Voice Extraction from track and ElevenLabs Voice Re-generation

I need someone to extract the first 51 seconds of dialog in the attached sound track that comes from the following video: https://drive.google.com/file/d/1oNGhnlhgY2jhQZxsOBzfGJMIBush0AB5/view?usp=sharing.

It is the first 9 lines of dialog between a mother and daughter. I then want to generate 3 variations of voices and line readings for this dialog that will then be overlayed into the final version of this new video: https://drive.google.com/file/d/1208iCrMkpnUHjghWP0L4xS_MLMBeZ71O/view?usp=sharing

Specifications for the voices:

8 year old girl, Anna: use standard American English, no accent. Raise the register of the existing girl's voice, it is presently too high pitched.

38 year old mother, Feyga: use standard American English, no accent. Use a tone that is not as harsh or brittle but still registers significant anxiety.

Emotional context of the scene: an intense scenario taking place in the small anteroom of the library where the absent-minded prince has inadvertently kept them waiting. It is an excruciating wait for Feyga; she does not want to knock on the door and impose. But she is desperate. That morning she learned that her recently deceased husband left her with substantial debt and her brother-in-law is scheming to get control of the prince's estate taverns that Feyga managed with her husband under the auspices of the Council. She is knowingly breaking the rules of the Jewish Council by approaching the prince directly.

Her savant daughter Anna is the key to the bet she is placing that will hopefully save them from ruin. Anna has a photographic memory as well as extraordinary pattern recognition capabilities. Anna has compiled information about the prince's estate taverns that could dramatically increase their revenue potential.

While there are only ten lines of dialog interspersed through the scene it is the characters' telling behavior and visceral emotional context that is the focus of the scene. It is key that the animation and spoken dialog convey this emotional content .

Attached is the audio track from the original POC video from which the voices will be extracted and a document with the dialog.

Note: there is a subtle background music that needs to be removed.

I need this work to be completed by Saturday, July 4th which will require at least one and possibly two rounds of review to get the voices/line readings correct.

If the work performed is satisfactory there will be a follow-up job of adding foley sound to the final video.