def test_list_voices_exception(self):
# Mock the API response
channel = ChannelStub(responses=[CustomException()])
client = texttospeech_v1.TextToSpeechClient(channel=channel)
with pytest.raises(CustomException):
client.list_voices()
def text_to_speech():
with open("introduction.txt", "r") as intro_ssml:
ssml_text = intro_ssml.read()
input = texttospeech.types.SynthesisInput(ssml=ssml_text)
# voice = texttospeech.types.VoiceSelectionParams(
# language_code='uk-UA',
# name='uk-UA-Wavenet-A',
# ssml_gender=texttospeech.enums.SsmlVoiceGender.FEMALE)
voice = texttospeech.types.VoiceSelectionParams(
language_code='en-US',
# name='uk-UA-Wavenet-A',
ssml_gender=texttospeech.enums.SsmlVoiceGender.MALE)
audio_config = texttospeech.types.AudioConfig(audio_encoding=texttospeech.enums.AudioEncoding.MP3)
client = texttospeech.TextToSpeechClient()
# print(client.list_voices())
response = client.synthesize_speech(input, voice, audio_config)
with open('output.mp3', 'wb') as out:
# Write the response to the output file.
out.write(response.audio_content)
print('Audio content written to file "output.mp3"')
def run_quickstart():
# [START tts_quickstart]
"""Synthesizes speech from the input string of text or ssml.
Note: ssml must be well-formed according to:
https://www.w3.org/TR/speech-synthesis/
"""
from google.cloud import texttospeech_v1
# Instantiates a client
client = texttospeech_v1.TextToSpeechClient()
# Set the text input to be synthesized
synthesis_input = texttospeech.types.SynthesisInput(text="Hello, World!")
# Build the voice request, select the language code ("en-US") and the ssml
# voice gender ("neutral")
voice = texttospeech.types.VoiceSelectionParams(
language_code='en-US',
ssml_gender=texttospeech.enums.SsmlVoiceGender.NEUTRAL)
# Select the type of audio file you want returned
audio_config = texttospeech.types.AudioConfig(
audio_encoding=texttospeech.enums.AudioEncoding.MP3)
# Perform the text-to-speech request on the text input with the selected
# voice parameters and audio file type
response = client.synthesize_speech(synthesis_input, voice, audio_config)
# The response's audio_content is binary.
with open('output.mp3', 'wb') as out:
# Write the response to the output file.
out.write(response.audio_content)
print('Audio content written to file "output.mp3"')
def test_synthesize_speech(self):
# Setup Expected Response
audio_content = b'16'
expected_response = {'audio_content': audio_content}
expected_response = cloud_tts_pb2.SynthesizeSpeechResponse(
**expected_response)
# Mock the API response
channel = ChannelStub(responses=[expected_response])
patch = mock.patch('google.api_core.grpc_helpers.create_channel')
with patch as create_channel:
create_channel.return_value = channel
client = texttospeech_v1.TextToSpeechClient()
# Setup Request
input_ = {}
voice = {}
audio_config = {}
response = client.synthesize_speech(input_, voice, audio_config)
assert expected_response == response
assert len(channel.requests) == 1
expected_request = cloud_tts_pb2.SynthesizeSpeechRequest(
input=input_, voice=voice, audio_config=audio_config)
actual_request = channel.requests[0][1]
assert expected_request == actual_request
def test_list_voices_exception(self):
# Mock the API response
channel = ChannelStub(responses=[CustomException()])
patch = mock.patch('google.api_core.grpc_helpers.create_channel')
with patch as create_channel:
create_channel.return_value = channel
client = texttospeech_v1.TextToSpeechClient()
with pytest.raises(CustomException):
client.list_voices()
def test_synthesize_speech_exception(self):
# Mock the API response
channel = ChannelStub(responses=[CustomException()])
client = texttospeech_v1.TextToSpeechClient(channel=channel)
# Setup request
input_ = {}
voice = {}
audio_config = {}
with pytest.raises(CustomException):
client.synthesize_speech(input_, voice, audio_config)
def test_synthesize_speech(self):
client = texttospeech_v1.TextToSpeechClient()
synthesis_input = texttospeech_v1.types.SynthesisInput(
text="Hello, World!")
