tools/audio_transcription.py

"""Tool for transcribing audio files to text."""
import os
from langchain_core.tools import tool
from langchain_community.document_loaders import AssemblyAIAudioTranscriptLoader

@tool
def audio_transcription(file_path: str) -> str:
    """
    Transcribe an audio file to text using AssemblyAI.
    
    Args:
        file_path: The path to the audio file.
    
    Returns:
        The transcribed text from the audio file.
    """
    search_docs = AssemblyAIAudioTranscriptLoader(file_path=file_path).load()

    formatted_search_docs = "\n\n---\n\n".join(
    [
        f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
        for doc in search_docs
    ])

    return {"audio_results": formatted_search_docs}