https://github.com/jenkstom/wavenet_generator

Create batch audio files for voice response systems
https://github.com/jenkstom/wavenet_generator

Last synced: 24 days ago
JSON representation

Create batch audio files for voice response systems

• Host: GitHub
• URL: https://github.com/jenkstom/wavenet_generator
• Owner: jenkstom
• Created: 2018-03-29T20:22:50.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2018-03-29T20:25:13.000Z (about 7 years ago)
• Last Synced: 2025-02-08T03:17:01.865Z (3 months ago)
• Language: Python
• Size: 1.95 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
This is a simple audio file generator for use with Google's new wavenet text-to-speech system.

Since this voice is so realistic, it is ideal for interactive voice response systems and

so I wrote a simple script to batch create sound files.

Currently this is using Python 2, and depends on the following packages:

  json

  requests

  base64

It calls the API service and writes the decoded response to an mp3 file. If you have

mpg321 you can uncomment the convert line and it will also create WAV files for you.

You might have to tweak the command to create the proper WAV files for your PBX,

but this is working for me on freeswitch.

You will need to enable the TTS API on https://cloud.google.com and put your API key 

into the script for it to work.