Add multi-speaker support and interface for text-to-speech conversion

Add subtitle generation option and guidance for SRT file creation in text_to_speech

Add SRT support and file upload functionality to text_to_speech

Refactor punctuation handling in text_to_speech function for improved accuracy

Enhance punctuation handling in text_to_speech function for various cases

Improve punctuation handling in text_to_speech function

Improve text formatting in text_to_speech function to handle punctuation correctly

Update project title in README.md to match application name

Add subtitle generation feature to text-to-speech functionality

Fix requirements.txt by removing pydub and ensuring gradio is listed correctly

Add application file

initial commit