Web-based Custom Voice Text-to-Speech Tool

Standalone Text-to-Speech Audio Tool
I am looking for a web developer to build a standalone web-based Text-to-Speech audio tool.

The tool should be simple, clean, and easy to use. I am looking for someone who can build the following functionality:

Large text box to type or paste text
Convert text into speech with AI using my own voice
If a custom voice is not possible, the tool should allow me to select and save a preferred available voice from what you generate that is similar to my voice
Generate the complete audio
Add music between sections of the spoken text so the music becomes part of the finished audio
Preview/listen to the entire finished audio
Download the final audio as MP3
Basic Workflow
Enter Text → Generate Speech → Add Music Between Sections → Preview → Download MP3

This is basically a Text-to-Speech system that allows music to be incorporated into the speech to create one complete finished audio file.

I want this to be a standalone tool, not a complicated platform. The interface should be straightforward so that I can use it quickly without technical knowledge.