Added both audio and video information

app.py

@@ -1,6 +1,7 @@
 import os
 import requests
 from flask import Flask, request, jsonify, render_template
+from deepgram import DeepgramClient, PrerecordedOptions
 from dotenv import load_dotenv
 import tempfile
 import json
@@ -37,8 +38,78 @@ def health_check():
     return jsonify({"status": "success", "message": "API is running successfully!"}), 200
 
 
+def transcribe_audio(wav_file_path):
+    """
+    Transcribe audio from a video file using Deepgram API synchronously.
+    
+    Args:
+        wav_file_path (str): Path to save the converted WAV file.
+    Returns:
+        dict: A dictionary containing status, transcript, or error message.
+    """
+    print("Entered the transcribe_audio function")
+    try:
+        # Initialize Deepgram client
+        deepgram = DeepgramClient(DEEPGRAM_API_KEY)
+
+        # Open the converted WAV file
+        with open(wav_file_path, 'rb') as buffer_data:
+            payload = {'buffer': buffer_data}
+
+            # Configure transcription options
+            options = PrerecordedOptions(
+                smart_format=True, model="nova-2", language="en-US"
+            )
+
+            # Transcribe the audio
+            response = deepgram.listen.prerecorded.v('1').transcribe_file(payload, options)
+
+            # Check if the response is valid
+            if response:
+                # print("Request successful! Processing response.")
+
+                # Convert response to JSON string
+                try:
+                    data_str = response.to_json(indent=4)
+                except AttributeError as e:
+                    return {"status": "error", "message": f"Error converting response to JSON: {e}"}
+
+                # Parse the JSON string to a Python dictionary
+                try:
+                    data = json.loads(data_str)
+                except json.JSONDecodeError as e:
+                    return {"status": "error", "message": f"Error parsing JSON string: {e}"}
+
+                # Extract the transcript
+                try:
+                    transcript = data["results"]["channels"][0]["alternatives"][0]["transcript"]
+                except KeyError as e:
+                    return {"status": "error", "message": f"Error extracting transcript: {e}"}
+
+                print(f"Transcript obtained: {transcript}")
+                # Step: Save the transcript to a text file
+                transcript_file_path = "transcript_from_transcribe_audio.txt"
+                with open(transcript_file_path, "w", encoding="utf-8") as transcript_file:
+                    transcript_file.write(transcript)
+                # print(f"Transcript saved to file: {transcript_file_path}")
+                
+                return transcript
+            else:
+                return {"status": "error", "message": "Invalid response from Deepgram."}
+
+    except FileNotFoundError:
+        return {"status": "error", "message": f"Video file not found: {wav_file_path}"}
+    except Exception as e:
+        return {"status": "error", "message": f"Unexpected error: {e}"}
+    finally:
+        # Clean up the temporary WAV file
+        if os.path.exists(wav_file_path):
+            os.remove(wav_file_path)
+            print(f"Temporary WAV file deleted: {wav_file_path}")
+            
 
-def download_audio(url, temp_video_path):
+
+def download_video(url, temp_video_path):
     """Download video (MP4 format) from the given URL and save it to temp_video_path."""
     response = requests.get(url, stream=True)
     if response.status_code == 200:
@@ -107,16 +178,31 @@ def process_video():
         # Step 1: Download the WAV file from the provided URL
         with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as temp_video_file:
             temp_video_path = temp_video_file.name
-            download_audio(video_url, temp_video_path)
+            download_video(video_url, temp_video_path)
         interval = 1
         # Step 2: get the information from the downloaded MP4 file synchronously
         video_info = get_information_from_video_using_OCR(temp_video_path, interval)
 
         if not video_info:
-            return jsonify({"error": "video information extraction failed"}), 500
+            video_info = ""
+
+        
+
+        # Step 2: Convert the MP4 to WAV
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_wav_file:
+            temp_wav_path = temp_wav_file.name
+            convert_mp4_to_wav(temp_video_path, temp_wav_path)
+
+        audio_info = transcribe_audio(temp_wav_path)
+        
+        # If no transcription present, use an empty string
+        if not audio_info:
+            audio_info = ""
 
+        
+            
         # Step 3: Generate structured recipe information using Gemini API synchronously
-        structured_data = query_gemini_api(video_info)
+        structured_data = query_gemini_api(video_info, audio_info)
 
         return jsonify(structured_data)
 
@@ -134,14 +220,14 @@ def process_video():
 
 
 
-def query_gemini_api(transcription):
+def query_gemini_api(video_transcription, audio_transcription):
     """
     Send transcription text to Gemini API and fetch structured recipe information synchronously.
     """
     try:
         # Define the structured prompt
         prompt = (
-            "Analyze the provided cooking video transcription and extract the following structured information:\n"
+            "Analyze the provided cooking video and audio transcription combined and based on the combined information extract the following structured information:\n"
             "1. Recipe Name: Identify the name of the dish being prepared.\n"
             "2. Ingredients List: Extract a detailed list of ingredients with their respective quantities (if mentioned).\n"
             "3. Steps for Preparation: Provide a step-by-step breakdown of the recipe's preparation process, organized and numbered sequentially.\n"
@@ -152,7 +238,9 @@ def query_gemini_api(transcription):
             "8. Special Notes or Variations: Include any specific tips, variations, or alternatives mentioned.\n"
             "9. Festive or Thematic Relevance: Note if the recipe has any special relevance to holidays, events, or seasons.\n"
             "Also, make sure not to provide anything else or any other information or warning or text apart from the above things mentioned."
-            f"Text: {transcription}\n"
+            f"Text: {audio_transcription}\n"
+            f"Text: {video_transcription}\n"
+            
         )
 
         # Prepare the payload and headers