Audio Deep Fake / ESPESY

This is not the former German chancellor Angela Merkel. However, the voice you hear is amazingly close to the original. Don’t you think?

With deep fake technology, it is possible to imitate people in virtually all their typical human expressions. Today you can already fake the visual appearance of people deceptively real, e.g. their faces, facial expressions and bodily movements. Of course, the human voice is another exciting field to investigate.

Soon, as voice technology matures further, we won’t be able to distinguish between real and AI-generated voices. Unique voice and speech qualities such as timbre, rhythm, tempo, intonation, linguistic and emotional expression can be imitated 100%.

❓ Promising future or terrifying dystopia?

❗️ We need to talk – person to person!

Note: the voice in our audio sample was generated by our own artificial intelligence ESPESY.