First of its kind AI model transforms a single photo into interactive, conversational video  SAN FRANCISCO, Dec. 23, 2025 /PRNewswire/ — New frontier AI researchFirst of its kind AI model transforms a single photo into interactive, conversational video  SAN FRANCISCO, Dec. 23, 2025 /PRNewswire/ — New frontier AI research

Lemon Slice Debuts with $10.5M in Funding and Unveils Real-Time Interactive Avatars

First of its kind AI model transforms a single photo into interactive, conversational video 

SAN FRANCISCO, Dec. 23, 2025 /PRNewswire/ — New frontier AI research and product lab, Lemon Slice, is building the future of interactive video by developing foundational technology that other companies integrate into their products. Today, the company launched Lemon Slice-2: the first real-time AI avatar model that turns any image into a live, conversational video call. No training data. No style limitations. Just one photo and the product creates an instant interactive experience with any character you can imagine. 

Existing avatar tools require users to upload videos, train custom models, or work only with photorealistic faces. Lemon Slice-2 is zero-shot: upload a single image—a corporate headshot, a beloved cartoon animal, a Renaissance painting—and start a real-time video conversation immediately. 

Lemon Slice-2 is launching today in two forms: an API for developers building interactive avatars into products, and an embeddable widget that lets merchants add a ‘video chat bubble’ to any website with a single line of code.The widget is like an AI support agent that users can see and talk to that captures attention, boosts conversions, and increases customer satisfaction.

“This is the first time since ChatGPT’s initial launch when I tried a product and thought ‘ah, so this is how people will talk to computers in the future,'” said Jared Friedman, Y Combinator Partner and Managing Director. 

Unlimited Use Cases from eCommerce & Sales Assistants, to Children’s Education to Healthcare and Coaching

The in-house developed, proprietary diffusion transformer video model, Lemon Slice-2, enables first-of-its-kind interactive, visual experiences that have not been possible until now. Educational tools for children become far more compelling and interactive when their favorite cartoon character is helping them study for an upcoming test. With Lemon Slice, a cute alien teaches math lessons, administers quizzes, and answers follow-up questions. Online shopping becomes more engaging when a virtual stylist can navigate the full site and model outfits or conversationally answer return policy questions. And rather than sitting in a doctor’s waiting room filling out forms, a virtual assistant conversationally guides patients through intake or answers preliminary questions about a medical procedure.

Lemon Slice’s Technical Breakthrough 

Lemon Slice 2 is built on a proprietary large-scale video diffusion transformer, similar in class to OpenAI’s Sora and Google’s Veo3 – but specialized for talking humans and optimized for real-time performance. The Lemon Slice-2 model is something developers can use to turn any voice agent or chatbot into an interactive video call.

Lemon Slice is the first to ship production ready real-time interactive video, not just a technology demo. Unlike existing avatar tools, Lemon Slice-2 generates every pixel from scratch, enabling full-emotion facial animation, hand gestures, and expressive whole-body movements. Only a few other labs have tech demos of real-time AI video, but Lemon Slice is the only company that has shipped a usable API or product.

“The primary complaint about AI avatars is that they lack realism and detract value. Our avatar models are charismatic and fun to interact with,” said Lina Colucci, Co-Founder and CEO of Lemon Slice. “In the future, all video will be interactive and personalized to whoever is watching. We’re building the technology that makes that possible.” 

Critical Guardrails to Keep Privacy and Safety at the Forefront

Lemon Slice has implemented significant guardrails to prevent unauthorized face and voice cloning, including consent attestation requirements and LLM-based content moderation. The widget clearly indicates to users they are chatting with an AI character. Terms & Conditions require that people only use photos and voices they have consent for. Users will be banned if they do otherwise. 

An Impressive Founding Team

The company has raised $10.5 million in seed funding from Matrix Partners, Y Combinator, Arash Ferdowsi (CTO Dropbox), Emmett Shear (CEO Twitch), and EDM-pop duo, The Chainsmokers, to accelerate development. Lemon Slice’s nimble team is led by co-founders Lina Colucci, Sidney Primas, and Andrew Weitz—PhDs who are also lifelong creators. Colucci is a ballerina, musician and vlogger, while Primas and Weitz grew up making home videos in the early days of YouTube. All three hold degrees from institutions including MIT, Harvard, Stanford, and Duke, and bring deep AI expertise—but it’s their shared love of visual storytelling that drives the company’s vision.

