Amazon Polly – Text To Speech
Amazon Polly uses deep learning technologies to synthesize natural sounding human speech, so you can convert any text you type into audio. Amazon’s Polly product is used by developers across a wide-range of industries, including education, media, government, and anyone that serves the visually impaired.
Here’s an overview of how it works:
Advanced VoIP Solutions uses an API to send the text that you want to synthesize, and Amazon Polly returns an audio stream. You can choose to have the audio returned in a male or female voice.
Also, Advanced VoIP Solutions has done the work of building an application gateway into our platform, so you don’t have any extra work or cost associated with using Polly for your organization. Read on to see exactly how to use this feature within the AVS dashboard.
To use Polly from within the AVS platform, just follow the simple steps below:
Applications > Recordings > Polly
Once you’re there, simply name the file, choose the voice you want, and enter the text to be synthesized. Then click save and you’re done! This can be incredibly helpful and time-saving, as well as ensure consistency across the organization.