import streamlit as st
import speech_recognition as sr
from gtts import gTTS
import os
import io

def transcribe_audio(audio_file):
    """Transcribe uploaded audio file to text."""
    recognizer = sr.Recognizer()
    try:
        # Save uploaded file temporarily
        with open("temp_audio.wav", "wb") as f:
            f.write(audio_file.read())
        
        # Transcribe using SpeechRecognition
        with sr.AudioFile("temp_audio.wav") as source:
            audio = recognizer.record(source)
            text = recognizer.recognize_google(audio)
        
        # Clean up
        os.remove("temp_audio.wav")
        return text
    except Exception as e:
        st.error(f"Audio transcription failed: {str(e)}")
        return ""

def text_to_speech(text, target_lang):
    """Convert translated text to audio with robust handling using memory buffer."""
    try:
        if not text:
            st.error("No text to convert to audio.")
            return None
        
        # Map target language to gTTS codes
        lang_map = {
            "English": "en",
            "French": "fr",
            "Spanish": "es",
            "German": "de",
            "Chinese": "zh-cn",
            "Arabic": "ar",
            "Russian": "ru",
            "Hindi": "hi",
            "Japanese": "ja",
        }
        lang_code = lang_map.get(target_lang, "en")
        
        # Generate audio in memory
        st.write(f"Generating audio for language code: {lang_code}")  # Debug output
        tts = gTTS(text=text, lang=lang_code, slow=False)
        audio_buffer = io.BytesIO()
        tts.write_to_fp(audio_buffer)
        audio_buffer.seek(0)
        
        # Save temporarily for debugging (optional)
        with open("output_audio.mp3", "wb") as f:
            f.write(audio_buffer.getbuffer())
        
        st.success(f"Audio generated in memory for {target_lang}")
        return audio_buffer
    except Exception as e:
        st.error(f"Audio generation failed: {str(e)}")
        return None