voice = texttospeech_v1.types.VoiceSelectionParams(
language_code="en-US",
ssml_gender=texttospeech_v1.enums.SsmlVoiceGender.NEUTRAL,
)
audio_config = texttospeech_v1.types.AudioConfig(
audio_encoding=texttospeech_v1.enums.AudioEncoding.MP3)
response = client.synthesize_speech(synthesis_input, voice,
audio_config)
assert response.audio_content is not None
def test_synthesize_speech_exception(self):
# Mock the API response
channel = ChannelStub(responses=[CustomException()])
patch = mock.patch('google.api_core.grpc_helpers.create_channel')
with patch as create_channel:
create_channel.return_value = channel
client = texttospeech_v1.TextToSpeechClient()
# Setup request
input_ = {}
voice = {}
audio_config = {}
with pytest.raises(CustomException):
client.synthesize_speech(input_, voice, audio_config)
def test_list_voices(self):
# Setup Expected Response
expected_response = {}
expected_response = cloud_tts_pb2.ListVoicesResponse(
**expected_response)
# Mock the API response
channel = ChannelStub(responses=[expected_response])
client = texttospeech_v1.TextToSpeechClient(channel=channel)
response = client.list_voices()
assert expected_response == response
assert len(channel.requests) == 1
expected_request = cloud_tts_pb2.ListVoicesRequest()
actual_request = channel.requests[0][1]
assert expected_request == actual_request
def __init__(self, voice_name="en-US-Wavenet-D"):
self._channel = TextToSpeechGrpcTransport.create_channel(
options=[("grpc.max_receive_message_length", 24 * 1024 * 1024)]
)
self._transport = TextToSpeechGrpcTransport(channel=self._channel)
self.client = texttospeech_v1.TextToSpeechClient(transport=self._transport)
self.voice = texttospeech.VoiceSelectionParams(
language_code="en-US", name=voice_name
)
self.audio_config = texttospeech.AudioConfig(
audio_encoding=texttospeech.AudioEncoding.LINEAR16
)
# rate limit stuff
self._minute = -1
self._requests_this_minute = 0
self._chars_this_minute = 0
self._chunk_counter = 1
self._coverfile = ''
self._used_characters = 0
def useTextToSpeech(speaking, lang, speed):
from google.cloud import texttospeech_v1 as texttospeech
client = texttospeech.TextToSpeechClient()
synthesis_input = texttospeech.types.SynthesisInput(text=speaking)
voice = texttospeech.types.VoiceSelectionParams(
language_code=lang,
ssml_gender=texttospeech.enums.SsmlVoiceGender.FEMALE,
)
audio_config = texttospeech.types.AudioConfig(
audio_encoding=texttospeech.enums.AudioEncoding.MP3,
speaking_rate=speed)
response = client.synthesize_speech(synthesis_input, voice, audio_config)
with open('output.mp3', 'wb') as out:
out.write(response.audio_content)
# print('Audio content written to file "output.mp3"')
from playsound import playsound
import os
playsound(os.path.abspath('output.mp3'))
def test_list_voices(self):
# Setup Expected Response
expected_response = {}
expected_response = cloud_tts_pb2.ListVoicesResponse(
**expected_response)
# Mock the API response
channel = ChannelStub(responses=[expected_response])
patch = mock.patch('google.api_core.grpc_helpers.create_channel')
with patch as create_channel:
create_channel.return_value = channel
client = texttospeech_v1.TextToSpeechClient()
response = client.list_voices()
assert expected_response == response
assert len(channel.requests) == 1
expected_request = cloud_tts_pb2.ListVoicesRequest()
actual_request = channel.requests[0][1]
assert expected_request == actual_request
def test_synthesize_speech(self):
# Setup Expected Response
audio_content = b'16'
expected_response = {'audio_content': audio_content}
expected_response = cloud_tts_pb2.SynthesizeSpeechResponse(
**expected_response)
# Mock the API response
channel = ChannelStub(responses=[expected_response])
client = texttospeech_v1.TextToSpeechClient(channel=channel)
# Setup Request
input_ = {}
voice = {}
audio_config = {}
response = client.synthesize_speech(input_, voice, audio_config)
assert expected_response == response
assert len(channel.requests) == 1
expected_request = cloud_tts_pb2.SynthesizeSpeechRequest(
input=input_, voice=voice, audio_config=audio_config)
actual_request = channel.requests[0][1]
assert expected_request == actual_request
Note: ssml must be well-formed according to:
https://www.w3.org/TR/speech-synthesis/
"""
# export GOOGLE_APPLICATION_CREDENTIALS='/home/luolu/Downloads/my-project-82452-txt2speech-d2f355055141.json'
# export GOOGLE_CLOUD_PROJECT="my-project-82452-txt2speech"
# export GCLOUD_PROJECT=$GOOGLE_CLOUD_PROJECT
from google.cloud import texttospeech
from google.cloud import texttospeech_v1
from google.cloud import texttospeech_v1beta1
