Vocal synthesis ?
Hi everyone !
It's possible to create a voice with Max ?
For example, two peoples A and B. Record some references words/sentences with B. Use this sample to create a programme.
And a few moment later, when A speaking in live (a speech), the audience listening and watching A with the voice of B but while keeping the way of speaking of A.
I hope I'm clear enough...
Thanks for your answer.
Well, everything is possible, but you are asking a LOT here.
Easy version if you are under a deadline: process the voice so that it sounds different (Darth Vador, etc.)
Use just Max, or combined with a voice-processing plugin (to do pitch-shifting, formant shifting, etc.)
To implement more advanced voice recognition + synthesis / re-synthesis, you'll need to learn about the standard techniques in the first place. It is a vast domain, and your solution will be tailored to your goals, context, language, probability of words or phonemes occurring in your particular application, etc.
I am trying to use the Cantor Digitalis with max but it is too difficult. There is no update after 2016.