IBM Watson text-to-speech in Python:没有这样的子资源

Question

我正在尝试基于一个简单的文本生成一个音频文件：

from ibm_watson import TextToSpeechV1
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator

authenticator = IAMAuthenticator('O6...............N')
text_to_speech = TextToSpeechV1(authenticator=authenticator)

text_to_speech.set_service_url('https://api.eu-gb.text-to-speech.watson.cloud.ibm.com/instances/b95d7....................956/v1/synthesize')

但是，我得到了以下输出：

ERROR:root: No such child resource.
Traceback (most recent call last):
  File "/Applications/anaconda2/envs/py3/lib/python3.6/site-packages/ibm_cloud_sdk_core/base_service.py", line 229, in send
    response.status_code, error_message, http_response=response)
ibm_cloud_sdk_core.api_exception.ApiException: Error: No such child resource., Code: 404 , X-global-transaction-id: 834e9.................698f5

我做错了什么？

Answer 1

对于set_service_url，请使用基本url https://api.eu-gb.text-to-speech.watson.cloud.ibm.com，如API reference中所示。

然后，您可以调用synthesize方法(请参阅API参考中的example )。

with open('hello_world.wav', 'wb') as audio_file:
    audio_file.write(
        text_to_speech.synthesize(
            'Hello world',
            voice='en-US_AllisonVoice',
            accept='audio/wav'        
        ).get_result().content)