Amazon Polly converts text to lifelike speech in the cloud. You can download generated audio from the console, or stream it to your applications and services through the API.
- You can sinthesize texts to mp3 files directly to S3 buckets
- This is done in a background task
- There are different languages and regions
- Uses Speech Synthesis Markup Language (SSML) to complement the input text, resulting in an enhanced user experience
- The main advantages of using Polly vs on-device text-to-speech solution are:
- Lower development costs and power consumption: text-to-speech solutions requires requires computing resources (CPU, RAM and disk space)
- Support to multiple languages and voices