def text_to_speech(text, outfile):
"""Converts plaintext to SSML and
generates synthetic audio from SSML
ARGS
text: text to synthesize
outfile: filename to use to store synthetic audio
RETURNS
nothing
"""
# Replace special characters with HTML Ampersand Character Codes
# These Codes prevent the API from confusing text with
# SSML commands
# For example, '<' --> '<' and '&' --> '&'
escaped_lines = html.escape(text)
# Convert plaintext to SSML in order to wait two seconds
# between each line in synthetic speech
ssml = '<speak>{}</speak>'.format(
escaped_lines.replace('\n', '\n<break time="2s"/>'))
# Instantiates a client
client = texttospeech.TextToSpeechClient()
# Sets the text input to be synthesized
synthesis_input = texttospeech.SynthesisInput(ssml=ssml)
# Builds the voice request, selects the language code ("en-US") and
# the SSML voice gender ("MALE")
voice = texttospeech.VoiceSelectionParams(
language_code='en-US',
ssml_gender=texttospeech.SsmlVoiceGender.MALE)
# Selects the type of audio file to return
audio_config = texttospeech.AudioConfig(
audio_encoding=texttospeech.AudioEncoding.MP3)
# Performs the text-to-speech request on the text input with the selected
# voice parameters and audio file type
request = texttospeech.SynthesizeSpeechRequest(
input=synthesis_input,
voice=voice,
audio_config=audio_config
)
response = client.synthesize_speech(request=request)
# Writes the synthetic audio to the output file.
with open(outfile, 'wb') as out:
out.write(response.audio_content)
print('Audio content written to file ' + outfile)
def synthesize(self, text: str, voice: Voice) -> bytes:
"""Synthesizes text and returns the voice as an mp3 file."""
input_text = texttospeech.SynthesisInput(text=text)
voice = texttospeech.VoiceSelectionParams(
language_code=voice.language_code,
name=voice.name,
ssml_gender=voice.gender,
)
audio_config = texttospeech.AudioConfig(
audio_encoding=texttospeech.AudioEncoding.MP3, speaking_rate=0.75)
request = texttospeech.SynthesizeSpeechRequest(
input=input_text, voice=voice, audio_config=audio_config)
response = self._client.synthesize_speech(request=request)
return bytes(response.audio_content)