Add TTS FastAPI Endpoint and run-api.sh Script

[m-aliabbas]

Pull Request Title

Add TTS FastAPI Endpoint and run-api.sh Script

---

Pull Request Description

Summary

This PR introduces:

1. A new TTS (Text-to-Speech) endpoint in the FastAPI application.
2. A run-api.sh script to streamline the API server startup process.

Changes Made

• Added a new FastAPI endpoint: /tts.
  • Accepts input text as a JSON payload.
  • Returns a generated audio file (e.g., .wav or .mp3) as a response.
• Added the run-api.sh script to simplify running the FastAPI server with uvicorn.

Files Added/Modified

1. app.py:
   • Implemented the /tts endpoint.
   • Example usage:

     POST /tts
     {
       "text": "Hello, this is a TTS demo."
     }

     Response: An audio file generated from the input text.
2. run-api.sh:
   • A script to run the FastAPI server.
   • Example usage:

     ./run-api.sh

How to Test

1. Start the FastAPI server:

   ./run-api.sh

2. Send a POST request to the /tts endpoint:

   curl -X POST http://127.0.0.1:8000/tts \
        -H "Content-Type: application/json" \
        -d '{"text": "Test text for TTS"}' --output output.wav

3. Verify that the output.wav file is generated and playable.

Checklist

• Implemented /tts endpoint.
• Added run-api.sh for easy server startup.
• Tested the /tts endpoint functionality locally.
• Updated documentation (if applicable).

Screenshots/Demo

(Optional: Add screenshots or attach an audio file showcasing the functionality.)

---

Request for Review

Please review the following:

• The accuracy of the /tts endpoint implementation.
• The usability and functionality of the run-api.sh script.
• Any edge cases or additional improvements.

[AznamirWoW]

You may want to do a re-do of this, because it is quite a mess.