After I input the following text in my text to speech project, I get a mixed VO of my content and other random content:

"Aerophones, in Hornbostel–Sachs, divide into four great branches. Edge-blown flutes: air split on a sharp rim — the ney, the bansuri, the recorder. Reed aerophones: air forced through a vibrating reed — clarinet, oboe, zurna, bagpipes. Lip-vibrated aerophones: air buzzing against the lips — trumpets, horns, conches. Free aerophones: air vibrates in open space — harmonica, accordion reeds, bullroarers."

It also consumes my characters.

Ps: I am using a custom voice.