ByteDance Suspends Seedance 2 Feature That Turns Facial Photos Into Personal Voices Over Potential Risks (technode.com)
(Tuesday February 10, 2026 @10:45PM (msmash)
from the too-good-and-true dept.)
- Reference: 0180766992
- News link: https://yro.slashdot.org/story/26/02/10/1913223/bytedance-suspends-seedance-2-feature-that-turns-facial-photos-into-personal-voices-over-potential-risks
- Source link: https://technode.com/2026/02/10/bytedance-suspends-seedance-2-0-feature-that-turns-facial-photos-into-personal-voices-over-potential-risks/
[1]hackingbear writes:
> China's Bytedance has [2]released Seedance 2.0 , an AI video generator which handles up to four types of input at once: images, videos, audio, and text. Users can combine up to nine images, three videos, and three audio files, up to a total of twelve files. Generated videos run between 4 and 15
>
> Its performance is unfortunately so good that it has forced the firm [4]to block its facial-to-voice feature after the model reportedly demonstrated the ability to generate highly accurate personal voice characteristics using only facial images, even without user authorization.
>
> In a recent test, Pan Tianhong, founder of tech media outlet MediaStorm, discovered that uploading a personal facial photo caused the model to produce audio nearly identical to his real voice -- without using any voice samples or authorized data. [...]
[1] https://slashdot.org/~hackingbear
[2] https://the-decoder.com/bytedance-shows-impressive-progress-in-ai-video-with-seedance-2-0/
[3] https://technode.com/2026/02/10/bytedance-suspends-seedance-2-0-feature-that-turns-facial-photos-into-personal-voices-over-potential-risks/
[4] https://technode.com/2026/02/10/bytedance-suspends-seedance-2-0-feature-that-turns-facial-photos-into-personal-voices-over-potential-risks/
> China's Bytedance has [2]released Seedance 2.0 , an AI video generator which handles up to four types of input at once: images, videos, audio, and text. Users can combine up to nine images, three videos, and three audio files, up to a total of twelve files. Generated videos run between 4 and 15
[3]or 60
seconds long and automatically come with sound effects or music.>
> Its performance is unfortunately so good that it has forced the firm [4]to block its facial-to-voice feature after the model reportedly demonstrated the ability to generate highly accurate personal voice characteristics using only facial images, even without user authorization.
>
> In a recent test, Pan Tianhong, founder of tech media outlet MediaStorm, discovered that uploading a personal facial photo caused the model to produce audio nearly identical to his real voice -- without using any voice samples or authorized data. [...]
[1] https://slashdot.org/~hackingbear
[2] https://the-decoder.com/bytedance-shows-impressive-progress-in-ai-video-with-seedance-2-0/
[3] https://technode.com/2026/02/10/bytedance-suspends-seedance-2-0-feature-that-turns-facial-photos-into-personal-voices-over-potential-risks/
[4] https://technode.com/2026/02/10/bytedance-suspends-seedance-2-0-feature-that-turns-facial-photos-into-personal-voices-over-potential-risks/
Are there any examples? (Score:2)
by liqu1d ( 4349325 )
I'm finding it a tad hard to believe an AI can guess someone's voice correctly from a photograph.
Typical AI use (Score:2)
This is practically a stereotypical AI use - look for associations in a massive database, inducing a formula from that data and then reversing the process to deduce a conclusion based on new data.
It is rather obvious that bone structure should both affect one's voice and also be observable via a picture, but at the same time involve such massive calculations that humans would be surprised by it.