Something magical is happening to videos

AI is changing everything and it is changing videos too. One step at a time. The act of meddling with camera for multiple takes to record a perfect video is being replaced by seamless one-click control to modify what and how you said in a video

Our aim at sync. is to lead this shift. by building magical tool that will enable everyone to just record once and create forever. Already using sync., several days of manual editing to modify lips to match the audio is replaced by AI lipsync in minutes. Traditional dubbing is being replaced by visual dubbing and millions of personalised videos generated in hours. Going forward, we hope sync. will let you modify humans in video so that you’ll never have to reshoot ever again — modify what is said and how it is said in a video including emotions and body language

We have a long road ahead of us. Today we announce our seed round while reflecting on our journey so far

Starting out of Computer Vision lab at IIIT Hyderabad in India as open-source tool Wav2Lip in 2020 as a first of it’s kind AI lipsync tool with 10k+ stars on Github and getting into YCombinator Winter ‘24 batch, graduating as one of the fastest growing start-up in the batch raising 5.5M in seed round. It’s been quite a journey for us at sync.

We formed a fantastic initial team that includes young and smart ML engineers, researchers in computer vision under Prof Andrew Zisserman and Prof. Jawahar who have contributed a lot to cv community. Together we can build SOTA vision models and serve them efficiently to billions of users

we raised $5.5M in seed round led by Google Ventures and participation from YCombinator, Creator ventures, Rebel Fund and multiple other awesome investors

We're incredibly excited about the future of video. If you are too, perhaps you should consider joining us.