audio_to_text_tool.py

import base64
import tempfile
from openai import OpenAI
from langchain.tools import tool
from constants import OPENAI_KEY
from pytube import YouTube

# Initialize OpenAI client (uses OPENAI_API_KEY from environment or explicitly)
client = OpenAI(api_key=OPENAI_KEY)
 
@tool
def audio_to_text(base64_audio_path: str) -> str:
    """
    Transcribes an audio file (base64-encoded text stored in a file) using OpenAI's Whisper API.

    Args:
        base64_audio_path (str): Path to a file containing base64-encoded audio as text.

    Returns:
        str: The transcribed text.
    """
    try:
        # Read base64 string
        with open(base64_audio_path, "r") as f:
            base64_str = f.read()

        # Decode base64 to bytes
        audio_bytes = base64.b64decode(base64_str)

        # Save audio bytes to temp file (must be supported format: mp3, m4a, wav, etc.)
        with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as temp_audio:
            temp_audio.write(audio_bytes)
            temp_audio_path = temp_audio.name

        # Transcribe using OpenAI Whisper API
        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()

    except Exception as e:
        return f"An error occurred during transcription: {str(e)}"

#@tool
def audio_to_text_from_youtube(youtube_url: str) -> str:
    """
    Downloads audio from a YouTube video and transcribes it using OpenAI Whisper API.

    Args:
        youtube_url (str): URL of the YouTube video.

    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()

    except Exception as e:
        return f"An error occurred during YouTube transcription: {str(e)}"

if __name__ == "__main__":
    # Example: path to a text file that contains base64-encoded audio (e.g., base64_audio.txt)
    base64_audio_file_path = r"C:\tmp\ibm\99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3.mp3.b64"

    # Call the tool function
    transcription = audio_to_text(base64_audio_file_path)

    # Print the result
    print("Transcription result:")
    print(transcription)