The main objective of a caller navigating an IVR system is to get to the desired destination as quickly as possible. If the script contains overly wordy phrases and long descriptions, the callers will get frustrated with every passing word.
Record the clips of what you want your callers to hear, then use an audio editing software to arrange the clips and add background music.

Curation by context is the game of late. We choose music by our mood, by our activity, and by our audience. Spotify lets you browse by mood and events, showcasing playlists that cross multiple genres because music can’t be sorted into individual boxes.
For those still using analogue or digital phone systems, voice on ISDN circuits has a bandwidth of around 4000Hz. The audio from an analogue phone is sampled at 8000Hz, and because of the nyquist theorem, must be low-pass filtered to 4000Hz. So any frequencies in the audio beyond 4000Hz are lost. Interestingly, the human ear and mind are good at recognising human speech, so this is considered "toll-quality" voice, i.e. good enough to pay for. This is the reason why certain vocalised letters are difficult or impossible to tell apart on the phone. For example, the differences between B, P, T, C, etc. are almost entirely above 4000Hz.