i asked for a speech generator. what i wanted was chatter: phrases coming from everywhere, left, right, and one pressing on you from the front.
it worked within the hour. then it got its name, VOICES IN MY HEAD, and my face in the middle of the radar. the more voices talk at once, the more the face tears, and the more of a tribal sigil grows around it. the sound has INSANITY knobs: SHRED, DEMON, RING, METAL THROAT.
that night i wrote a note to myself. i’d started using what i know about programming, and about how video processing works on the inside, on music. the crowd is the cleanest example. three phrases a second, each one with its own voice, its own cut, its own path around your head, its own chance to play backwards. in ableton that’s hundreds of clips and 3d panning drawn by hand. in code it’s one function that gets called forever.
ableton wins when the decisions are few and a hand makes them. code wins when every word needs its own decision and there are thousands of words.
the neural voices turned out too slow, even with the files sitting on my own site. so the crowd got voices baked ahead of time, and a MY VOICE mode: record your own phrases through the mic and the crowd is you.
put headphones on.