If you are familiar with Text to Speech software (T2S), then you’ll know how much of a life line it is when crafting and checking your written work. I literally couldn’t write this blog without it. But no matter how useful the software is, there’s still one issue that polarizes opinion amongst users; some people just can’t get to grips with the voices. While ‘Daniel’ or ‘Serena’ (the default voices that are loaded into most T2S packages) may sound a little robotic, you can improve things with the use of add-ons or additional downloads, that do a pretty decent job of giving your T2S warmer, more human tones.
But what if there was a way to have your work read back to you in a voice that you actually have a connection to. Well, judging by what’s been going on at Adobe, this may be a reality much sooner than you think.
Project VoCo, from Adobe, has been touted as the ‘Photoshop for audio’. In the same way that Photoshop allows you to doctor images and blur the lines between reality and your imagination, Project VoCo allows you to edit and reproduce speech in any speakers voice just by typing the text.
Unlike traditional audio editing programmes, there is no need to master the technicalities of editing waveforms, as Project VoCo turns your audio into text and allows you to edit the audio simply by changing the text, as you would in a word processor. If that wasn’t cool enough, the package takes this function further by allowing you to add audio to the recording that wasn’t there in the original. Just by typing the text you wish to add to the dialogue, that text is turned into audio and added to the recording in the same voice as the original speaker. It has to be seen to be believed and will have great uses in the audio and video production industries.
However, what excites me most is the application it could have in the world of Assistive Technology. Imagine your text to speech package reading back your work in the voice of your mum, partner or favorite movie actor! All the software needs is 20 minutes of the voice you want to use and the software can reproduce any word typed, in the voice of your choice. The software is currently in it’s infancy and only seems to be able to handle a few words at a time but as the software improves it could really revolutionise the sound of text to speech in the future.
Would you like to see this function added to Text to Speech or do you prefer the voices that are already available? Let us know in the comments below.
The Codpast is a multimedia production from www.extraordinaire.tv