Google Cloud Speech-to-Text API using Client Libraries

Figure 0$\colon$ Official Quickstart for Google Cloud Speech-to-Text Service

Figur 0呈現Google官方針對使用「Client Libraries方式」呼叫「Speech-to-Text API」的基本操作。

安裝Google speech-to-text (使用python語言)

1. Setup a GCP Console Project
   • Create or select project
   • Enable Google Speech-to-Text API for that project
   • Create a service account
   • Download a private key as JSON
2. Set the environment variable GOOGLE_APPLICATION_CREDENTIALS to the file path of the JSON file

   export GOOGLE_APPLICATION_CREDENTIALS="[PATH]"
   

3. Install and initialize the Cloud SDK
   • install $\colon$ ./google-cloud-sdk/install.sh
   • initialize $\colon$ ./google-cloud-sdk/bin/gcloud init
     1. set/select configuration
     2. authenticate user account
     3. set GCP console project connection

4. Install the client library
   pip install --upgrade google-cloud-speech

5. Make a simple audio transcription request [1] by from google.cloud import speech

※ Note: 在anaconda的環境下，執行完第3步後，GOOGLE_APPLICATION_CREDENTIALS的值會被重新設定，所以在Realization時，第二步會跟第三步交換。也就是先Install and initialize Cloud SDK (步驟三)後再export GOOGLE_APPLICATION_CREDENTIALS(步驟二)。

[0]
https://cloud.google.com/speech-to-text/docs/quickstart-client-libraries#client-libraries-install-python

[1]
https://github.com/GoogleCloudPlatform/python-docs-samples/blob/master/speech/cloud-client/quickstart.py