Enable Custom Voices
Last updated
Last updated
Voice Out lets you integrate high-quality custom voices from a variety of providers, including Amazon Polly, Google Wavenet, IBM Watson, Nvidia Riva, OpenAI, and Azure. Follow this guide to configure custom voices and enhance your text-to-speech experience.
Step 1: Navigate to Voice Settings
Open Voice Out and go to Settings (refer to the screenshot for guidance).
Under Voice, scroll down to Additional Voices and click on Enable Custom Voices.
Step 2: Configure Custom Voices
Depending on your preferred provider, input the necessary credentials to enable the voices. Here’s a breakdown of the options available:
Amazon Polly Voices Enter your AWS credentials:
Access Key ID
Secret Access Key
Google Wavenet Voices Enter your GCP API Key to enable Google Wavenet voices. Optionally, you can include Google Studio voices, but be mindful of the higher cost (10x).
IBM Watson Voices Enter the following to enable IBM Watson voices:
API Key
URL
Nvidia Riva Voices Enter the URL of your Riva TTS proxy server to enable Nvidia Riva voices.
OpenAI ChatGPT Voices Enter your OpenAI API Key to enable ChatGPT voices. You can also provide an optional API URL if you are using a custom endpoint.
Microsoft Azure Voices Enter the following credentials to enable Azure voices:
SPEECH_REGION: The Azure region where your speech services are hosted.
SPEECH_KEY: Your Azure Speech API key.
Step 3: Customize Your Text-to-Speech Experience
After enabling custom voices, return to the Voice menu and select the custom voice you want to use. You can further adjust settings like speed, pitch, and volume to tailor your listening experience.