Python WebSocket server which converts input audio stream from microphone to text using Google speech to text
Setup
-
Clone the repo
$ git clone https://github.com/dawntcherian/Google-speech-to-text-python-websocket-server-using-microphone-stream.git
-
Install pip and virtualenv if you do not already have them.
-
Create a virtualenv with Python 3.6.4
-
Install the dependencies
$ pip install -r requirements.txt
-
Provide authentication credentials to your application code by setting the environment variable GOOGLE_APPLICATION_CREDENTIALS. (Follow https://cloud.google.com/docs/authentication/getting-started)
-
Run
$ python websocket_server.py
$ python websocket_client.py