voice.py

from typing import Optional
from fastapi import HTTPException
from config import logger
import io
import speech_recognition as sr
from gtts import gTTS
from pydub import AudioSegment
import base64

def recognize_speech(audio_data: bytes, language: str = "en-US") -> str:
    recognizer = sr.Recognizer()
    try:
        with io.BytesIO(audio_data) as audio_file:
            with sr.AudioFile(audio_file) as source:
                audio = recognizer.record(source)
                text = recognizer.recognize_google(audio, language=language)
                return text
    except sr.UnknownValueError:
        logger.error("Google Speech Recognition could not understand audio")
        raise HTTPException(status_code=400, detail="Could not understand audio")
    except sr.RequestError as e:
        logger.error(f"Could not request results from Google Speech Recognition service; {e}")
        raise HTTPException(status_code=503, detail="Speech recognition service unavailable")
    except Exception as e:
        logger.error(f"Error in speech recognition: {e}")
        raise HTTPException(status_code=500, detail="Error processing speech")

def text_to_speech(text: str, language: str = "en", slow: bool = False) -> bytes:
    try:
        tts = gTTS(text=text, lang=language, slow=slow)
        mp3_fp = io.BytesIO()
        tts.write_to_fp(mp3_fp)
        mp3_fp.seek(0)
        return mp3_fp.read()
    except Exception as e:
        logger.error(f"Error in text-to-speech conversion: {e}")
        raise HTTPException(status_code=500, detail="Error generating speech")

def extract_text_from_pdf(pdf_data: bytes) -> str:
    try:
        from PyPDF2 import PdfReader
        pdf_reader = PdfReader(io.BytesIO(pdf_data))
        text = ""
        for page in pdf_reader.pages:
            text += page.extract_text() or ""
        return clean_text_response(text)
    except Exception as e:
        logger.error(f"Error extracting text from PDF: {e}")
        raise HTTPException(status_code=400, detail="Failed to extract text from PDF")