| import streamlit as st | |
| import speech_recognition as sr | |
| from gtts import gTTS | |
| import io | |
| import time | |
| def transcribe_audio(audio_file): | |
| recognizer = sr.Recognizer() | |
| try: | |
| with open("temp_audio.wav", "wb") as f: | |
| f.write(audio_file.read()) | |
| with sr.AudioFile("temp_audio.wav") as source: | |
| audio = recognizer.record(source) | |
| text = recognizer.recognize_google(audio) | |
| return text | |
| except Exception as e: | |
| st.error(f"Transcription failed: {str(e)}") | |
| return "" | |
| def text_to_speech(text, target_lang, max_retries=2): | |
| try: | |
| if not text: | |
| return None | |
| lang_map = { | |
| "English": "en", "French": "fr", "Spanish": "es", "German": "de", | |
| "Hindi": "hi", "Chinese": "zh-cn", "Arabic": "ar", "Russian": "ru", "Japanese": "ja" | |
| } | |
| lang_code = lang_map.get(target_lang, "en") | |
| for attempt in range(max_retries): | |
| try: | |
| tts = gTTS(text=text[:200], lang=lang_code, slow=False) | |
| audio_buffer = io.BytesIO() | |
| tts.write_to_fp(audio_buffer) | |
| audio_buffer.seek(0) | |
| if audio_buffer.getbuffer().nbytes > 0: | |
| return audio_buffer | |
| time.sleep(2 ** attempt) | |
| except Exception: | |
| if attempt == max_retries - 1: | |
| return None | |
| return None | |
| except Exception: | |
| return None |