|
# Written by retoor@molodetz.nl
|
|
|
|
# This script interfaces with Google's Text-to-Speech API to synthesize spoken audio from text.
|
|
# It also includes functionality to handle Google authentication tokens.
|
|
|
|
# External imports:
|
|
# - aiohttp: Asynchronous HTTP requests.
|
|
# - google-auth packages: For managing Google authentication tokens.
|
|
# - env, play: Local modules for playing audio and environment configurations.
|
|
|
|
# MIT License
|
|
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
# of this software and associated documentation files (the "Software"), to deal
|
|
# in the Software without restriction, including without limitation the rights
|
|
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
# copies of the Software, and to permit persons to whom the Software is
|
|
# furnished to do so, subject to the following conditions:
|
|
# The above copyright notice and this permission notice shall be included in
|
|
# all copies or substantial portions of the Software.
|
|
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER
|
|
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
|
# THE SOFTWARE.
|
|
|
|
|
|
import aiohttp
|
|
import asyncio
|
|
from urllib.parse import urlencode
|
|
import base64
|
|
import sys
|
|
from functools import cache
|
|
from google.oauth2 import id_token
|
|
from google.auth.transport import requests
|
|
import google.auth
|
|
from play import play_audio
|
|
import google.oauth2.credentials
|
|
import uuid
|
|
import pathlib
|
|
|
|
|
|
@cache
|
|
def google_token():
|
|
gcloud_default, project = google.auth.default()
|
|
from google.oauth2 import _client as google_auth_client
|
|
import google.auth.transport.urllib3 as google_auth_urllib3
|
|
import urllib3
|
|
http = urllib3.PoolManager()
|
|
request = google_auth_urllib3.Request(http)
|
|
token_uri = 'https://oauth2.googleapis.com/token'
|
|
refresh_token = gcloud_default.refresh_token
|
|
client_id = gcloud_default.client_id
|
|
client_secret = gcloud_default.client_secret
|
|
|
|
scopes = ['https://www.googleapis.com/auth/cloud-platform']
|
|
|
|
access_token, _, _, _ = google_auth_client.refresh_grant(
|
|
request, token_uri, refresh_token, client_id, client_secret, scopes)
|
|
return access_token
|
|
|
|
|
|
async def tts(text):
|
|
url = "https://texttospeech.googleapis.com/v1/text:synthesize"
|
|
text = text.replace("*", "").replace("#", "").replace("`", "").strip()
|
|
if not text:
|
|
return
|
|
|
|
headers = {
|
|
"Authorization": f"Bearer {google_token()}",
|
|
"Content-Type": "application/json",
|
|
"X-Goog-User-Project": "lisa-448004",
|
|
}
|
|
data = {
|
|
"input": {
|
|
"text": text
|
|
},
|
|
"voice": {
|
|
"languageCode": "nl-NL",
|
|
"name": "nl-NL-Standard-D",
|
|
"ssmlGender": "FEMALE"
|
|
},
|
|
"audioConfig": {
|
|
"audioEncoding": "MP3",
|
|
"speakingRate": 1.0,
|
|
"pitch": 0.0
|
|
}
|
|
}
|
|
async with aiohttp.ClientSession() as session:
|
|
response = await session.post(url, headers=headers, json=data)
|
|
response_json = await response.json()
|
|
audio_content = response_json.get("audioContent")
|
|
file = pathlib.Path(str(uuid.uuid4()) + ".mp3")
|
|
with file.open("wb") as audio_file:
|
|
audio_file.write(base64.b64decode(audio_content.encode('latin1')))
|
|
play_audio(file)
|
|
file.unlink()
|
|
return
|
|
|
|
|
|
def oud():
|
|
client = speech.SpeechClient()
|
|
|
|
with open(file_path, "rb") as audio_file:
|
|
content = audio_file.read()
|
|
|
|
audio = speech.RecognitionAudio(content=content)
|
|
config = speech.RecognitionConfig(
|
|
encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
|
|
sample_rate_hertz=16000,
|
|
language_code="en-US",
|
|
)
|
|
response = client.recognize(config=config, audio=audio)
|
|
for result in response.results:
|
|
print("Transcript:", result.alternatives[0].transcript)
|
|
|
|
|
|
async def main():
|
|
print(google_token())
|
|
await tts("If you hear this sentence, the google part works fine. Congrats.")
|
|
|
|
|
|
if __name__ == '__main__':
|
|
asyncio.run(main())
|