fix

app.py

@@ -77,12 +77,12 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         
-        if "in response to the question" not in question_text: 
-            continue     
+        #if "in response to the question" not in question_text: 
+        #    continue     
         
-        print('testing whisper with youtube video...')
-        whisper_return = audio_to_text_from_youtube('https://www.youtube.com/watch?v=1htKBjuUWec')
-        print(whisper_return)
+        #print('testing whisper with youtube video...')
+        #whisper_return = audio_to_text_from_youtube('https://www.youtube.com/watch?v=1htKBjuUWec')
+        #print(whisper_return)
         
         try:
             file_name = item.get("file_name")

audio_to_text_tool.py

@@ -3,7 +3,12 @@ import tempfile
 from openai import OpenAI
 from langchain.tools import tool
 from constants import OPENAI_KEY
-from pytube import YouTube
+import tempfile
+import os
+import openai
+from openai import OpenAI
+from langchain.tools import tool
+import yt_dlp
 
 # Initialize OpenAI client (uses OPENAI_API_KEY from environment or explicitly)
 client = OpenAI(api_key=OPENAI_KEY)
@@ -45,7 +50,7 @@ def audio_to_text(base64_audio_path: str) -> str:
     except Exception as e:
         return f"An error occurred during transcription: {str(e)}"
 
-#@tool
+@tool
 def audio_to_text_from_youtube(youtube_url: str) -> str:
     """
     Downloads audio from a YouTube video and transcribes it using OpenAI Whisper API.
@@ -56,27 +61,34 @@ def audio_to_text_from_youtube(youtube_url: str) -> str:
     Returns:
         str: Transcribed text.
     """
-    try:
-        # Download audio stream
-        yt = YouTube(youtube_url)
-        audio_stream = yt.streams.filter(only_audio=True).first()
-
-        if not audio_stream:
-            return "No audio stream found in the YouTube video."
-
-        with tempfile.NamedTemporaryFile(suffix=".mp4", delete=False) as temp_audio_file:
-            audio_stream.download(output_path=None, filename=temp_audio_file.name)
-            temp_audio_path = temp_audio_file.name
-
-        # Transcribe using OpenAI Whisper
-        with open(temp_audio_path, "rb") as audio_file:
-            transcript = client.audio.transcriptions.create(
-                model="whisper-1",
-                file=audio_file,
-                response_format="text"
-            )
-
-        return transcript.strip()
+   try:
+        with tempfile.TemporaryDirectory() as tmpdir:
+            audio_output_path = os.path.join(tmpdir, "audio.mp3")
+
+            # Download best audio using yt-dlp
+            ydl_opts = {
+                "format": "bestaudio/best",
+                "outtmpl": audio_output_path,
+                "quiet": True,
+                "postprocessors": [{
+                    "key": "FFmpegExtractAudio",
+                    "preferredcodec": "mp3",
+                    "preferredquality": "192",
+                }],
+            }
+
+            with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+                ydl.download([youtube_url])
+
+            # Transcribe with OpenAI Whisper
+            with open(audio_output_path, "rb") as audio_file:
+                transcript = client.audio.transcriptions.create(
+                    model="whisper-1",
+                    file=audio_file,
+                    response_format="text"
+                )
+
+            return transcript.strip()
 
     except Exception as e:
         return f"An error occurred during YouTube transcription: {str(e)}"