import os
# os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "/home/luolu/PycharmProjects/video-processing/pqAmazon/my-project-82452-txt2speech-32250ea466e8.json"
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "/home/luolu/Downloads/my-project-82452-txt2speech-d2f355055141.json"
# Instantiates a client
client = texttospeech_v1.TextToSpeechClient()
print("client list: ", client.list_voices())
with open("/home/luolu/Desktop/amazontest/test/B07F81VDL2.txt", 'r') as file:
txt_data = file.read().replace('\n', '')
# Set the text input to be synthesized
synthesis_input = texttospeech_v1.SynthesisInput(text=txt_data)
# Build the voice request, select the language code ("en-US") and the ssml
# voice gender ("neutral")
voice = texttospeech_v1.VoiceSelectionParams(
language_code="en-US",
name="en-US-Wavenet-E",
ssml_gender=texttospeech_v1.SsmlVoiceGender.FEMALE
)
from ebooklib import epub
# Google Cloud Imports
from google.cloud import texttospeech
from google.cloud import texttospeech_v1
# NOTE: This is here to resolve the issues with the ProtoBuf size-restrictions with the Python implementation of the
# Google Cloud API and will hopefully not be required with future releases of this API
# See: https://github.com/googleapis/python-texttospeech/issues/5
from google.cloud.texttospeech_v1.services.text_to_speech.transports.grpc import (
TextToSpeechGrpcTransport, )
channel = TextToSpeechGrpcTransport.create_channel(
options=[("grpc.max_receive_message_length", 24 * 1024 * 1024)])
transport = TextToSpeechGrpcTransport(channel=channel)
client = texttospeech_v1.TextToSpeechClient(transport=transport)
def TextToSpeech(voice_name, text):
""" Processes the input text and returns the wav-encoded audio"""
# TODO Check the Voice, OutputFilename and Text meet requirements
language_code = "-".join(voice_name.split("-")[:2])
text_input = texttospeech_v1.SynthesisInput(text=text)
voice_params = texttospeech_v1.VoiceSelectionParams(
language_code=language_code, name=voice_name)
audio_config = texttospeech_v1.AudioConfig(
audio_encoding=texttospeech.AudioEncoding.LINEAR16)
response = client.synthesize_speech(input=text_input,
voice=voice_params,
audio_config=audio_config)
MINIO_HOST = os.environ.get('MINIO_HOST', None)
MINIO_ACCESS_KEY = os.environ.get('MINIO_ACCESS_KEY', None)
MINIO_SECRET_KEY = os.environ.get('MINIO_SECRET_KEY', None)
MINIO_BUCKET = os.environ.get('MINIO_BUCKET', None)
if MINIO_HOST:
minioClient = Minio(MINIO_HOST,
access_key=MINIO_ACCESS_KEY,
secret_key=MINIO_SECRET_KEY,
secure=True)
else:
minioClient = None
GOOGLE_APPLICATION_CREDENTIALS = os.environ.get(
"GOOGLE_APPLICATION_CREDENTIALS", None)
if GOOGLE_APPLICATION_CREDENTIALS:
TTSClient = tts.TextToSpeechClient()
STTClient = stt.SpeechClient()
else:
TTSClient = None
STTClient = None
# Global Variables
COUNT_MSG = 0
USERS = {}
COUNT_PM = {}
LASTMSG = {}
ENABLE_KILLME = True
def test_list_voices(self):
client = texttospeech_v1.TextToSpeechClient()
voices = client.list_voices()
assert len(voices.voices) > 0
SECTION_BREAK = 2 # sec
CAPTION_BREAK = 1.5 # sec
# prediction labels
LABEL_BODY = "body"
LABEL_HEADER = "header"
LABEL_CAPTION = "caption"
LABEL_OTHER = "other"
FEATURE_CSV_HEADER = (
"id,text,chars,width,height,area,char_size,pos_x,pos_y,aspect,layout")
# ML API clients
project_id = os.environ.get("GCLOUD_PROJECT") # os.environ["GCP_PROJECT"]
vision_client = vision.ImageAnnotatorClient()
storage_client = storage.Client()
speech_client = texttospeech.TextToSpeechClient()
client_options = {'api_endpoint': 'eu-automl.googleapis.com:443'}
automl_client = automl.TablesClient(project=project_id,
region=compute_region,
client_options=client_options)
def p2a_gcs_trigger(file, context):
# get bucket and blob
file_name = file["name"]
bucket = None
file_blob = None
while bucket == None or file_blob == None: # retry
bucket = storage_client.get_bucket(file["bucket"])
file_blob = bucket.get_blob(file_name)
from google.cloud import texttospeech_v1 as texttospeech
speech_api = texttospeech.TextToSpeechClient()
def text_to_audio_file(text, audio_filename):
"""
Convert `text` into an audio file, written at `audio_filename`
"""
input_text = texttospeech.types.SynthesisInput(text=text)
voice = texttospeech.types.VoiceSelectionParams(language_code='en-US',
name='en-US-Wavenet-F')
audio_config = texttospeech.types.AudioConfig(
speaking_rate=1.3, audio_encoding=texttospeech.enums.AudioEncoding.MP3)
response = speech_api.synthesize_speech(input_text, voice, audio_config)
with open(audio_filename, 'wb') as out:
out.write(response.audio_content)
