import moviepy.editor as mp
import speech_recognition as sr
from googletrans import Translator
import srt
from datetime import timedelta
import time

def video_to_srt(video_path, output_srt_path):
    # Load the video file
    video = mp.VideoFileClip(video_path)
    
    # Extract the audio
    audio_path = "temp_audio.wav"
    video.audio.write_audiofile(audio_path)
    
    # Initialize recognizer
    recognizer = sr.Recognizer()
    
    # Load the audio file
    audio = sr.AudioFile(audio_path)
    
    # Split the audio into chunks
    def get_chunks(audio, chunk_length=30):
        with audio as source:
            recognizer.adjust_for_ambient_noise(source)
            duration = source.DURATION
            chunks = [(i, min(i + chunk_length, duration)) for i in range(0, int(duration), chunk_length)]
        return chunks
    
    # Transcribe each chunk with retries
    def transcribe_chunk(start, end):
        with audio as source:
            audio_data = recognizer.record(source, duration=end - start, offset=start)
            for _ in range(3):  # Retry up to 3 times
                try:
                    text = recognizer.recognize_google(audio_data)
                    return text
                except sr.UnknownValueError:
                    print(f"Google Speech Recognition could not understand audio chunk {start}-{end}")
                    return "[INAUDIBLE]"
                except sr.RequestError as e:
                    print(f"Request error from Google Speech Recognition service; {e}")
                    time.sleep(1)
            return "[ERROR]"

    chunks = get_chunks(audio)
    transcript = []

    for start, end in chunks:
        transcript.append(transcribe_chunk(start, end))
    
    transcript = " ".join(transcript)
    
    # Detect the language
    translator = Translator()
    detected_lang = translator.detect(transcript).lang
    
    # Split text into chunks (simplified)
    sentences = transcript.split('. ')
    
    # Create subtitles
    subtitles = []
    start_time = 0
    for i, sentence in enumerate(sentences):
        end_time = start_time + (len(sentence.split()) / 3)  # Assume 3 words per second
        subtitles.append(srt.Subtitle(index=i, start=timedelta(seconds=start_time), end=timedelta(seconds=end_time), content=sentence))
        start_time = end_time
    
    # Write to .srt file
    with open(output_srt_path, "w") as f:
        f.write(srt.compose(subtitles))

# Example usage
video_to_srt("Downloads/Avengers Endgame Movie Review _ Deeksha Sharma.mp4", "output_subtitles.srt")