app.py

import os
import streamlit as st
from pydub import AudioSegment
from groq import Groq

# Set ffmpeg path
ffmpeg_path = r"ffmpeg.exe"
os.environ["PATH"] += os.pathsep + os.path.dirname(ffmpeg_path)
AudioSegment.converter = ffmpeg_path

# Groq API configuration
groq_api_key = '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'  # Replace with your actual API key
client = Groq(api_key=groq_api_key)
model = 'whisper-large-v3'

# Function to ensure the file is in a suitable format
def ensure_suitable_format(file_path):
    allowed_formats = ["flac", "mp3", "mp4", "mpeg", "mpga", "m4a", "ogg", "opus", "wav", "webm"]
    file_extension = file_path.split('.')[-1].lower()
    if file_extension not in allowed_formats:
        new_file_path = f"{os.path.splitext(file_path)[0]}.wav"
        os.rename(file_path, new_file_path)
        return new_file_path
    return file_path

# Function to convert audio to WAV
def convert_audio_to_wav(input_path, output_path):
    audio = AudioSegment.from_file(input_path)
    audio.export(output_path, format="wav")
    return output_path

# Function to transcribe audio using Groq
def audio_to_text(filepath):
    with open(filepath, "rb") as file:
        translation = client.audio.translations.create(
            file=(filepath, file.read()),
            model=model,
        )
    return translation.text

# Streamlit App UI
st.title("Audio-to-Text Transcription")
st.write("Upload an audio file to get the transcribed text.")

# File upload
uploaded_file = st.file_uploader("Upload your audio file", type=["flac", "mp3", "mp4", "mpeg", "mpga", "m4a", "ogg", "opus", "wav", "webm"])

if uploaded_file:
    # Save the uploaded file locally
    file_path = os.path.join("uploaded_audio", uploaded_file.name)
    os.makedirs("uploaded_audio", exist_ok=True)
    with open(file_path, "wb") as f:
        f.write(uploaded_file.getbuffer())
    
    st.write(f"File uploaded: {uploaded_file.name}")

    # Ensure file format is suitable
    suitable_audio_path = ensure_suitable_format(file_path)

    # Convert audio to WAV
    wav_path = f"{os.path.splitext(suitable_audio_path)[0]}.wav"
    converted_audio = convert_audio_to_wav(suitable_audio_path, wav_path)

    # Transcribe audio
    st.write("Processing transcription...")
    try:
        transcription = audio_to_text(converted_audio)
        st.success("Transcription complete!")
        st.text_area("Transcribed Text", transcription, height=200)
    except Exception as e:
        st.error(f"Error during transcription: {e}")