“People connect with faces, not text boxes,” said Ilya Sukhar, Matrix General Partner. “Lemon Slice is building charismatic, interactive avatars that give every chatbot a face. It’s the natural evolution of conversational AI.”

About Lemon Slice

Lemon Slice is a frontier AI research and product lab building the future of interactive video. The company believes all video will eventually be interactive—generated on the fly and personalized to whoever is watching. Lemon Slice is building both the core video foundation model technology and the platform layer to enable this new medium. Backed by $10.5 million in seed funding, the team of eight includes talent from MIT, Harvard, Stanford, CMU, and Duke with deep expertise in AI and a shared passion for visual storytelling. To learn more, visit lemonslice.com.

Press Contact:
Mary Devincenzi
[email protected]
408-761-4285

Cision View original content to download multimedia:https://www.prnewswire.com/news-releases/lemon-slice-debuts-with-10-5m-in-funding-and-unveils-real-time-interactive-avatars-302648920.html

SOURCE Lemon Slice

Disclaimer: The articles reposted on this site are sourced from public platforms and are provided for informational purposes only. They do not necessarily reflect the views of MEXC. All rights remain with the original authors. If you believe any content infringes on third-party rights, please contact [email protected] for removal. MEXC makes no guarantees regarding the accuracy, completeness, or timeliness of the content and is not responsible for any actions taken based on the information provided. The content does not constitute financial, legal, or other professional advice, nor should it be considered a recommendation or endorsement by MEXC.

You May Also Like

The Channel Factories We’ve Been Waiting For

The Channel Factories We’ve Been Waiting For

The post The Channel Factories We’ve Been Waiting For appeared on BitcoinEthereumNews.com. Visions of future technology are often prescient about the broad strokes while flubbing the details. The tablets in “2001: A Space Odyssey” do indeed look like iPads, but you never see the astronauts paying for subscriptions or wasting hours on Candy Crush.  Channel factories are one vision that arose early in the history of the Lightning Network to address some challenges that Lightning has faced from the beginning. Despite having grown to become Bitcoin’s most successful layer-2 scaling solution, with instant and low-fee payments, Lightning’s scale is limited by its reliance on payment channels. Although Lightning shifts most transactions off-chain, each payment channel still requires an on-chain transaction to open and (usually) another to close. As adoption grows, pressure on the blockchain grows with it. The need for a more scalable approach to managing channels is clear. Channel factories were supposed to meet this need, but where are they? In 2025, subnetworks are emerging that revive the impetus of channel factories with some new details that vastly increase their potential. They are natively interoperable with Lightning and achieve greater scale by allowing a group of participants to open a shared multisig UTXO and create multiple bilateral channels, which reduces the number of on-chain transactions and improves capital efficiency. Achieving greater scale by reducing complexity, Ark and Spark perform the same function as traditional channel factories with new designs and additional capabilities based on shared UTXOs.  Channel Factories 101 Channel factories have been around since the inception of Lightning. A factory is a multiparty contract where multiple users (not just two, as in a Dryja-Poon channel) cooperatively lock funds in a single multisig UTXO. They can open, close and update channels off-chain without updating the blockchain for each operation. Only when participants leave or the factory dissolves is an on-chain transaction…
Share
BitcoinEthereumNews2025/09/18 00:09
What is the Outlook for Digital Assets in 2026?

What is the Outlook for Digital Assets in 2026?

The post What is the Outlook for Digital Assets in 2026? appeared on BitcoinEthereumNews.com. The crypto market cap reached $4.3 trillion in 2025 as institutions
Share
BitcoinEthereumNews2025/12/25 03:23
Pudgy Penguins’ Non-Crypto Display Wraps Las Vegas Sphere, Potentially Elevating PENGU Brand Reach

Pudgy Penguins’ Non-Crypto Display Wraps Las Vegas Sphere, Potentially Elevating PENGU Brand Reach

The post Pudgy Penguins’ Non-Crypto Display Wraps Las Vegas Sphere, Potentially Elevating PENGU Brand Reach appeared on BitcoinEthereumNews.com. Pudgy Penguins,
Share
BitcoinEthereumNews2025/12/25 03:41