tts.py

from gtts import gTTS
from typing import Dict, Any
import re
from deep_translator import GoogleTranslator
import io

class TextToSpeechConverter:
    def __init__(self):
        pass
    
    def clean_text_for_tts(self, text: str) -> str:
        text = re.sub(r'http\S+', '', text)
        text = re.sub(r'[^\w\s.,?!;:\-\'"()]', ' ', text)
        text = re.sub(r'\s+', ' ', text).strip()
        return text
    
    def translate_to_hindi(self, text: str) -> str:
        try:
            hindi_text = GoogleTranslator(source='auto', target='hi').translate(text)
            return hindi_text
        except Exception as e:
            print(f"Translation error: {e}")
            return "अनुवाद में त्रुटि हुई। कृपया पुनः प्रयास करें।"
    
    def generate_speech(self, text: str) -> Dict[str, Any]:
        try:
            cleaned_text = self.clean_text_for_tts(text)
            hindi_text = self.translate_to_hindi(cleaned_text)
            tts = gTTS(text=hindi_text, lang='hi', slow=False)
            audio_buffer = io.BytesIO()
            tts.write_to_fp(audio_buffer)
            audio_buffer.seek(0)
            return {
                "success": True,
                "message": "Speech generated successfully",
                "audio_buffer": audio_buffer,
                "hindi_text": hindi_text
            }
        except Exception as e:
            print(f"Error generating speech: {str(e)}")
            return {
                "success": False,
                "message": f"Error generating speech: {str(e)}",
                "audio_buffer": None,
                "hindi_text": None
            }