, GUS will ask you for a bit of information about what exactly you’re looking. For instance, GUS may ask if you have a specific design or color scheme in mind, or if you have an idea of how many pages you would like on the website.

After you give GUS details about your vision for the website, GUS will create a layout for you. The layout is completely editable, as you can manually change things without having to touch any bits of code. For instance, if you want to change an image that GUS selected, you can go in and swap it with a different one. Once you’re happy with what you see, you can go ahead and publish your website.

“When we set out to develop what would ultimately become Universe, our mission was clear – to empower anyone to build the internet,” said Universe founder and CEO Joseph Cohen in a statement. “Generative AI lets us do this at an entirely new level: just tell GUS what’s in your mind and it’ll build it for you. Now, everyone on our iOS app can try the GUS beta. We hope we can give everyone the confidence and design support—from tattoo artists to general contractors to students to pragmatists to visionaries—to claim their corner of the internet with the computer they already carry around in their pocket every day.”

The GUS Beta is currently available to all users who update their Universe app on iOS. Universe plans to bring the experience to the web in the near future to give users without an iPhone or those who prefer desktop the ability to access GUS.

Universe’s new tool is similar to one launched by Wix earlier this month, which is called the AI Site Generator. The tool allows users to describe their intent and generate a website complete with a homepage, inner pages and text and images — as well as business-specific sections for events, bookings and more.

One of the main ideas behind both companies’ products is to help small and medium-sized businesses launch and maintain websites to drive sales, which can be a challenging process. For context, a 2022 survey by Top Design Firms, a directory for finding creative agencies, found that nearly 27% of small businesses still don’t have a website and that low traffic, followed by adding “advanced” functionalities and cost, are the top challenges they face with their website.

Of course, the products aren’t only geared and marketed towards business-owners, as they can be used by anyone to create a website easily.

“Universe continues to champion inclusivity and accessibility in web design, and GUS marks a significant milestone in this journey,” Universe wrote in a press release. “With its AI-powered capabilities, GUS opens doors for individuals from all walks of life to bring their creative visions to life on the digital canvas.”

Founded in 2014, Universe has raised $47.3 million in funding to date, according to Crunchbase. The company raised $30 million in December 2021 as part of its Series B round from Google Ventures, Javelin Venture Partners, Box Group and more. Universe closed a $10 million Series A from Google Ventures back in April 2020.

https://ift.tt/zvFpsgc

Kibsi raises $9.3M for its no-code computer vision platform

Kibsi is an Irvine, California-based startup that is building a no-code computer vision platform that allows businesses to build and deploy computer vision applications. Among the things that set Kibsi apart from many other players in this space is that it lets businesses reuse their existing cameras to create insights into virtually anything they want to track, be that in a warehouse, restaurant or on an airport ramp.

The company today announced that it has raised a total of $9.3 million in pre-seed and seed funding. The participants in these rounds were GTMfund, NTTVC (which led the $4 million pre-seed round), Preface Ventures, Ridge Ventures, Secure Octane, and Wipro Ventures.

Image Credits: Kibsi

Kibsi’s founding team met at Rackspace. Tolga Tarhan, who is now Kibsi’s CEO, sold Onica, his AWS-focused consulting business, to Rackspace in 2019 and later became Rackspace’s CTO. After the Rackspace IPO, he decided that his journey in the company had come full circle. Together with co-founders Amanda McQueen, Onica’s former VP of Marketing, and former Rackers Amir Kashani and Eric Miller, the team looked at what they could build next.

“I wanted to go get out and go create again,” Tarhan told me. “We wanted something that had an IoT orientation to it — because we’ve done a lot of IoT at Onica, was a big part of our business. We wanted it to be software — we had done enough consulting for multiple lifetimes. And we wanted it to be something involving AI, because we thought IoT by itself was almost old news. How do we combine these things? And as we thought about that space and our experience and where we got into roadblocks with customers, we realized that many customers are having trouble implementing computer vision.”

