to me here it sounds (hiya ustáδah) [δ=th in this] - I'm on PC here so probably there are some differences between mobile and PC, not sure.
Anyway, the audio for me sounds correct, but as for the -tun sound, here is the story:
First, the (-un) sound is called Nunation or Tanwin. The theory says it was a nasal sound but then developed to full (N). Anyway, Tanwin has many purposes and uses in Arabic but for the time being you can see it as the equivalent of (a/an) in English; That is, somewhat similar to the indefinite article.
Secondly, the word (ustáδah) ends with Ta-Marbútah ة (like many feminine nouns). This letter is combination of (H) and (T). When the word is isolate or simply at the end of the sentence or phrase, usually there is no need to add the last vowel in the word, so the Ta-Marbútah remains as (H). Once we move this letter with any short vowel (or even when we add possessive suffixes) this (H) changes to (T). So, if you combine Tanwin with this letter, you would get -tun.
And by the way, Tanwin comes in 3 flavors depending on the case of the word: -an, -in and -un.