This New Video-Based AI-Powered Tool Lets You ‘Speak’ In Another Language

HeyGen, a generative AI video program, has unveiled a new feature that allows users to seamlessly translate their spoken content into different languages while maintaining perfect lip synchronization.

Traditionally, video translation involved the use of subtitles or dubbing, but HeyGen’s new technology aims to eliminate the need for these approaches. 

Users can now record a video in their native language, and HeyGen’s AI takes care of overdubbing the content in a language of their choice, with what it touts is “native-like fluency.” The program also superimposes realistic mouth movements on the video, creating a convincing illusion of the speaker using the chosen language. 

Selkirk Copper Mines — sponsored Sponsored · Selkirk Copper Mines

Currently, HeyGen supports translation into several languages, including English, Spanish, French, Italian, German, Polish, Portuguese, and Hindi.

The company, which was originally called Movio before a rebranding in April, also recently launched a way to create a “personal deepfake” or an AI-generated video double that can say practically anything you type into a text field. Its founder, Joshua Xu, says this new product is “more than just a translation feature; it’s a new paradigm for content consumption.”

To experience it for yourself, you’ll need to record a video of at least 30 seconds up to a maximum of 5 minutes, in mp4, Quicktime, or Webm format, with a file size not exceeding 500 MB and upload it here.

X user Jon Finger posted a test on Monday and the results, while still not completely natural-looking, were pretty astonishing.

In a reply, a native French speaker pointed out that the language Finger “spoke” was “technically perfect” but the accent was more French-Canadian or Québécois.

The potential impact of this technology extends to various industries, including content creation and localization. As HeyGen continues to refine its system, it could reshape the landscape of video translation and potentially impact industries like dubbing. And also, more deepfakes.


Information for this story was found via HeyGen, Jon Finger on X, and the sources and companies mentioned. The author has no securities or affiliations related to the organizations discussed. Not a recommendation to buy or sell. Always do additional research and consult a professional before purchasing a security. The author holds no licenses.

Video Articles

A $2.2B Gold Project Is Outgrowing Its Plan | Michael Henrichsen – Gold X2 Mining

Pay for the Copper, Get the Gold Free | Rob McEwen – McEwen Inc

This Gold Discovery Was Already Huge. Now It’s Becoming a Monster. | Goliath Resources

Recommended

Golden Cariboo’s First Quesnelle Resource Estimate Tallies 1.19 Million Gold Equivalent Ounces

Brixton Wraps Camp Creek Drilling With 17.58 Metres of 1.47 g/t Gold Equivalent

Related News

OpenAI’s GPT-4o-Powered ChatGPT Is Now More (Terrifyingly) Conversational and Life-Like

OpenAI on Monday announced GPT-4o, a new flagship generative AI model that expands on the...

Tuesday, May 14, 2024, 05:32:00 PM

Japan’s Government Foregoes Copyright Enforcement on Data Used for AI Training

The Japanese government recently asserted that it would not require copyrights on data used in...

Saturday, June 3, 2023, 07:15:00 AM

Is AI Taking Away Entry Level Fast Food Jobs?

Automation and artificial intelligence (AI) are everywhere. One of the recent areas of significant penetration...

Sunday, July 23, 2023, 01:26:00 PM

From RSS to Robo-Pinkerton: Feedly AI Invites You to Track Protests “Posing Risks to Your Company’s Assets”

Researcher Rick Claypool couldn’t help but draw on the Pinkerton analogy when he discovered that...

Friday, March 31, 2023, 03:02:00 PM

Sam Altman Wants To Raise Trillions For The Future Of AI

OpenAI CEO Sam Altman wants to transform the global semiconductor industry. The catch: he needs...

Friday, February 9, 2024, 10:38:00 AM