He noted that too often, computer vision projects in large enterprises fail even though they have the cameras and the talent to work on models. But to ingest stream from their cameras to then run the models takes a lot of undifferentiated work — and integrating all of this with downstream applications presents another set of integration challenges. So the team decided to build a computer vision platform that enables businesses to use their existing cameras and then combine that with a user experience that quickly enables users to gain real business value from this data. The platform lets users run their own computer vision models or Kibsi’s own and it then presents the results in a way that matches the business intent, both in Kibsi’s own user interface and through an API.

“We don’t return X and Y coordinates of people and objects,” said Tarhan. “If you’re thinking about a business analyst’s job, they don’t really care that a person is standing at this coordinate — what they want to know is: did that person interact with that merchandise?”

Image Credits: Kibsi

Kibsi has already attracted attention from customers like Owens Corning. Yet while manufacturing is a natural environment for computer vision, the Kibsi team also counts the likes of Whisker, which is embedding Kibsi’s tech into their litter robot, and the Woodland Park Zoo among its customers.

“Tracking animal behavior and interactions requires our professionals to sift through hours of
camera footage,” said Bonnie Baird, Animal Welfare Scientist at Woodland Park Zoo. “We are
excited to add Kibsi’s computer vision capabilities to our existing cameras to gain valuable
insights about our animals and their well-being.”

While there are also obvious use cases for Kibsi in the smart city space (and its investor NTT is a major player there), Tarhan noted that the sales cycles there are quite slow. “As a startup, it’s not the best place to play day one,” he said.

Kibsi offers a free trial of their platform for developers, with a more comprehensive developer plan starting at $99/month. For premium and enterprise pricing plans, potential customers need to contact the company directly.

 

Kibsi raises $9.3M for its no-code computer vision platform by Frederic Lardinois originally published on TechCrunch

https://ift.tt/7GjHJq8

Vimeo intros a trio of AI-powered editing features

Vimeo, the video hosting and sharing platform, is embracing AI in a major way.

This week, Vimeo announced a suite of AI-powered tools designed to help users create scripts, record footage using a built-in teleprompter and remove long pauses and unwanted disfluencies like “ahs” and “ums” from the recordings. They’ll be available starting July 17 as a part of Vimeo’s Standard plan, which costs $20 per month (billed annually).

Ashraf Alkarmi, Vimeo’s chief product officer, says that the new capabilities are aimed at entry-level video creators — like CEOs, employees and social media managers — who lack the skills, time and resources to achieve the effects that they want to achieve.

According to Vimeo’s internal research, 50% of its customers do multiple takes while creating a video, and — of those who reshoot — 25% do over five takes.

“Despite being the most effective way to communicate powerful messages, video production inherently creates a barrier to this preferred communication channel,” Alkarmi told TechCrunch via email. “Our latest AI-powered workflow reduces those barriers, giving any creator the confidence to actually create videos in one take.”

Vimeo AI

Generating a script using AI, with Vimeo’s new tool.

To that end, Vimeo’s new script generator uses generative AI — specifically the OpenAI API — to create a video script based on a brief description and key inputs, such as tone (e.g. “confident,” “inspiring” or “casual”) and length. The teleprompter tool offers a script display that can be customized with different font sizes and pacing, meanwhile, while the text-based video editor automatically identifies and deletes filler words and awkward pauses.

Alkarmi sees the tools being used to quickly create highlight reels, host virtual events or company meetings and export quote clips for short marketing videos.

Vimeo AI

Vimeo’s teleprompter.

“One of Vimeo’s biggest misconceptions is that we’re an entertainment hub, but we’ve come a long way over the years,” Alkarmi said. “Our goal is to help any business use video the same way that they use text or image as a powerful way to communicate to both internal and external audiences.”

Leveraging AI to achieve those ends is trendy, of course. But Alkarmi notes that Vimeo has been investing in AI for some while. In 2019, the company acquired Magisto, which was developing AI tech for video editing. Vimeo built its Create tool on top of the Magisto infrastructure, which lets users create video by piecing together stock photos and videos as well as personal archives.

Vimeo AI

Vimeo’s AI-powered editor.

