Using WaveNet with Google Cloud API

WaveNet is used in Cloud text-to-speech for TTS, which has a demo on the page. Currently a beta version

How to use

• Registration and Certification reference: Quickstart:text-to-speech
• Install the Python library for Google Clould
• Install Google Cloud Text-to-Speech API Python dependency (Dependencies), see GitHub instructions
• ----included, install PIP install google-cloud-texttospeech==0.1.0

To implicit the call, set the environment variable google_application_credentials to your API Key (JSON file) and reboot after completion

Python script: Text to mp3

# [START tts_synthesize_text]def Synthesize_text (text): "" "" "    synthesizes speech from the input string of text.    " "" From Google.cloud import texttospeech    client = Texttospeech. Texttospeechclient ()    input_text = Texttospeech.types.SynthesisInput (text=text)    # note:the voice can also be specified by name.    # Names of voices can is retrieved with Client.list_voices ().    Voice = Texttospeech.types.VoiceSelectionParams (        language_code= ' en-us ',        ssml_gender= Texttospeech.enums.SsmlVoiceGender.FEMALE)    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.    With open (' Output.mp3 ', ' WB ') as Out:        out.write (response.audio_content)        print (' audio content written to file "Output.mp3" ') # [END Tts_synthesize_text]

　　

WaveNet characteristics

6 Types of voice type currently supported

Parameter description

Https://cloud.google.com/text-to-speech/docs/reference/rest/v1beta1/text/synthesize#audioconfig

• Input_text

• Voice

• Audio_config

Using WaveNet with Google Cloud API