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_v1beta1.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 post(self, request, *args, **kwargs):
if request.method == 'POST':
post_data = request.POST.copy()
form = forms.BaseForm(post_data, request.FILES)
print('get post req')
print(form.errors)
if form.is_valid():
print('form is valid')
obj = form
obj.textFile = form.cleaned_data['textFile']
obj.gender = form.cleaned_data['gender']
obj.pitch = form.cleaned_data['pitch']
obj.speed = form.cleaned_data['speed']
obj.voice_type = form.cleaned_data['voice_type']
obj.save()
text_path = os.path.join(settings.MEDIA_ROOT, 'texts/', obj.textFile.name)
text = text_path
txt = Path(text).read_text(encoding='cp1252')
fileName = obj.textFile.name[:-4]
print('File Name is: {}'.format(fileName))
input_text = {'text': txt}
voice = {
'language_code': 'en-US',
'ssml_gender': obj.gender,
}
audio_config = {
'audio_encoding': texttospeech_v1beta1.enums.AudioEncoding.MP3,
'pitch': float(obj.pitch),
'speaking_rate': float(obj.speed),
}
client = texttospeech_v1beta1.TextToSpeechClient(credentials=credentials)
response = client.synthesize_speech(input_=input_text,
voice=voice,
audio_config=audio_config)
with open('media/audios/' + str(fileName) + '.mp3', 'wb') as out:
out.write(response.audio_content)
print('Audio content written to file "output.mp3"')
file = open('media/audios/' + str(fileName) + '.mp3', "rb").read()
rea_response = HttpResponse(file, content_type='audio/mpeg')
rea_response['Content-Disposition'] = 'attachment; filename={}'.format(fileName + '.mp3')
return rea_response
else:
return HttpResponse('Something went wrong', status=400)
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_v1beta1.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 __init__(
self,
gender="female",
speaking_rate=1.0,
pitch=0,
sample_rate=16000,
language_code="en-US",
name="en-US-Wavenet-C",
):
self.gender = gender
self.speaking_rate = speaking_rate
self.pitch = pitch
self.sample_rate = sample_rate
self.language_code = language_code
self.name = name
# tts
self.client = texttospeech.TextToSpeechClient()
self.voices = self._list_voices()
self.voice_parameters = self._voice_parameters()
self.audio_config = self._audio_config()
def synthesize_text(text):
"""Synthesizes speech from the input string of text."""
from google.cloud import texttospeech_v1beta1
client = texttospeech_v1beta1.TextToSpeechClient()
input_text = texttospeech_v1beta1.types.SynthesisInput(text=text)
# Note: the voice can also be specified by name.
# Names of voices can be retrieved with client.list_voices().
voice = texttospeech_v1beta1.types.VoiceSelectionParams(
language_code='en-US',
ssml_gender=texttospeech_v1beta1.enums.SsmlVoiceGender.FEMALE)
audio_config = texttospeech_v1beta1.types.AudioConfig(
audio_encoding=texttospeech_v1beta1.enums.AudioEncoding.MP3)
response = client.synthesize_speech(input_text, voice, audio_config)
# The response's audio_content is binary.
with open('output.mp3', 'wb') as out:
out.write(response.audio_content)
print('Audio content written to file "output.mp3"')
def synthesize_text(text, output_filename, output_dir, voice=None):
"""
Synthesizes speech from the input string of text.
Female voice = 0, Male voice = 1
output filename doesn't need extension
"""
from google.cloud import texttospeech_v1beta1 as texttospeech
client = texttospeech.TextToSpeechClient()
input_text = texttospeech.types.SynthesisInput(text=text)
genders = (texttospeech.enums.SsmlVoiceGender.FEMALE, texttospeech.enums.SsmlVoiceGender.MALE)
if not voice:
gender = genders[random.randrange(0, 2)]
else:
gender = genders[voice]
# Note: the voice can also be specified by name.
# Names of voices can be retrieved with client.list_voices().
voice = texttospeech.types.VoiceSelectionParams(
language_code='en-US',
ssml_gender=gender)
audio_config = texttospeech.types.AudioConfig(
audio_encoding=texttospeech.enums.AudioEncoding.MP3)
response = client.synthesize_speech(input_text, voice, audio_config)
# The response's audio_content is binary.
mp3_filepath = os.path.join(output_dir, "%s.mp3" % output_filename)
with open(mp3_filepath, 'wb') as out:
out.write(response.audio_content)
print('Audio content written to file %s' % mp3_filepath)
wav_name = os.path.join(output_dir, "%s.wav" % output_filename)
print('Audio content re-written to file %s' % wav_name)
os.system("mpg321 -w %s %s" % (wav_name, mp3_filepath))
print('Deleting mp3')
os.remove(mp3_filepath)
def google_cloud_tts(self, text, folder):
try:
client = texttospeech_v1beta1.TextToSpeechClient()
except Exception as e:
print('\n')
print('{}'.format('- ' * 30))
print(
' Error, client = texttospeech_v1beta1.TextToSpeechClient()\n {}'
.format(e))
print('{}'.format('- ' * 30))
return
input_text = texttospeech_v1beta1.types.SynthesisInput(text=text)
# Note: the voice can also be specified by name.
# Names of voices can be retrieved with client.list_voices().
voice = texttospeech_v1beta1.types.VoiceSelectionParams(
language_code='ko-KR',
ssml_gender=texttospeech_v1beta1.enums.SsmlVoiceGender.FEMALE)
audio_config = texttospeech_v1beta1.types.AudioConfig(
audio_encoding=texttospeech_v1beta1.enums.AudioEncoding.MP3
# speaking_rate = 말 하는 속도를 적어놓은 것이다, double 형태로 지정할 수 있고 범위가 있었는데.. document 에 있으니 참고바람..
# 삭제하면 1.0배속으로 된다.
# speaking_rate=0.4)
)
response = client.synthesize_speech(input_text, voice, audio_config)
# The response's audio_content is binary.
if folder is not None:
output_gcltts = self.DEFAULT_FOLDER_PATH + folder + '/' + text + '.mp3'
else:
output_gcltts = self.DEFAULT_FOLDER_PATH + text + '.mp3'
with open(output_gcltts, 'wb') as out:
out.write(response.audio_content)
print('Audio content written to file {}'.format(output_gcltts))
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_v1beta1.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
def list_voices():
"""Lists the available voices."""
