Files
everyone-can-use-english/1000-hours/public/jupyter-notebooks/edge-tts-valcab-pronounciation.ipynb
2024-08-22 17:36:26 +08:00

404 lines
13 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"id": "b94f103d-ac43-4d13-83cb-eb5090220881",
"metadata": {},
"source": [
"# EdgeTTS\n",
"\n",
"https://github.com/rany2/edge-tts\n",
"\n",
"edge-tts is a Python module that allows you to use Microsoft Edge's online text-to-speech service from within your Python code or using the provided edge-tts or edge-playback command."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "77deb08f-fec3-4327-b2f9-1c893aacaddc",
"metadata": {
"collapsed": true,
"jupyter": {
"outputs_hidden": true
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: edge-tts in /opt/homebrew/Caskroom/miniconda/base/lib/python3.12/site-packages (6.1.10)\n",
"Requirement already satisfied: aiohttp>=3.8.0 in /opt/homebrew/Caskroom/miniconda/base/lib/python3.12/site-packages (from edge-tts) (3.9.3)\n",
"Requirement already satisfied: certifi>=2023.11.17 in /opt/homebrew/Caskroom/miniconda/base/lib/python3.12/site-packages (from edge-tts) (2024.2.2)\n",
"Requirement already satisfied: aiosignal>=1.1.2 in /opt/homebrew/Caskroom/miniconda/base/lib/python3.12/site-packages (from aiohttp>=3.8.0->edge-tts) (1.3.1)\n",
"Requirement already satisfied: attrs>=17.3.0 in /opt/homebrew/Caskroom/miniconda/base/lib/python3.12/site-packages (from aiohttp>=3.8.0->edge-tts) (23.2.0)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in /opt/homebrew/Caskroom/miniconda/base/lib/python3.12/site-packages (from aiohttp>=3.8.0->edge-tts) (1.4.1)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in /opt/homebrew/Caskroom/miniconda/base/lib/python3.12/site-packages (from aiohttp>=3.8.0->edge-tts) (6.0.5)\n",
"Requirement already satisfied: yarl<2.0,>=1.0 in /opt/homebrew/Caskroom/miniconda/base/lib/python3.12/site-packages (from aiohttp>=3.8.0->edge-tts) (1.9.4)\n",
"Requirement already satisfied: idna>=2.0 in /opt/homebrew/Caskroom/miniconda/base/lib/python3.12/site-packages (from yarl<2.0,>=1.0->aiohttp>=3.8.0->edge-tts) (3.4)\n",
"Requirement already satisfied: pygame in /opt/homebrew/Caskroom/miniconda/base/lib/python3.12/site-packages (2.5.2)\n"
]
}
],
"source": [
"%pip install edge-tts"
]
},
{
"cell_type": "markdown",
"id": "2df59a42",
"metadata": {},
"source": [
"# English Voices\n",
"\n",
"* voice = \"en-US-GuyNeural\" (Male)\n",
"* voice = \"en-US-AnaNeural\" (Female)\n",
"* voice = \"en-US-AndrewNeural\" (Male)\n",
"* voice = \"en-US-AriaNeural\" (Female)\n",
"* voice = \"en-US-AvaNeural\" (Female)\n",
"* voice = \"en-US-BrianNeural\" (Male)\n",
"* voice = \"en-US-ChristopherNeural\" (Male)\n",
"* voice = \"en-US-EmmaNeural\" (Female)\n",
"* voice = \"en-US-EricNeural\" (Male)\n",
"* voice = \"en-US-GuyNeural\" (Male)\n",
"* voice = \"en-US-JennyNeural\" (Female)\n",
"* voice = \"en-US-MichelleNeural\" (Female)\n",
"* voice = \"en-US-RogerNeural\" (Male)\n",
"* voice = \"en-US-SteffanNeural\" (Male)\n",
"* voice = \"en-GB-LibbyNeural\" (Female)\n",
"* voice = \"en-GB-MaisieNeural\" (Female)\n",
"* voice = \"en-GB-RyanNeural\" (Male)\n",
"* voice = \"en-GB-SoniaNeural\" (Female)\n",
"* voice = \"en-GB-ThomasNeural\" (Male)\n",
"* voice = \"en-AU-NatashaNeural\" (Female)\n",
"* voice = \"en-AU-WilliamNeural\" (Male)\n",
"* voice = \"en-CA-ClaraNeural\" (Female)\n",
"* voice = \"en-CA-LiamNeural\" (Male)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "71d35cd9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['en-US-GuyNeural', 'en-US-AriaNeural']\n",
"ear\n",
"../audios/ear-us-male.mp3 created\n",
"../audios/ear-us-female.mp3 created\n",
"idea\n",
"../audios/idea-us-male.mp3 created\n",
