Multilingual Support in image_to_sound

Issue Details: Currently, the code converts text to speech in English ("en"). It would be beneficial to extend this functionality to support multiple languages. Users should be able to specify the
target language for the generated audio.

Changes Made:

1. Allowed users to input the target language code or name as an argument when calling the image_to_sound function.
2. Implemented logic to select the appropriate language for the gTTS module based on the user's input. Research and Challenges: Researched the gTTS documentation and language codes. The main challenge was ensuring compatibility with different language inputs.

Interactions with Maintainers: No direct interactions with maintainers for this issue. Difficulties Faced and Solutions: Understanding the gTTS API and integrating multilingual
support required careful reading of the documentation. Regular testing helped verify the implementation.
Pull Request: Link to Pull Request