In April 2016, Adobe reported about an experimental piece of software, VoCo. Basically it's Photoshop for voices: you have a sound recording, but you're able to edit it like text, i.e. remove a word and replace it by another. In the link they descibe it as
When recording voiceovers, dialogue, and narration, wouldn’t you love the option to edit or insert a few words without the hassle of recreating the recording environment or bringing the voiceover artist in for another session? #VoCo allows you to change words in a voiceover simply by typing new words. Have to hear it to believe it? Check out a live demo using a recording of Keegan-Michael Key’s voice.
And of course, they then switch to a video (Youtube), which can much better demonstrate its capability.
Sometimes, Open Source people are really clever and once the idea and concept is known, they rapidly adapt it and come up with a similar solution.
I'd like to know whether this particular text to speech roundtrip has been implemented in a gratis or open source way.
- Import recorded voice (any common file format is ok, e.g. WAV or MP3)
- Voice recognition to transform the wave format into text
- Text editing / replacement
- TTS (text to speech), in order to change the recorded voice to match the new text
- Save the result (again, any common file format)
I can try it on Windows or Linux.