{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from openai import OpenAI\n",
    "from dotenv import load_dotenv\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "load_dotenv()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "openai_key = os.getenv(\"OPENAI\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "client = OpenAI(api_key=openai_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "response = client.audio.speech.create(\n",
    "    model=\"tts-1-hd\",\n",
    "    voice=\"alloy\",\n",
    "    input=\"My Name is Testimony[laughs]\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_39704/3198597338.py:1: DeprecationWarning: Due to a bug, this method doesn't actually stream the response content, `.with_streaming_response.method()` should be used instead\n",
      "  response.stream_to_file(\"../data/output.mp3\")\n"
     ]
    }
   ],
   "source": [
    "response.stream_to_file(\"../data/output.mp3\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "audio_file = open(\"../data/output.mp3\", \"rb\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "text_response = client.audio.transcriptions.create(\n",
    "    model=\"whisper-1\",\n",
    "    file= audio_file,\n",
    "    response_format= 'text'\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'My name is testimony.\\n'"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text_response"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "\n",
    "\n",
    "def transcribe(audio_file):\n",
    "  transcription = client.audio.transcriptions.create(\n",
    "    model=\"whisper-1\", \n",
    "    file=audio_file, \n",
    "    response_format=\"text\",\n",
    "    prompt=\"ZyntriQix, Digique Plus, CynapseFive, VortiQore V8, EchoNix Array, OrbitalLink Seven, DigiFractal Matrix, PULSE, RAPT, B.R.I.C.K., Q.U.A.R.T.Z., F.L.I.N.T.\"\n",
    "  )\n",
    "  return transcription"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "system_prompt = \n",
    "def generate_corrected_transcript(temperature, system_prompt, audio_file):\n",
    "    response = client.chat.completions.create(\n",
    "        model=\"gpt-3.5-turbo-16k\",\n",
    "        temperature=temperature,\n",
    "        messages=[\n",
    "            {\n",
    "                \"role\": \"system\",\n",
    "                \"content\": system_prompt\n",
    "            },\n",
    "            {\n",
    "                \"role\": \"user\",\n",
    "                \"content\": transcribe(audio_file)\n",
    "            }\n",
    "        ]\n",
    "    )\n",
    "    return response.choices[0].message.content\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "audio_fil = open(\"../data/output.mp3\", \"rb\")\n",
    "corrected_text = generate_corrected_transcript(0.7, system_prompt, audio_file=audio_fil)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'My name is Testimony.'"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "corrected_text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}