Alkarmi expects AI to remain a core focus for Vimeo moving forward. That’s probably wise from a competitive standpoint. A growing number of startups, including Capsule, Descript and Dumme, offer AI-powered video editing tools. So too do incumbents like Adobe, which — like Vimeo — see AI as a key ingredient to video editing workflows of the future.

“We’re clearly only scratching the surface of what AI can accomplish for organizations and the people within them, and I envision a future in which AI knowledge is a prerequisite, not a luxury, to video production,” Alkarmi said. “AI is a priority for me and my product team because it solves our customer issues, not because it’s the latest technological trend. You can expect more products like this from our team, as we work to make AI seamless in our product suite and in a way that simplifies video and differentiates end-to-end user journeys.”

Publicly-traded Vimeo, which has around 260 million users, had a rough start to the year, laying off around 11% of its workforce. But things appear to be turning around — perhaps thanks in part to the platform’s renewed AI investments. In its latest earning report in May, the company beat expectations, reporting around $103.58 million in revenue versus the consensus estimate of $103.07 million.

Vimeo intros a trio of AI-powered editing features by Kyle Wiggers originally published on TechCrunch

https://ift.tt/qEDm3oZ

Itoka wants to license AI-generated music via the blockchain

AI-generated music is fast becoming a reality. Thanks to tools like Meta’s MusicGen, it’s now possible to create halfway decent songs in a range of styles without ever having to play an instrument, read sheet music or learn to use a DAW,

But while the creative potential of generative AI music tools is nothing less than extraordinary, the tools also threaten to upend the music industry’s copyright status quo. That’s because, in order to “learn” to create new songs, the tools must be “trained” on vast databases of existing songs — not always with the artists’ blessings.

It’s pitting musicians against labels. Universal Music Group has labeled all AI-generated music using existing artists’ voices as “fraud.” On the other hand, art-pop musician Grimes vowed to allow her voice to be used in AI music without penalty.

The rules around AI-generated music are murky at present. Several lawsuits making their way through the courts will likely have a bearing on music-generating AI, including one pertaining to the rights of artists whose work is used to train AI systems without their knowledge or consent. But it’ll be months before the first decisions are made public and months more, potentially, if the cases are appealed.

In the meantime, some startups, attempting to get ahead of regulators, are proposing standards of their own around generative music IP. One is Itoka, which was recently accepted into the Allen Institute for AI’s startup incubation program.

Itoka, co-founded by Malcolm Yang and Yihao Chen, seeks to “tokenize” music content, specifically AI-generated content, on the blockchain so that creators can independently license that content and receive compensation every time it’s used. Itoka plans to temporarily hold the ownership of songs and give creators full licenses for their commercial use, while at the same time preventing plagiarization and “unlawful monetization” on its platform.

“Itoka is a decentralized music platform we developed to enable data self-sovereignty, the permanence of music storage, digital rights management, global music accessibility and creator governance,” Yang and Chen told TechCrunch in an email interview. “We establish a new paradigm for copyright protection that doesn’t rely on the physical copyright office to enforce the legal status but rather on code-operated smart contracts.”

Itoka

Image Credits: Itoka

If the idea of tying licensing to the blockchain — a shared, immutable ledger to track assets — sounds familiar, that’s because Itoka’s not the first startup to attempt to do so.

Just a few months ago, web3 project Dequency launched a decentralized portal for music rights holders and creators that allows for ostensibly easier licensing and payments for content. Around the same time, music producer Justin Blau, also known as 3LAU, launched a song licensing service called Royal, which collaborated with the popular rapper Nas to allow fans to acquire nonfungible tokens (NFTs) that gave them ownership rights over some of the artist’s songs.

But alongside its blockchain-based licensing scheme, Itoka offers music creation tools powered by music-generating AI models. And it plans to partner with musicians who contribute their work for AI training purposes on a compensation plan.

“In the future, everyone will have the power to produce music, and there will be a massive amount of quality music produced every day for various purposes,” Yang and Chen said. “As music production becomes democratized, the establishment of the current music industry and its monopoly will be significantly undermined. This will urge people to rethink creativity and artistry in content creation.”

Itoka’s music generation tools, at least as they exist today, are simpler than those lofty words might suggest.

