> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AWS Polly

> Amazon text-to-speech

## Usage

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import AudioAgent

agent = AudioAgent(llm="polly/neural")
agent.say("Hello world!", output="hello.mp3")
```

## Setup

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
export AWS_ACCESS_KEY_ID=your-key
export AWS_SECRET_ACCESS_KEY=your-secret
export AWS_REGION_NAME=us-east-1
```

## Voices

Neural voices: `Joanna`, `Matthew`, `Kendra`, `Ivy`, `Ruth`

## Models

| Model            | Description     |
| ---------------- | --------------- |
| `polly/neural`   | Neural voices   |
| `polly/standard` | Standard voices |