tools/transcribe_youtube

from pytube import YouTube
import whisper
import io


def transcribe_youtube_audio(youtube_url: str) -> str:
    try:
        # Step 1: Download audio from YouTube
        yt = YouTube(youtube_url)
        audio_stream = yt.streams.filter(only_audio=True).first()
        
        # Use a BytesIO buffer to store the audio in memory
        audio_buffer = io.BytesIO()
        audio_stream.stream_to_buffer(audio_buffer)
        audio_buffer.seek(0)  # Reset buffer position to the beginning

        # Step 2: Load Whisper model
        model = whisper.load_model("base")  # Use "small", "medium", or "large" for better accuracy

        # Step 3: Transcribe audio from memory
        result = model.transcribe(audio_buffer)
        return result["text"]
    except Exception as e:
        return f"An error occurred: {str(e)}"

# Example usage
youtube_url = "https://www.youtube.com/watch?v=example"
lyrics = transcribe_youtube_audio(youtube_url)
print("Lyrics:", lyrics)