Upload 2 files

app.py

@@ -0,0 +1,83 @@
+# app.py
+import os
+import gradio as gr
+import tempfile
+from video_processing import (
+    process_video_file,
+)
+from quiz_processing import process_text
+
+ELEVENLABS_API_KEY = os.environ.get("ELEVENLABS_API_KEY", None)
+GOOGLE_API_KEY = os.environ.get('GOOGLE_API_KEY', None)
+
+def combined_process_video_file(video_file, output_format, elevenlabs_api_key, model_id, google_api_key):
+    audio_path, audio_msg, transcript_file, transcript_msg, transcript_text, _ = process_video_file(
+        video_file, output_format, elevenlabs_api_key, model_id
+    )
+
+    if not transcript_text:
+        return audio_path, audio_msg, transcript_file, transcript_msg, "No transcript text to analyze", None, None
+
+    formatted_quiz, quiz_file, json_file = process_text(transcript_text, google_api_key)
+
+    return audio_path, audio_msg, transcript_file, transcript_msg, formatted_quiz, quiz_file, json_file
+
+# Create the Gradio interface
+with gr.Blocks(title="Video to Quiz Generator") as app:
+    gr.Markdown("Video => Quiz")
+    gr.Markdown("Upload a video or provide a URL to extract audio, transcribe, and automatically generate a quiz with topics, key concepts, summaries, and questions.")
+
+    with gr.Row():
+        with gr.Column():
+            elevenlabs_api_key = gr.Textbox(
+                placeholder="Enter your ElevenLabs API key",
+                label="ElevenLabs API Key (for transcription)",
+                type="password",
+                value=ELEVENLABS_API_KEY
+            )
+
+            model_id = gr.Dropdown(
+                choices=["scribe_v1"],
+                value="scribe_v1",
+                label="Transcription Model"
+            )
+
+            google_api_key = gr.Textbox(
+                placeholder="Enter your Google Gemini API key",
+                label="Google API Key (for quiz generation)",
+                type="password",
+                value=GOOGLE_API_KEY
+            )
+
+    with gr.Tabs():
+        with gr.TabItem("Upload Video"):
+            with gr.Row():
+                with gr.Column():
+                    video_input = gr.Video(label="Upload Video")
+                    format_choice_file = gr.Radio(["mp3", "wav"], value="mp3", label="Audio Format")
+                    extract_button_file = gr.Button("Process Video & Generate Quiz")
+
+                with gr.Column():
+                    audio_output_file = gr.Audio(label="Extracted Audio", type="filepath")
+                    status_output_file = gr.Textbox(label="Audio Extraction Status")
+                    transcript_file_output = gr.File(label="Transcription Text File")
+                    transcript_status_output = gr.Textbox(label="Transcription Status")
+
+            with gr.Row():
+                with gr.Column():
+                    quiz_output_file = gr.Textbox(
+                        label="Generated Quiz",
+                        lines=15
+                    )
+                    with gr.Row():
+                        quiz_file_output_file = gr.File(label="Download Quiz Text")
+                        json_file_output_file = gr.File(label="Download Quiz JSON")
+
+            extract_button_file.click(
+                fn=combined_process_video_file,
+                inputs=[video_input, format_choice_file, elevenlabs_api_key, model_id, google_api_key],
+                outputs=[audio_output_file, status_output_file, transcript_file_output,
+                         transcript_status_output, quiz_output_file, quiz_file_output_file, json_file_output_file]
+            )
+if __name__ == "__main__":
+    app.launch(share= True, debug = True)

video_processing.py

@@ -0,0 +1,78 @@
+import os
+import requests
+import json
+import uuid
+from moviepy import VideoFileClip
+
+def extract_audio(video_path, output_format="mp3"):
+    if not video_path:
+        return None, "No video provided"
+
+    output_path = f"extracted_audio_{uuid.uuid4().hex[:8]}.{output_format}"
+
+    try:
+        video = VideoFileClip(video_path)
+        video.audio.write_audiofile(output_path)
+        video.close()
+        return output_path, f"Audio extracted successfully"
+    except Exception as e:
+        return None, f"Error extracting audio: {str(e)}"
+
+def transcribe_audio(audio_file, api_key, model_id="scribe_v1"):
+    if not api_key:
+        return {"error": "Please provide an API key"}
+
+    url = "https://api.elevenlabs.io/v1/speech-to-text"
+    headers = {
+        "xi-api-key": api_key
+    }
+    files = {
+        "file": open(audio_file, "rb"),
+        "model_id": (None, model_id)
+    }
+
+    try:
+        response = requests.post(url, headers=headers, files=files)
+        response.raise_for_status()
+        result = response.json()
+        return result
+    except requests.exceptions.RequestException as e:
+        return {"error": f"API request failed: {str(e)}"}
+    except json.JSONDecodeError:
+        return {"error": "Failed to parse API response"}
+    finally:
+        files["file"].close()
+
+def save_transcription(transcription):
+    if "error" in transcription:
+        return None, transcription["error"]
+
+    transcript_filename = f"transcription_{uuid.uuid4().hex[:8]}.txt"
+
+    try:
+        with open(transcript_filename, "w", encoding="utf-8") as f:
+            f.write(transcription.get('text', 'No text found'))
+
+        return transcript_filename, "Transcription saved as text file"
+    except Exception as e:
+        return None, f"Error saving transcription: {str(e)}"
+
+def process_video_file(video_file, output_format, elevenlabs_api_key, model_id):
+    if video_file is None:
+        return None, "Please upload a video file", None, "No video provided", None, None
+
+    audio_path, message = extract_audio(video_file, output_format)
+
+    if audio_path and os.path.exists(audio_path):
+        transcription = transcribe_audio(audio_path, elevenlabs_api_key, model_id)
+        transcript_file, transcript_message = save_transcription(transcription)
+
+        transcript_text = ""
+        if transcript_file:
+            with open(transcript_file, "r", encoding="utf-8") as f:
+                transcript_text = f.read()
+
+        return audio_path, message, transcript_file, transcript_message, transcript_text, None
+    else:
+        return None, message, None, "Audio extraction failed, cannot transcribe", None, None
+