Lately, the AI photo "resurrection" technique has caused quite a stir online, and Heygen finally couldn't resist, launching its lip-syncing tool.
All you need to do is upload a photo and an audio clip, and the person in the photo will start speaking, singing, or even reading based on the audio content. Moreover, it currently supports audio clips up to 20 seconds long, meaning you can create a 20-second video. Even more impressive, the tool can identify the main voice and ensure that the lip movements and expressions in the video are perfectly synchronized with the audio.
However, there is a small drawback. It seems that Heygen has set a barrier for Chinese users, as they are currently unable to log in or register new accounts. This may disappoint many friends who are interested in this technology.
Setting this aside, Heygen's development momentum is still quite strong. Just this June, Heygen raised $60 million in a round of funding at a valuation of $500 million. This round was led by Benchmark, with participation from well-known investment firms such as Conviction, Thrive Capital, and Bond Capital. As part of the deal, Benchmark partner Victor Lazarte will join Heygen's board of directors.
To date, Heygen has raised a total of $74 million. This startup, founded in 2020, is one of many that utilize generative AI technology to produce videos at a lower cost and in a more convenient manner. Heygen's tools allow anyone to create realistic avatars, speak using their own voice, and even translate into multiple languages.
Experience link: https://labs.heygen.com/guest/expressive-photo-avatar
