Elja Trum

Microsoft lets portrait photos talk with AI

Wednesday 1 May 2024, 13:31 by | 2,686 views | 3 comments

This article was translated from Dutch with the help of AI. Read the original.

Microsoft's VASA-1 AI model can make a single portrait photo talk and sing realistically. The company does not want to release the programme for fear of misuse in deepfakes, but someone else will probably do it with something similar.


The input can be an audio file, or simply a chunk of text. As you can see in the video, this can happen entirely in real time. So it can even be used in live streams.

On the research page, you can see many more examples of the software.

Share: WhatsApp Facebook
Elja Trum

About the author

Elja Trum is the founder of Photofacts and online photography course website Photofacts Academy. He has been writing about photography since 2006. Elja is also the author of (Dutch) books on composition, black-and-white photography, flash photography and portrait photography.

Show every article in Science

3 comments

  1. Donald Willemsen
    Donald Willemsen wrote on Tuesday 7 May 2024 at 11:12  | reply

    A development that certain groups will be only too happy to misuse to seize power and destroy democracy.
    Just take a look at the Gaza Strip, where the Israeli army selects targets based on AI. That has already cost more than 35000 lives.
    It is also being massively misused to spread disinformation, such as what is happening around elections in the US, Russia and the EU.
    A development that we need to start regulating heavily in order to give the positive sides of AI a fair chance.

    Translated from Dutch.
  2. Rob IJsselstein
    Rob IJsselstein wrote on Tuesday 7 May 2024 at 16:32  | reply

    MyHeritage's genealogy site has offered that possibility for a year already. The person can tell their life story based on the information the user has in the family tree. Very fun if you only know the person from a photo, creepy if you know the person well. Quite special, and nothing wrong with it.

    Translated from Dutch.
  3. Donald Willemsen
    Donald Willemsen wrote on Tuesday 7 May 2024 at 18:39  | reply

    Rob, completely pointless and has nothing to do with photography. Just because it can be done doesn't mean it should be. For Myheritage, it's simply a business model. Myheritage is expensive enough without that useless addition.

    Translated from Dutch.

Have your say

Please note: Articles older than a week can only be commented on by signed-in visitors.
Would you still like to comment? sign in or create a free account.

Become a better photographer every week

A practical photography tip in your inbox every week.
39,213 photography enthusiasts already receive the tips! More about the weekly mail. Or keep up to date via Facebook. Sign-up secured with Google reCaptcha.

Elja Trum

Elja Trum

Photofacts; everything to do with photography!

Would you like to take better photos and keep up with what is happening in photography? Photofacts publishes articles that teach you something about photography — from a product announcement to a practical shooting tip or a look at a website. Photofacts covers photography every day and is a hobby project of Elja Trum's that got out of hand. The articles are written by a team of volunteer authors. If you would enjoy writing one or more articles for Photofacts, do get in touch.More about Photofacts

Photofacts is made possible in part by


We use cookies to make Photofacts work properly. Read our cookie policy. got it