At first I recorded (sound card and screen capture) my playing on kslider (by mouse) on makenote object's help in Max 7.
Then I opened the mp3 file (the recorded kslider playing) in text editor and made Daniel (system voice) read it.
For the system voice called Milena I wrote the lyrics by myself. It's "O-o-o-o-o-o-o-ö-o".
Then I mixed all this in Ableton (voices of Daniel and Milena were sampled and recorded with launchpad, which work was also screen captured in Midi Monitor in the process of playing launchpad).
In the result - there are several screen capture video in framing screen capture video. But after closeup with "makenote.mp3"'s opening in TextEdit, I haven't used framing screen capture video and have edited several screen capture videos with desktop image (Final Cut). Interface aesthetics.
Software sum: Max 7, QuickTime, SoundTap, Adobe Premier, TextEdit, Ableton, Midi Monitor, Final Cut.