如何在 Python 中使用 Google 的 Text-to-Speech API

Question

我的钥匙已准备好提出请求并从 Google 的文本中获取语音。我尝试了这些命令以及更多命令。这些文档没有提供我发现的 Python 入门的直接解决方案。我不知道我的 API 密钥与 JSON 和 URL 一起去哪里了他们的文档中的一种解决方案是针对 CURL。. 但是涉及在必须将请求发送回他们以获取文件之后下载txt。有没有办法在 Python 中做到这一点而不涉及我必须返回的 txt？我只希望我的字符串列表作为音频文件返回。（我把我的实际密钥放在上面的块中。我不打算在这里分享它。）

Answer 1

为 JSON 文件配置 Python 应用程序并安装客户端库

1. 创建服务帐户

2. 使用此处的服务帐户创建服务帐户密钥

3. JSON 文件下载并安全保存

4. 在您的 Python 应用程序中包含 Google 应用程序凭据

5. 安装库： pip install --upgrade google-cloud-texttospeech

使用 Google 的 Python 示例找到：https : //cloud.google.com/text-to-speech/docs/reference/libraries 注意：在 Google 的示例中，它没有正确包含 name 参数。和 https://github.com/GoogleCloudPlatform/python-docs-samples/blob/master/texttospeech/cloud-client/quickstart.py

以下是使用谷歌应用程序凭据和女性的 wavenet 语音从示例中修改的内容。

os.environ["GOOGLE_APPLICATION_CREDENTIALS"]="/home/yourproject-12345.json"

from google.cloud import texttospeech

# Instantiates a client

client = texttospeech.TextToSpeechClient()

# Set the text input to be synthesized

synthesis_input = texttospeech.types.SynthesisInput(text="Do no evil!")

# Build the voice request, select the language code ("en-US") 

# ****** the NAME

# and the ssml voice gender ("neutral")

voice = texttospeech.types.VoiceSelectionParams(

    language_code='en-US',

    name='en-US-Wavenet-C',

    ssml_gender=texttospeech.enums.SsmlVoiceGender.FEMALE)

# 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"')

语音、姓名、语言代码、SSML 性别等

语音列表：https : //cloud.google.com/text-to-speech/docs/voices

在上面的代码示例中，我将 Google 示例代码中的语音更改为包含名称参数并使用 Wavenet 语音（大大改进但更贵 16 美元/百万个字符）和 SSML 性别为 FEMALE。

voice = texttospeech.types.VoiceSelectionParams(

        language_code='en-US',

        name='en-US-Wavenet-C',

        ssml_gender=texttospeech.enums.SsmlVoiceGender.FEMALE)

Answer 2

如果您想避免使用 google Python API，您可以简单地执行以下操作：

import requests 

import json

url = "https://texttospeech.googleapis.com/v1beta1/text:synthesize"

text = "This is a text"

data = {

        "input": {"text": text},

        "voice": {"name":  "fr-FR-Wavenet-A", "languageCode": "fr-FR"},

        "audioConfig": {"audioEncoding": "MP3"}

      };

headers = {"content-type": "application/json", "X-Goog-Api-Key": "YOUR_API_KEY" }

r = requests.post(url=url, json=data, headers=headers)

content = json.loads(r.content)

它与您所做的类似，但您需要包含您的 API 密钥。

Answer 3

找到了答案并丢失了我打开的 150 个 Google 文档页面之间的链接。

#(Since I'm using a Jupyter Notebook)

import os

os.environ["GOOGLE_APPLICATION_CREDENTIALS"]="/Path/to/JSON/file/jsonfile.json"

from google.cloud import texttospeech

# Instantiates a client

client = texttospeech.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"')

我耗时的追求是尝试使用 Python 通过 JSON 发送请求，但这似乎是通过自己的模块，工作正常。请注意，默认语音性别为“中性”。