133 lines
3.6 KiB
Plaintext
133 lines
3.6 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "e6525deb-267c-475f-a73a-7939c5bdca86",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/var/folders/k_/t1vf2gd95jbc1j3k49xxdfy80000gn/T/ipykernel_4713/2720232930.py:29: DeprecationWarning: Due to a bug, this method doesn't actually stream the response content, `.with_streaming_response.method()` should be used instead\n",
|
|
" rspd_audio.stream_to_file(speech_file_path)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from openai import OpenAI\n",
|
|
"import IPython\n",
|
|
"from datetime import datetime\n",
|
|
"import sys\n",
|
|
"from dotenv import load_dotenv\n",
|
|
"import os\n",
|
|
"\n",
|
|
"load_dotenv()\n",
|
|
"client = OpenAI(\n",
|
|
")\n",
|
|
"\n",
|
|
"\n",
|
|
"text = \"\"\"\n",
|
|
"I heard him singing.\n",
|
|
"\"\"\"\n",
|
|
"# Create audios for each versions (three was set as default previously.)\n",
|
|
"\n",
|
|
"for v in [\"alloy\", \"nova\"]:\n",
|
|
" # alloy, echo, fable, onyx, nova, and shimmer, the last two of which are femail voices.\n",
|
|
" \n",
|
|
" speech_file_path = f'sentence-{text.split(\" \")[1]}-{text.split(\" \")[2]}-{v}.mp3'\n",
|
|
" \n",
|
|
" rspd_audio = client.audio.speech.create(\n",
|
|
" model=\"tts-1\",\n",
|
|
" voice=v,\n",
|
|
" input=text\n",
|
|
" )\n",
|
|
" \n",
|
|
" rspd_audio.stream_to_file(speech_file_path)\n",
|
|
" \n",
|
|
" # IPython.display.Audio(speech_file_path)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "603fb48b-2fd5-482c-9c96-38a65fc43824",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/var/folders/k_/t1vf2gd95jbc1j3k49xxdfy80000gn/T/ipykernel_5661/2864483681.py:30: DeprecationWarning: Due to a bug, this method doesn't actually stream the response content, `.with_streaming_response.method()` should be used instead\n",
|
|
" rspd_audio.stream_to_file(speech_file_path)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from openai import OpenAI\n",
|
|
"import IPython\n",
|
|
"from datetime import datetime\n",
|
|
"import sys\n",
|
|
"from dotenv import load_dotenv\n",
|
|
"import os\n",
|
|
"\n",
|
|
"load_dotenv()\n",
|
|
"client = OpenAI(\n",
|
|
")\n",
|
|
"\n",
|
|
"\n",
|
|
"text = \"\"\"\n",
|
|
"lookout,seekout\n",
|
|
"\"\"\"\n",
|
|
"# Create audios for each versions (three was set as default previously.)\n",
|
|
"\n",
|
|
"for w in text.split(\",\"):\n",
|
|
" for v in [\"alloy\", \"nova\"]:\n",
|
|
" # alloy, echo, fable, onyx, nova, and shimmer, the last two of which are femail voices.\n",
|
|
" \n",
|
|
" speech_file_path = f\"{w.strip()}-us-{\"male\" if v == \"alloy\" else \"female\"}.mp3\"\n",
|
|
" \n",
|
|
" rspd_audio = client.audio.speech.create(\n",
|
|
" model=\"tts-1\",\n",
|
|
" voice=v,\n",
|
|
" input=w.strip()\n",
|
|
" )\n",
|
|
" \n",
|
|
" rspd_audio.stream_to_file(speech_file_path)\n",
|
|
" \n",
|
|
" # IPython.display.Audio(speech_file_path)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "a3c6184a-430f-491e-ad78-2f6e4fd36a54",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"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": "3.12.4"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|