app.py

import requests
import pytz
import streamlit as st
import os

from datetime import datetime
from audio_recorder_streamlit import audio_recorder

API_URL = f'https://tonpixzfvq3791u9.us-east-1.aws.endpoints.huggingface.cloud'
headers = {
	"Authorization": "Bearer XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX",
	"Content-Type": "audio/wav"
}

def query(filename):
    with open(filename, "rb") as f:
        data = f.read()
    response = requests.post(API_URL, headers=headers, data=data)
    return response.json()

def generate_filename(prompt, file_type):
    central = pytz.timezone('US/Central')
    safe_date_time = datetime.now(central).strftime("%m%d_%H%M")
    replaced_prompt = prompt.replace(" ", "_").replace("\n", "_")
    safe_prompt = "".join(x for x in replaced_prompt if x.isalnum() or x == "_")[:90]
    return f"{safe_date_time}_{safe_prompt}.{file_type}"

# 10. Audio recorder to Wav file:
def save_and_play_audio(audio_recorder):
    audio_bytes = audio_recorder()
    if audio_bytes:
        filename = generate_filename("Recording", "wav")
        with open(filename, 'wb') as f:
            f.write(audio_bytes)
        st.audio(audio_bytes, format="audio/wav")
        return filename

# 9B. Speech transcription to file output - OPENAI Whisper
def transcribe_audio(filename):
    output = query(filename)
    return output


def main():
    st.title("Speech to Text")
    st.write("Record your speech and get the text.")

    # Audio, transcribe, GPT:
    filename = save_and_play_audio(audio_recorder)
    if filename is not None:
        transcription = transcribe_audio(filename)
        st.write(transcription)

if __name__ == "__main__":
    main()