ev-audio-streaming-transcription-py

Engage Voice Audio Streaming Quick Test Package

This package is to test basic functionality of Engage Voice Audio Streaming feature by using Google Cloud Speech-To-Text Service

Getting Started

1. Enable Google Cloud Speech-To-Text Service

• Google Cloud Account
• Enable Google Speech To Text Service
• Google Service Account

After above steps, you will get a JSON key file in your local drive. Create a new environment variable with name as 'GOOGLE_APPLICATION_CREDENTIALS' and value as your file path(including file name).

2. Install This Package

1. Create a new folder and do:

pip install ev_audio_streaming_transcription_py

1. Create a new file server.py with code below in it:

from ev_audio_streaming_transcription_py import server
import asyncio

port=3333
if __name__ == "__main__":  
    asyncio.run(server.main(port))

1. Run the script
2. Install ngrok or other similar web tunneling tool, and run:

ngrok http 3333

You'll get a HTTPS address. Replace 'HTTPS' with 'WSS' and that is the address to be uploaded to your streaming profile.