228 lines
6.8 KiB
Plaintext
228 lines
6.8 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": null,
|
|
"id": "77deb08f-fec3-4327-b2f9-1c893aacaddc",
|
|
"metadata": {
|
|
"collapsed": true,
|
|
"jupyter": {
|
|
"outputs_hidden": true
|
|
}
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%pip install edge-tts pygame"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 42,
|
|
"id": "71d35cd9",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"['en-US-GuyNeural', 'en-US-AriaNeural']\n",
|
|
"ma\n",
|
|
"../audios/ma-us-male.mp3 created\n",
|
|
"../audios/ma-us-female.mp3 created\n",
|
|
"\n",
|
|
"room\n",
|
|
"../audios/room-us-male.mp3 created\n",
|
|
"../audios/room-us-female.mp3 created\n",
|
|
"\n",
|
|
"conversation\n",
|
|
"../audios/conversation-us-male.mp3 created\n",
|
|
"../audios/conversation-us-female.mp3 created\n",
|
|
"\n",
|
|
"army\n",
|
|
"../audios/army-us-male.mp3 created\n",
|
|
"../audios/army-us-female.mp3 created\n",
|
|
"\n",
|
|
"mob\n",
|
|
"../audios/mob-us-male.mp3 created\n",
|
|
"../audios/mob-us-female.mp3 created\n",
|
|
"\n",
|
|
"mom\n",
|
|
"../audios/mom-us-male.mp3 created\n",
|
|
"../audios/mom-us-female.mp3 created\n",
|
|
"\n",
|
|
"mind\n",
|
|
"../audios/mind-us-male.mp3 created\n",
|
|
"../audios/mind-us-female.mp3 created\n",
|
|
"\n",
|
|
"night\n",
|
|
"../audios/night-us-male.mp3 created\n",
|
|
"../audios/night-us-female.mp3 created\n",
|
|
"\n",
|
|
"nine\n",
|
|
"../audios/nine-us-male.mp3 created\n",
|
|
"../audios/nine-us-female.mp3 created\n",
|
|
"\n",
|
|
"know\n",
|
|
"../audios/know-us-male.mp3 created\n",
|
|
"../audios/know-us-female.mp3 created\n",
|
|
"\n",
|
|
"knight\n",
|
|
"../audios/knight-us-male.mp3 created\n",
|
|
"../audios/knight-us-female.mp3 created\n",
|
|
"\n",
|
|
"gnaw\n",
|
|
"../audios/gnaw-us-male.mp3 created\n",
|
|
"../audios/gnaw-us-female.mp3 created\n",
|
|
"\n",
|
|
"gnome\n",
|
|
"../audios/gnome-us-male.mp3 created\n",
|
|
"../audios/gnome-us-female.mp3 created\n",
|
|
"\n",
|
|
"anchor\n",
|
|
"../audios/anchor-us-male.mp3 created\n",
|
|
"../audios/anchor-us-female.mp3 created\n",
|
|
"\n",
|
|
"bank\n",
|
|
"../audios/bank-us-male.mp3 created\n",
|
|
"../audios/bank-us-female.mp3 created\n",
|
|
"\n",
|
|
"thank\n",
|
|
"../audios/thank-us-male.mp3 exists, skipping...\n",
|
|
"../audios/thank-us-female.mp3 exists, skipping...\n",
|
|
"\n",
|
|
"bang\n",
|
|
"../audios/bang-us-male.mp3 created\n",
|
|
"../audios/bang-us-female.mp3 created\n",
|
|
"\n",
|
|
"long\n",
|
|
"../audios/long-us-male.mp3 created\n",
|
|
"../audios/long-us-female.mp3 created\n",
|
|
"\n",
|
|
"sing\n",
|
|
"../audios/sing-us-male.mp3 created\n",
|
|
"../audios/sing-us-female.mp3 created\n",
|
|
"\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",
|
|
"sam\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.replace(\" \", \"-\")}-{regions[i]}-{genders[i]}.mp3'\n",
|
|
" await generate_edge_tts_audio(w, filename, voice=voice, verbose=True, overwrite=False, play=True)\n"
|
|
]
|
|
},
|
|
{
|
|
"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)"
|
|
]
|
|
}
|
|
],
|
|
"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
|
|
}
|