from google.cloud import texttospeech_v1beta1
client = texttospeech_v1beta1.TextToSpeechClient()
# Performs the list voices request
voices = client.list_voices()
for voice in voices.voices:
# Display the voice's name. Example: tpc-vocoded
print(f"Name: {voice.name}")
# Display the supported language codes for this voice. Example: "en-US"
for language_code in voice.language_codes:
print(f"Supported language: {language_code}")
ssml_gender = texttospeech_v1beta1.SsmlVoiceGender(voice.ssml_gender)
# Display the SSML Voice Gender
print(f"SSML Voice Gender: {ssml_gender.name}")
# Display the natural sample rate hertz for this voice. Example: 24000
print(f"Natural Sample Rate Hertz: {voice.natural_sample_rate_hertz}\n")
def synthesize_text_with_audio_profile(text, output, effects_profile_id):
"""Synthesizes speech from the input string of text."""
from google.cloud import texttospeech_v1beta1 as texttospeech
client = texttospeech.TextToSpeechClient()
input_text = texttospeech.types.SynthesisInput(text=text)
# Note: the voice can also be specified by name.
# Names of voices can be retrieved with client.list_voices().
voice = texttospeech.types.VoiceSelectionParams(language_code='en-US')
# Note: you can pass in multiple effects_profile_id. They will be applied
# in the same order they are provided.
audio_config = texttospeech.types.AudioConfig(
audio_encoding=texttospeech.enums.AudioEncoding.MP3,
effects_profile_id=[effects_profile_id])
response = client.synthesize_speech(input_text, voice, audio_config)
# The response's audio_content is binary.
with open(output, 'wb') as out:
out.write(response.audio_content)
print('Audio content written to file "%s"' % output)
def goog_text2speech():
text = request.args.get(
'text',
"Oh No! There seems to be something wrong with my ram. Can you try calling back a little later after i talk to my friends in IT"
)
# Pre-process the text
#if len(text) == 0:
#text = "We are experiencing technical difficulties at the moment. Please call back later."
# Adding space between numbers for better synthesis
#if re.search(r'\b\d{1,16}\b', text):
#text = re.sub('(?<=\d)(?=\d)', ' ', text)
#print "Changed input: " + text
# Setting profile id
effects_profile_id = 'telephony-class-application'
#Setting credentials - Read env data
credentials_raw = os.environ.get('GOOGLE_APPLICATION_CREDENTIALS')
#Generate Google TTS Credentials
service_account_info = json.loads(credentials_raw)
credentials = service_account.Credentials.from_service_account_info(
service_account_info)
# Create Google Text-To-Speech client
client = texttospeech.TextToSpeechClient(credentials=credentials)
#pass the text to be synthesized by Google Text-To-Speech
input_text = texttospeech.types.SynthesisInput(text=text)
#Set the Google Text-To-Speech voice parameters
voice = texttospeech.types.VoiceSelectionParams(
language_code='en-AU',
name='en-AU-Wavenet-B',
ssml_gender=texttospeech.enums.SsmlVoiceGender.MALE)
#Set Google Text-To-Speech audio configuration parameters
audio_config = texttospeech.types.AudioConfig(
audio_encoding=texttospeech.enums.AudioEncoding.MP3,
effects_profile_id=[effects_profile_id])
# Request speech synthesis from Google Text-To-Speech
response = client.synthesize_speech(input_text, voice, audio_config)
# Write the output to a temp file
with open('output.mp3', 'wb') as out:
out.write(response.audio_content)
print('Audio content written to file "output.mp3"')
if response.audio_content:
# Read the audio stream from the response
def generate():
print 'inside google tts generate method'
with open('output.mp3', 'rb') as dmp3:
data = dmp3.read(1024)
while data:
yield data
data = dmp3.read(1024)
print 'generate complete for google tts'
return Response(generate(), mimetype="audio/mpeg")
else:
# The response didn't contain audio data, exit gracefully
print("Could not stream audio")
return "Error"
def test_list_voices(self):
client = texttospeech_v1beta1.TextToSpeechClient()
voices = client.list_voices()
assert len(voices.voices) > 0
from google.cloud import texttospeech_v1beta1
from google.oauth2 import service_account
credentials = service_account.Credentials.from_service_account_file(
"OAuth/JING-704cd29711ee.json",
scopes=["https://www.googleapis.com/auth/cloud-platform"],
)
client = texttospeech_v1beta1.TextToSpeechClient(credentials=credentials)
voice = texttospeech_v1beta1.types.VoiceSelectionParams(
language_code="en-US",
ssml_gender=texttospeech_v1beta1.enums.SsmlVoiceGender.FEMALE)
audio_config = texttospeech_v1beta1.types.AudioConfig(
audio_encoding=texttospeech_v1beta1.enums.AudioEncoding.LINEAR16)
def textToSpeech(text):
synthesis_input = texttospeech_v1beta1.types.SynthesisInput(text=text)
response = client.synthesize_speech(synthesis_input, voice, audio_config)
'''
with open(file_path, "wb") as out:
out.write(response.audio_content)
print("Audio content written to file %s" % file_path)
'''
return response.audio_content