File size: 4,806 Bytes
4cc0ea8
 
 
 
 
7f92889
 
 
 
 
 
 
 
4cc0ea8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f92889
 
 
4cc0ea8
 
7f92889
 
 
4cc0ea8
7f92889
 
 
4cc0ea8
7f92889
4cc0ea8
7f92889
 
4cc0ea8
 
 
 
 
7f92889
4cc0ea8
7f92889
 
 
 
 
 
4cc0ea8
7f92889
4cc0ea8
7f92889
4cc0ea8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f92889
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
import os
import requests
import uuid
import subprocess
import time
import os
import tempfile
import subprocess
from typing import Optional, Tuple, List
import pytube
import docx
import PyPDF2
import re

def extract_audio_from_video(video_path, output_format="mp3"):
    if not video_path:
        return None
    
    output_path = f"audio_{uuid.uuid4().hex[:6]}.{output_format}"
    
    try:
        cmd = [
            "ffmpeg",
            "-i", video_path,
            "-vn",
            "-c:a", "libmp3lame" if output_format == "mp3" else output_format,
            "-q:a", "9",
            "-ac", "1",
            "-ar", "12000",
            "-y", output_path
        ]
        
        subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
        
        if os.path.exists(output_path):
            return output_path
        else:
            raise Exception("Audio extraction failed")
    except Exception as e:
        raise Exception(f"Error extracting audio: {str(e)}")

def transcribe_audio(audio_path, elevenlabs_api_key, model_id="scribe_v1"):
    import requests
    import tempfile
    
    try:
        url = "https://api.elevenlabs.io/v1/speech-to-text"
        headers = {"xi-api-key": elevenlabs_api_key}
        
        with open(audio_path, "rb") as file:
            files = {"file": file}
            data = {"model_id": model_id}
            
            response = requests.post(
                url, 
                headers=headers,
                files=files,
                data=data,
                timeout=120
            )
        
        if response.status_code == 200:
            result = response.json()
            transcription = result.get('text', '')
            
            # Save transcription to file
            transcript_path = tempfile.mktemp(suffix='.txt')
            with open(transcript_path, 'w', encoding='utf-8') as f:
                f.write(transcription)
                
            return transcription, transcript_path, "Transcription completed successfully"
        else:
            return None, None, f"Transcription failed: {response.text}"
    except Exception as e:
        return None, None, f"Transcription error: {str(e)}"

def process_video_file(video_path, audio_format, elevenlabs_api_key, model_id, gemini_api_key, language, content_type):
    try:
        audio_path = extract_audio_from_video(video_path, audio_format)
        
        transcription, transcript_path, transcription_status = transcribe_audio(
            audio_path, 
            elevenlabs_api_key, 
            model_id
        )
        
        if not transcription:
            return audio_path, "Audio extracted, but transcription failed", None, transcription_status, None, None, None
        
        # Generate summary or quiz from transcription
        formatted_output, json_path, txt_path = analyze_document(
            transcription, 
            gemini_api_key, 
            language, 
            content_type
        )
        
        return audio_path, "Processing completed successfully", transcript_path, transcription_status, formatted_output, txt_path, json_path
    except Exception as e:
        error_message = f"Error processing video: {str(e)}"
        return None, error_message, None, error_message, error_message, None, None



def process_youtube_video(youtube_url, audio_format, elevenlabs_api_key, model_id, gemini_api_key, language, content_type):
    try:
        yt = pytube.YouTube(youtube_url)
        stream = yt.streams.filter(progressive=True, file_extension='mp4').order_by('resolution').desc().first()
        
        if not stream:
            raise Exception("No suitable video stream found")
        
        video_path = tempfile.mktemp(suffix='.mp4')
        stream.download(filename=video_path)
        
        audio_path = extract_audio_from_video(video_path, audio_format)
        
        transcription, transcript_path, transcription_status = transcribe_audio(
            audio_path, 
            elevenlabs_api_key, 
            model_id
        )
        
        if not transcription:
            return audio_path, "Audio extracted, but transcription failed", None, transcription_status, None, None, None
        
        # Generate summary or quiz from transcription
        formatted_output, json_path, txt_path = analyze_document(
            transcription, 
            gemini_api_key, 
            language, 
            content_type
        )
        
        return audio_path, "Processing completed successfully", transcript_path, transcription_status, formatted_output, txt_path, json_path
    except Exception as e:
        error_message = f"Error processing YouTube video: {str(e)}"
        return None, error_message, None, error_message, error_message, None, None