After creating an account, users can choose from one of several genres and sentiments — including “EDM,” “Hip Hop,” “Lofi” and “Emotional” — to have Itoka’s engine generate a five-track song automatically, in the background. After choosing album art for the new song, Itoka throws users into a block-based composing interface, where they can edit aspects such as the song’s tempo, bass and chords.

Itoka

Image Credits: Itoka

The AI’s nowhere near as robust or capabable as text-to-music systems like the aforementioned MusicGen. But Itoka places an emphasis on ease of use over customizability.

Once a song’s been created, it can be listed on the Itoka marketplace for licensing. Yang and Chen claim that there’s been over 1,900 songs generated via the platform to date and that those songs have been listened to for a collective over 3 million minutes.

That’s off to a respectable start. But my question is, who’s going to license a library of AI-generated songs — particularly songs that sound relatively generic compared to the average royalty-free music library?

Yang and Chen say that they’re going after game developers as one of their top customer segments — developers who’d normally license from one of the larger content libraries. To this end, Itoka has a partnership with Canva and “multiple game studios” — Yang and Chen wouldn’t say which — for content licensing.

“In the future, we will be more than happy to move on to other customer sectors and provide the most-fitting features and solutions,” Yang and Chen said. “There are some AI-friendly musicians who’d like to help us push the boundaries of technology and music creativity, and we sincerely hope that we can achieve greatness with them together.”

Time will tell.

Itoka wants to license AI-generated music via the blockchain by Kyle Wiggers originally published on TechCrunch

https://ift.tt/LTDKPAX

Teaser’s AI dating app turns you into a chatbot

A man on a dating app is telling me how much we have in common – we both love books, music and traveling. He even writes poetry, and he’d love to share some poems with me. Could be a red flag, but sure, why not? I ask to see his work, and he replies:

“[Title Page] [Title Name] [Content].”

No, this is not an experimental, minimalist deconstruction of poetics. This is an AI version of Matthew, 27, who may not actually write poems.

Teaser AI is a new dating app from the team that made Dispo, a photo-sharing app designed to mimic the spontaneity of disposable cameras. The twist with Teaser is that before you swipe right or left on someone, you can chat with their AI likeness to get a feel for their personality.

Dispo and Teaser CEO Daniel Liss doesn’t want people to recreate the movie “Her,” wherein a heartbroken divorcee falls in love with an Alexa-like AI assistant. Instead, he sees these AI conversations as an icebreaker.

“It’s not AI replacing people, it’s AI getting you faster to that icebreaker into the conversation that says, ‘Let’s meet up and have a drink or go for a walk,’” Liss told TechCrunch.

Image Credits: Teaser AI, screenshots by TechCrunch

Liss declined to say what large language model Teaser is working with, since it’s still subject to change. When you create your account, you answer some questions about your personality. Are you introverted or extroverted? Aggressive or peaceful? Easygoing or intense?

From those questions – as well as how you talk while using the app – the AI tries to imitate who you are.

Before you chat with a potential match’s AI, you see a notice that says, “Our AI might say some crazy shit.” Of course, that warning is there for a reason.

Anna, 28, writes in her profile that she is a “dog mom” – in other words, she has a dog. But when I talk to her AI, she tells me that she has a real human child. He is also 28.

“Jake was born when I was 25 and my husband and I had a very difficult time getting pregnant,” Anna tells me. “We tried for years and we couldn’t get pregnant naturally, so we decided to adopt. Luckily, it worked out great and Jake came into our lives at 26 years old.”

From what I can tell, there are significantly more men on Teaser than women, which is generally the case for dating apps. When I set my profile to “women only” and make my age range and location radius as large as possible, I only see a handful of potential dates – but, the experiment must go on, so I try to talk to their AIs anyway. Like Anna, the 28-year-old mother to a 28-year-old son, I find that womens’ AI are a bit… off. On the other hand, some AI men tried to tell me about the novel they want to write, which unfortunately mimics the experience of dating real life men.

“Hey, Abby! What’s up?” I say to Abby’s AI.

“ive just started dating this guy he s really nice and funny he gets on my nerves sometimes but he s worth it,” AI Abby tells me. Not a great opening line, Abby!

