app.py

import streamlit as st
import moviepy.editor as mp
import speech_recognition as sr
from pydub import AudioSegment
import tempfile
import os

# Function to convert video to audio
def video_to_audio(video_file):
    # Load the video using moviepy
    video = mp.VideoFileClip(video_file)
    
    # Extract audio
    audio = video.audio
    temp_audio_path = tempfile.mktemp(suffix=".mp3")
    
    # Write the audio to a file
    audio.write_audiofile(temp_audio_path)
    return temp_audio_path

# Function to transcribe audio to text
def transcribe_audio(audio_file):
    # Initialize recognizer
    recognizer = sr.Recognizer()
    
    # Load the audio file using speech_recognition
    audio = sr.AudioFile(audio_file)
    
    with audio as source:
        audio_data = recognizer.record(source)
    
    try:
        # Transcribe the audio data to text using Google Web Speech API
        text = recognizer.recognize_google(audio_data)
        return text
    except sr.UnknownValueError:
        return "Audio could not be understood."
    except sr.RequestError:
        return "Could not request results from Google Speech Recognition service."

# Streamlit app layout
st.title("Video to Audio to Text Transcription")
st.write("Upload a video file, and it will be converted to audio and transcribed into text.")

# File uploader for video
uploaded_video = st.file_uploader("Upload Video", type=["mp4", "mov", "avi"])

if uploaded_video is not None:
    # Save the uploaded video file temporarily
    with tempfile.NamedTemporaryFile(delete=False) as tmp_video:
        tmp_video.write(uploaded_video.read())
        tmp_video_path = tmp_video.name
    
    # Convert video to audio
    st.write("Converting video to audio...")
    audio_file = video_to_audio(tmp_video_path)
    
    # Provide the audio file to the user for download
    st.audio(audio_file, format='audio/mp3')
    
    # Transcribe audio to text
    st.write("Transcribing audio to text...")
    transcription = transcribe_audio(audio_file)
    
    # Show the transcription
    st.text_area("Transcription", transcription, height=300)
    
    # Cleanup temporary files
    os.remove(tmp_video_path)
    os.remove(audio_file)