"../audios/idea-us-female.mp3 created\n"
]
}
],
"source": [
"import edge_tts\n",
"import os\n",
"import pygame\n",
"import time\n",
"\n",
"async def generate_edge_tts_audio(text, file_name, voice='en-US-GuyNeural', style='newscast-formal', verbose=False, play=False, overwrite=False):\n",
" communicate = edge_tts.Communicate(text, voice)\n",
" # whether file exists?\n",
" if os.path.exists(file_name):\n",
" if overwrite:\n",
" if verbose:\n",
" print(f'{file_name} exists, overwriting...')\n",
" else:\n",
" if verbose:\n",
" print(f'{file_name} exists, skipping...')\n",
" return\n",
" \n",
" await communicate.save(file_name)\n",
" if play:\n",
" pygame.mixer.init()\n",
" pygame.mixer.music.load(file_name)\n",
" pygame.mixer.music.play()\n",
" if verbose:\n",
" print(f'{file_name} created')\n",
" \n",
" time.sleep(1.5)\n",
"\n",
"\n",
"\n",
"voices = [\"en-US-GuyNeural\", \"en-US-AriaNeural\", \"en-GB-RyanNeural\", \"en-GB-LibbyNeural\"]\n",
"regions = ['us', 'us', 'uk', 'uk']\n",
"genders = ['male', 'female', 'male', 'female']\n",
"\n",
"# only_us = False\n",
"only_us = True\n",
"if only_us:\n",
" voices = voices[:2]\n",
" print(voices)\n",
"\n",
"words = \"\"\"\n",
"bed,\n",
"guess,\n",
"pet,\n",
"bread,\n",
"dead,\n",
"lead,\n",
"any,\n",
"many,\n",
"says,\n",
"again,\n",
"said,\n",
"friend,\n",
"apple,\n",
"cat,\n",
"glass,\n",
"calf,\n",
"half,\n",
"laugh,\n",
"draught,\n",
"\"\"\"\n",
"\n",
"for word in words.strip().split(','):\n",
" print(word)\n",
" for i, voice in enumerate(voices):\n",
" w = word.strip().lower()\n",
" if len(w) > 0:\n",
" filename = f'../audios/{w}-{regions[i]}-{genders[i]}.mp3'\n",
" await generate_edge_tts_audio(w, filename, voice=voice, verbose=True, overwrite=False, play=True)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "862f0948",
"metadata": {},
"outputs": [],
"source": [
"pygame.mixer.init()\n",
"pygame.mixer.music.load(OUTPUT_FILE)\n",
"pygame.mixer.music.play()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "00939422-fbf9-4842-b82a-b6106624c075",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Files created!\n"
]
}
],
"source": [
"#American\n",
"\n",
"import asyncio\n",
"import edge_tts\n",
"import pygame\n",
"\n",
"TEXT = \"hands\"\n",
"Wordlist = TEXT.split(\",\")\n",
"\n",
"for w in Wordlist:\n",
" # for VOICE in ['en-US-GuyNeural', 'en-US-JennyNeural', 'en-GB-RyanNeural', 'en-GB-SoniaNeural']:\n",
" for VOICE in ['en-US-GuyNeural', 'en-US-MichelleNeural']:\n",
" w = w.strip()\n",
" # OUTPUT_FILE = f\"{w}-{VOICE.replace('EricNeural', 'Guy-Male').replace('JennyNeural', 'Jenny-Female').replace('RyanNeural', 'Ryan-Male').replace('SoniaNeural', 'Sonia-Female').lower()}.mp3\"\n",
" OUTPUT_FILE = f\"{w}-{VOICE.replace('EricNeural', 'Male').replace('MichelleNeural', 'Female').replace('en-', '').lower()}.mp3\"\n",
" communicate = edge_tts.Communicate(w, VOICE)\n",
" await communicate.save(OUTPUT_FILE) \n",
"\n",
"print(\"Files created!\") "
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "cecefa85-b37d-457e-9e99-e582dabdfb9f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Files created!\n"
]
}
],
"source": [
"#American Sentence\n",
"\n",
"import asyncio\n",
"import edge_tts\n",
"import pygame\n",
"\n",
"TEXT = \"cat,foot\"\n",
"Wordlist = TEXT.split(\",\")\n",
"\n",
"for w in Wordlist:\n",
" # for VOICE in ['en-US-GuyNeural', 'en-US-JennyNeural', 'en-GB-RyanNeural', 'en-GB-SoniaNeural']:\n",
" for VOICE in ['en-US-EricNeural', 'en-US-MichelleNeural']:\n",
" w = w.strip().replace(' ', '-')\n",
" # OUTPUT_FILE = f\"{w}-{VOICE.replace('EricNeural', 'Guy-Male').replace('JennyNeural', 'Jenny-Female').replace('RyanNeural', 'Ryan-Male').replace('SoniaNeural', 'Sonia-Female').lower()}.mp3\"\n",
