Way2Lip promises to reduce pain in creating video content
Even as celebrities and those in power fear deepfake technology threatens their reputation, a Hyderabad-based start-up has developed an artificial intelligence-based solution that promises to revolutionize the way media, businesses information technology and film production houses create visual content. content.
All it takes is a one minute video footage of a person talking about any topic and the Way2Lip solution developed by NeuralSync AI can video that person talking for hours. The technology allows the person in the video to make perfect lip movements for the text that is fed into the system.
“It’s exactly as if this person was speaking or reading the text. Why, you can even make characters from the popular movie Pushpa speak in different (dubbed) languages with perfect lip movement, regardless of whether different dubbing artists lend their voices,” said Pavan Reddy, CEO of NeuralSync AI. Activity area.
The AI-based solution captures the nuances of how lips are moved to spell words and juxtaposes them as new words or dialogue are fed into the system.
“Unlike similar tools available in the market, it is language and voice independent and works on any face, including CGI faces,” said Rudrabha Mukhopadhyay, Founder and CTO of NeuralSync AI.
“It all started with Rudrabha’s PhD project on the subject at IIIT-H. We translated the idea into a commercially viable technology solution. We are incubated at the institute,” Reddy said.
Feed the scenario
The product allows users to feed a script and select an avatar of their choice, or create their own avatar with different backgrounds and create videos in minutes.
“Alternatively, users can also upload a video and audio pair to the platform to generate lip-synced videos,” Reddy said.
Within two months of its soft launch, NeuralSync AI has already signed two major customers, including a US media house that uses it to generate news and analytics videos.
“An edtech company in India is also using the technology to generate videos for their students,” he said.
Mukhopadhyay said the technology reduces operating costs and the time needed to produce a video.
“With the entry of AI into video production, those inconsistent lip movements will be a thing of the past,” he said.
After building a solution for the media and edtech industries, NeuralSync AI is working on a version to meet the needs of the film industry.
Pay for use
It charges $3-4 for a simple talking head for one minute. If there is more than one person in a frame, NeuralSync AI will charge $10 per minute. The start-up is in talks with a few Bollywood and Tollywood filmmakers, who have started making stunning pan-Indian films.
NeuralSync AI now aims to further improve the product and achieve global scale by joining an international incubator in the United States.
May 06, 2022