Synthetically generated versions of real people which can be can be programmed to say anything sounds like a scenario from the latest episode of Black Mirror.
But in fact, production-grade video-based characters based on real people – which can talk about any product or subject at all, in a hyper-life-like manner – are arguably going to be part of the next wave in areas like e-commerce and remote learning. Further, a Hollywood celebrity could simply license out their avatar to explain products, at a scale that would make it impossible to physically film. But perhaps more realistically, ‘digital twins’ like this make much more convincing videos than invented characters, because of their human-like qualities.
The market for this technology is expanding. Key players in the space include SoulMachines (which has raised $135M) and Synthesia (raised $66.6M).
Back in 2020 we reported how Hour One, a New York and Tel Aviv startup which creates AI-driven synthetic characters based on real humans, had closed a $5 million seed funding round.
It’s now raised a $20 million Series A funding round led by Insight Partners. Also participating in the round was Galaxy Interactive, Remagine Ventures, Kindred Ventures, Semble Ventures, Cerca Partners, Digital-Horizon and Eynat Guez.
The startup plans to expand its Reals platform, a self-service platform allowing businesses “to create human-led video automatically, from just text, in a matter of minutes” said the company in a statement.
This, says the firm, converts people into virtual human characters for commercial and professional use cases. The human is first captured on video, then Hour One’s AI generates a virtual twin. This could be a virtual receptionist, salesperson, HR representative or language teacher, for example.
To some extent, Hour Pen’s view that the shift to remote work has meant video and more immersive media – such as for educational content – has become much more important, is correct. Therefore this kind of video people well be expanded.
Hour One CEO and Founder Oren Aharon said in a statement: “Very soon, any person will be able to have a virtual twin for professional use that can deliver content on their behalf, speak in any language, and scale their productivity in ways previously unimaginable.”
“The power and accuracy of generative AI continues to improve at an extremely rapid pace, and Hour One is at the vanguard,” added Lonne Jaffe, Managing Director at Insight Partners. “You just type in some text, and behind the scenes the incredibly scalable Hour One infrastructure creates a fluid and realistic video of an avatar talking along with matching voice and graphics. The team’s grand vision is to be able to embed this extraordinary capability within any software product or allow it to be invoked in real-time via API.”
Berlitz, the language and culture training giant, now uses Hour One to generate video, featuring virtual instructors across thousands of its videos. Hour One has also partnered with NBCUniversal, DreamWorks and Cameo, the latter of which allows celebrities to record paid videos for fans.
The appearance of the likes of SoulMachines, Synthesia and Hour One raises questions about how this technology might well also be abused. Watermarking videos as ‘artificial’ might be one way to prevent this, but we are still swimming in uncharted waters here. Hour One says it has an ethical policy code for how its technology is used.
We are definitely going to see some ‘interesting’ scenarios appear around this technology, which is proliferating much faster than the startups themselves.