" OUTPUT_FILE = f\"{w}-{VOICE.replace('EricNeural', 'Male').replace('MichelleNeural', 'Female').replace('en-', '').lower()}.mp3\"\n",
" communicate = edge_tts.Communicate(w, VOICE)\n",
" await communicate.save(OUTPUT_FILE) \n",
"\n",
"print(\"Files created!\") "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "93f68a91-7e6b-45ef-932e-533b695e4ac1",
"metadata": {},
"outputs": [],
"source": [
"# ru-RU-DmitryNeural\n",
"# ko-KR-InJoonNeural"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "474c3f39-11ed-4d0a-b039-63df8b270044",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Files created!\n"
]
}
],
"source": [
"# British\n",
"\n",
"import asyncio\n",
"import edge_tts\n",
"import pygame\n",
"\n",
"TEXT = \"speak, student, school, frustrate\"\n",
"Wordlist = TEXT.split(\",\")\n",
"\n",
"for w in Wordlist:\n",
" # for VOICE in ['en-US-GuyNeural', 'en-US-JennyNeural', 'en-GB-RyanNeural', 'en-GB-SoniaNeural']:\n",
" for VOICE in ['en-GB-RyanNeural', 'en-GB-SoniaNeural']:\n",
" w = w.strip()\n",
" # OUTPUT_FILE = f\"{w}-{VOICE.replace('EricNeural', 'Guy-Male').replace('JennyNeural', 'Jenny-Female').replace('RyanNeural', 'Ryan-Male').replace('SoniaNeural', 'Sonia-Female').lower()}.mp3\"\n",
" OUTPUT_FILE = f\"{w}-{VOICE.replace('RyanNeural', 'Male').replace('SoniaNeural', 'Female').replace('en-GB-', 'uk-').lower()}.mp3\"\n",
" communicate = edge_tts.Communicate(w, VOICE)\n",
" await communicate.save(OUTPUT_FILE) \n",
"\n",
"print(\"Files created!\") "
]
},
{
"cell_type": "code",
"execution_count": 49,
"id": "42ecfe3f-f3ac-4fb7-92d0-795d51972051",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Files created!\n"
]
}
],
"source": [
"#Korean\n",
"\n",
"import asyncio\n",
"import edge_tts\n",
"import pygame\n",
"\n",
"TEXT = \"photo, video\"\n",
"Wordlist = TEXT.split(\",\")\n",
"\n",
"for w in Wordlist:\n",
" # for VOICE in ['en-US-GuyNeural', 'en-US-JennyNeural', 'en-GB-RyanNeural', 'en-GB-SoniaNeural']:\n",
" for VOICE in ['ko-KR-InJoonNeural']:\n",
" w = w.strip()\n",
" # OUTPUT_FILE = f\"{w}-{VOICE.replace('EricNeural', 'Guy-Male').replace('JennyNeural', 'Jenny-Female').replace('RyanNeural', 'Ryan-Male').replace('SoniaNeural', 'Sonia-Female').lower()}.mp3\"\n",
" OUTPUT_FILE = f\"{w}-{VOICE.replace('InJoonNeural', 'kr').replace('SoniaNeural', 'Female').replace('ko-KR', 'ko').lower()}.mp3\"\n",
" communicate = edge_tts.Communicate(w, VOICE)\n",
" await communicate.save(OUTPUT_FILE) \n",
"\n",
"print(\"Files created!\") "
]
},
{
"cell_type": "code",
"execution_count": 55,
"id": "95b12e63-f92d-49b4-bd51-a2b9d059fd52",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Files created!\n"
]
}
],
"source": [
"#Chinese\n",
"\n",
"import asyncio\n",
"import edge_tts\n",
"import pygame\n",
"\n",
"TEXT = \"room\"\n",
"Wordlist = TEXT.split(\",\")\n",
"\n",
"for w in Wordlist:\n",
" # for VOICE in ['en-US-GuyNeural', 'en-US-JennyNeural', 'en-GB-RyanNeural', 'en-GB-SoniaNeural']:\n",
" for VOICE in ['zh-CN-liaoning-XiaobeiNeural']:\n",
" w = w.strip()\n",
" # OUTPUT_FILE = f\"{w}-{VOICE.replace('EricNeural', 'Guy-Male').replace('JennyNeural', 'Jenny-Female').replace('RyanNeural', 'Ryan-Male').replace('SoniaNeural', 'Sonia-Female').lower()}.mp3\"\n",
" OUTPUT_FILE = f\"{w}-{VOICE.replace('liaoning-XiaobeiNeural', 'zh').replace('SoniaNeural', 'Female').replace('zh-CN', 'cn').lower()}.mp3\"\n",
" communicate = edge_tts.Communicate(w, VOICE)\n",
" await communicate.save(OUTPUT_FILE) \n",
"\n",
"print(\"Files created!\") "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2128587f-e6c8-488d-8c40-6c958b9c735e",
"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": "3.12.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}