通过google cloud API 使用 WaveNet

2022-11-28 09:38:18

Cloud Text-to-Speech 中使用了WaveNet，用于TTS，页面上有Demo。目前是BETA版

使用方法

注册及认证参考：Quickstart: Text-to-Speech
安装google clould 的python库
安装 Google Cloud Text-to-Speech API Python 依赖（Dependencies），参见github说明
----其中包括了，安装pip install google-cloud-texttospeech==0.1.0

为了implicit调用，设置环境变量GOOGLE_APPLICATION_CREDENTIALS到你的API Key（json文件），完成后重启

python脚本：text到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 be 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]