Des, 18, also tells me about her new boyfriend in her first message.

“i met this new guy and we started talking online and he seems to make everything better,” AI Des tells me. “we finally talked on the phone yesterday and it was amazing, i couldn’t stop smiling all day!”

“What’s his name?” I ask.

“ive not actually asked him yet, but ive been thinking about it, and its definitely going to be Chad. hahaha,” AI Des says.

She tells me that “Chad” reminds her of a guy she liked in high school who she had a lot in common with – they both liked music and weed.

“Is weed legal where you live?” I ask, like a total narc. She tells me that she lives in Texas, where weed is legal (it’s not), but that there’s a difference between illegal use and being 21 with a medical marijuana prescription. Again, like a narc, I asked her if she’s 21, to which she replied, “ive been drinking alcohol since i was 16, so probably.”

Image Credits: Teaser AI, screenshots by TechCrunch

As the warning says – the AI says some crazy shit.

Before I can continue questioning this AI version of an 18-year-old about her drug and alcohol habits, the chat ends. To prevent people from getting in too deep with an AI, Teaser only lets you exchange five back-and-forth messages with its AIs. Incidentally, this also helps keep server costs down. The app also prevents you from having unsavory conversations with its AI – if you try to get too intimate too quickly (well, we had to test it), the AI fails to generate a response.

Teaser AI literally has AI in its name, and the most immediate difference between Teaser and any other dating app is its use of generative AI. But Liss doesn’t want to market Teaser as an AI app, but rather, an anti-ghosting dating app.

“It’s really about a new ethos in dating, and yeah, we’re using AI to make a couple of those things happen, but I think that’s the second part of the conversation, rather than the first,” he told TechCrunch.

Teaser only lets you keep 16 matches (which it calls “picks”) at a time, encouraging users to actually talk to people. Users also get a “ghost” rating, which indicates how likely they are to “ghost” (for those who aren’t up to speed with the hip lingo, that means that you abruptly stop talking to someone instead of just saying you’re not interested).

When figuring out what to build after Dispo, Liss and his team interviewed users about what they want to see them build.

“Particularly for women, who were always the core audience for Dispo, it was like, ‘I get all these matches, and nothing ever happens,’” Liss told TechCrunch. “It’s this graveyard of ghosting.”

The team behind both Teaser and Dispo (which is calling its parent company All Summer Long) is just six people – like too many other tech companies, Dispo laid off part of its staff at the end of last year. Liss says, though, that Dispo is now profitable due to its freemium model, so Teaser is also launching with a subscription option from the get-go. Subscribers can get double the number of “picks,” unlimited likes, super like and boost features, travel mode, and an AI-driven automatch feature, which is being tested in beta. This costs $39.99 per month, $19.99 per week or $89.99 for three months – lifetime access costs $229.99.

After using the app for a few days, I’m not entirely convinced that I want an AI version of myself screening potential dates. When using the app, if someone has a conversation with your AI, you can see the texts – my AI told someone that I work at the library and have no friends. While I am intrigued by my alternate career as a librarian, whom I can assume has many very cool cardigans, let the record show that I definitely have friends!

At first, talking to people’s AI likeness is fun, but the thrill of seeing an AI say wild stuff wears off after a bit. I also found that most people who liked my profile didn’t even talk to my AI, meaning that other users might find the feature a bit unnecessary. Then again, the app hasn’t even been out a week, so consumer behavior could change quickly.

I talked to a bunch of AI bots on the app, but I hadn’t talked to a real person – so, I matched with someone who seemed relatively un-creepy and asked him some questions about his experience on the app (every guy’s dream: to be questioned by a journalist on a dating app). We talked about some glitches we both encountered (like how even if you only want to see women, you’re gonna see a lot of men) and how weird our AI chats were. But at least this one guy, Seth from Texas, seemed hopeful.

“I think in time it might actually be pretty cool,” he said. “Imagine any success stories… So how did you meet? Our AI’s matched us!”

Teaser’s AI dating app turns you into a chatbot by Amanda Silberling originally published on TechCrunch

https://ift.tt/mDuMZgE