It has a wide selection of natural-sounding voices across multiple languages and supports both standard and neural engine options. The AWS Polly plugin for the Stream Python AI SDK allows you to add TTS functionality to your project.
Installation
Install the Stream AWS plugin withExample
Check out our AWS Polly example to see a working code sample using the plugin, or read on for extra details.Initialisation
The AWS Polly plugin for Stream exists in the form of theTTS class:
AWS credentials are resolved via the standard AWS SDK chain (environment variables, AWS profiles, or IAM roles).
Make sure your AWS credentials are properly configured with access to Amazon Polly.
Parameters
These are the parameters available in the AWS Polly TTS plugin for you to customise:| Name | Type | Default | Description |
|---|---|---|---|
region_name | str or None | None | AWS region name. If not provided, uses AWS_REGION or AWS_DEFAULT_REGION environment variable, or defaults to us-east-1. |
voice_id | str | "Joanna" | The ID of the voice to use for TTS. AWS Polly offers a variety of voices across different languages. |
text_type | str or None | "text" | Type of input text: "text" for plain text or "ssml" for Speech Synthesis Markup Language. |
engine | str or None | None | The synthesis engine to use: "standard" or "neural". Neural voices provide more natural-sounding speech. |
language_code | str or None | None | Language code for the voice (e.g., "en-US", "es-ES"). Optional parameter for specifying the language variant. |
lexicon_names | List[str] or None | None | List of pronunciation lexicon names to apply. Lexicons allow you to customize pronunciation of specific words. |
client | Any or None | None | Optional pre-configured boto3 Polly client. If not provided, a client will be created automatically. |
Functionality
Send text to convert to speech
Thesend() method sends the text passed in for the service to synthesize.
The resulting audio is then played through the configured output track.