transcribe.py

import os
from fastapi import APIRouter, File, UploadFile, HTTPException
from groq import Groq
from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()
GROQ_API_KEY = os.getenv("GROQ_API_KEY")
if not GROQ_API_KEY:
    raise Exception("GROQ_API_KEY is not set in the environment.")

router = APIRouter()

@router.post("/transcribe")
async def transcribe_audio(file: UploadFile = File(...)):
    """
    Transcribe an uploaded audio file using the Groq client with the Whisper model.
    Returns the transcribed text.
    """
    try:
        # Initialize the Groq client with the API key from the environment.
        client = Groq(api_key=GROQ_API_KEY)
        file_bytes = await file.read()
        transcription = client.audio.transcriptions.create(
            file=(file.filename, file_bytes),
            model="whisper-large-v3",
            response_format="verbose_json",
        )
        return {"transcription": transcription.text}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))