Photo by: Maurice Rodin
Audio technology has come on in leaps and bounds in the past few centuries, from the phonograph, a device developed in 1877 that was the first to record and reproduce sound, to today having such advanced technology that the pioneers of the past could only dream of it.
Adobe has announced an extremely interesting technological development in the world of audio with a new piece of software, nicknamed Project Voco.
Project Voco has the capability to be able to mimic a recorded voice to generate new words in a piece of audio.
Apparently, it only needs around 20 minutes of recorded audio in order to copy a voice, and the software does this by simply allowing the user to type in the new text into an edit box.
The software was announced and demonstrated in California at the start of this month, and has certainly grabbed the attention of audio enthusiasts.
In the demonstration, Adobe showed off the impressive technology by changing a recording of a man saying ‘and I kissed my dogs and wife” to “and I kissed Jordan three times”. Scary stuff.
In an official statement, Adobe justified the project: “When recording voiceovers, dialog, and narration, people would often like to change or insert a word or a few words due to either a mistake they made or simply because they would like to change part of the narrative”.
However, according to the BBC, one expert has warned this technology could further lower trust in journalism, and another warns about it posing a potential security threat.
Has the time come where we are taking technology too far? Or are technological developments like this an exciting glimpse into the potential of the future?