Create app.py

app.py

@@ -0,0 +1,171 @@
+import os
+import gradio as gr
+import requests
+import json
+from moviepy.editor import VideoFileClip
+import yt_dlp
+import uuid
+
+ELEVENLABS_API_KEY = scribe_api
+
+def download_video_from_url(url):
+    try:
+        filename = f"downloaded_video_{uuid.uuid4().hex[:8]}.mp4"      
+        ydl_opts = {
+            'format': 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/mp4',
+            'outtmpl': filename,
+            'quiet': True,
+        }
+        
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            ydl.download([url])
+        
+        return filename, None
+    except Exception as e:
+        return None, f"Error downloading video: {str(e)}"
+
+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, verbose=False, logger=None)
+        video.close()
+        return output_path, f"Audio extracted successfully"
+    except Exception as e:
+        return None, f"Error extracting audio: {str(e)}"
+
+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, api_key, model_id):
+    if video_file is None:
+        return None, "Please upload a video file", None, "No video provided"
+    
+    audio_path, message = extract_audio(video_file, output_format)
+    
+    if audio_path and os.path.exists(audio_path):
+        transcription = transcribe_audio(audio_path, api_key, model_id)
+        transcript_file, transcript_message = save_transcription(transcription)
+        return audio_path, message, transcript_file, transcript_message
+    else:
+        return None, message, None, "Audio extraction failed, cannot transcribe"
+
+def process_video_url(video_url, output_format, api_key, model_id):
+    if not video_url.strip():
+        return None, "Please enter a video URL", None, "No URL provided"
+    video_path, error = download_video_from_url(video_url)
+    if error:
+        return None, error, None, "Video download failed, cannot transcribe"
+    
+    audio_path, message = extract_audio(video_path, output_format)
+    if video_path and os.path.exists(video_path):
+        try:
+            os.remove(video_path)
+        except:
+            pass
+    
+    if audio_path and os.path.exists(audio_path):
+        transcription = transcribe_audio(audio_path, api_key, model_id)
+        transcript_file, transcript_message = save_transcription(transcription)
+        return audio_path, message, transcript_file, transcript_message
+    else:
+        return None, message, None, "Audio extraction failed, cannot transcribe"
+
+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()
+
+with gr.Blocks(title="Video to Audio to Transcription") as app:
+    gr.Markdown("# Video => Audio => Transcription")
+    gr.Markdown("Upload a video or provide a URL to extract audio and transcribe it using ElevenLabs' API.")
+    
+    api_key = gr.Textbox(
+        placeholder="Enter your ElevenLabs API key",
+        label="ElevenLabs API Key",
+        type="password",
+        value=ELEVENLABS_API_KEY
+    )
+    
+    model_id = gr.Dropdown(
+        choices=["scribe_v1", "eleven_turbo_v2"],
+        value="scribe_v1",
+        label="Transcription Model"
+    )
+    
+    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="Output Format")
+                    extract_button_file = gr.Button("Extract Audio & Transcribe")
+                
+                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")
+            
+            extract_button_file.click(
+                fn=process_video_file,
+                inputs=[video_input, format_choice_file, api_key, model_id],
+                outputs=[audio_output_file, status_output_file, transcript_file_output, transcript_status_output]
+            )
+            
+        with gr.TabItem("Video URL"):
+            with gr.Row():
+                with gr.Column():
+                    url_input = gr.Textbox(label="Video URL (YouTube, etc.)", placeholder="https://www.youtube.com/watch?v=...")
+                    format_choice_url = gr.Radio(["mp3", "wav"], value="mp3", label="Output Format")
+                    extract_button_url = gr.Button("Extract Audio & Transcribe")
+                
+                with gr.Column():
+                    audio_output_url = gr.Audio(label="Extracted Audio", type="filepath")
+                    status_output_url = gr.Textbox(label="Audio Extraction Status")
+                    transcript_file_output_url = gr.File(label="Transcription Text File")
+                    transcript_status_output_url = gr.Textbox(label="Transcription Status")
+            
+            extract_button_url.click(
+                fn=process_video_url,
+                inputs=[url_input, format_choice_url, api_key, model_id],
+                outputs=[audio_output_url, status_output_url, transcript_file_output_url, transcript_status_output_url]
+            )
+
+if __name__ == "__main__":
+    app.launch()