***

id: f7fbcf5a-022b-4b2e-ae2b-fdad62017204
title: Amazon Polly
description: Learn how to use Polly TTS voices on the SignalWire platform.
slug: /voice/tts/amazon-polly
-----------------------------

Amazon Web Services' Polly TTS engine includes several models to accommodate different use cases.

## Models

SignalWire supports the following three Amazon models.

<CardGroup cols={3}>
  <Card title="Standard" href="https://docs.aws.amazon.com/polly/latest/dg/standard-voices.html">
    Polly Standard is a traditional, cost-effective, and reliable TTS model.

    Example voice ID string: `amazon.Emma:en-GB` or `amazon.Emma:standard:en-GB`
  </Card>

  <Card title="Neural" href="https://docs.aws.amazon.com/polly/latest/dg/neural-voices.html">
    Polly Neural produces more natural, human-like speech than Polly Standard.

    Example voice ID string: `amazon.Kendra:neural:en-US`
  </Card>

  <Card title="Generative" href="https://docs.aws.amazon.com/polly/latest/dg/generative-voices.html">
    Polly Generative is Amazon's largest and most realistic model.

    Example voice ID string: `amazon.Danielle:generative:en-US`
  </Card>
</CardGroup>

## Languages

Consult AWS documentation for a comprehensive and up-to-date list of supported voices,
as well as information on accented and fully bilingual voices.

<Card title="List of supported voices" href="https://docs.aws.amazon.com/polly/latest/dg/available-voices.html">
  Most Amazon Polly voices support a single language.
  Select voices from this list, which includes Standard, Neural, and Generative models.
</Card>

<CardGroup cols={2}>
  <Card title="Bilingual pronunciation" href="https://docs.aws.amazon.com/polly/latest/dg/bilingual-voices.html#accented-bilingual">
    All Amazon Polly voices support accented bilingual pronunciation through the use of the SSML `lang` tag.
  </Card>

  <Card title="Fully bilingual voices" href="https://docs.aws.amazon.com/polly/latest/dg/bilingual-voices.html#true-bilingual">
    Learn more about fully bilingual voices like `Aditi`, `Kajal`, `Hala`, and `Zayd`,
    which are designed to fluently speak two languages.
  </Card>
</CardGroup>

## Usage

Amazon voice IDs conform to the following format:

```
amazon.<voice>:<model>:<language>
```

| Parameter                                                  | Possible values                                                               | Description                             |
| :--------------------------------------------------------- | :---------------------------------------------------------------------------- | :-------------------------------------- |
| `engine`<br /><span class="required-arg">required</span>   | <ul><li>`amazon`</li><li>`polly` (will be deprecated in the future)</li></ul> | TTS engine                              |
| `voice`<br /><span class="required-arg">required</span>    | Choose from the [**Name/ID** column][polly]                                   | Voice ID                                |
| `model`<br /><span class="optional-arg">optional</span>    | `standard`, `neural`, or `generative`                                         | Amazon Polly model. Default: `standard` |
| `language`<br /><span class="optional-arg">optional</span> | Choose from the [**Language code** column][polly]                             | Sets model language. Default: `en-US`   |

**Examples:**

```
amazon.Joanna
amazon.Joanna:standard:en-US
amazon.Kendra:neural:en-US
amazon.Matthew:neural:en-US
amazon.Danielle:generative:en-US
amazon.Amy:generative:en-GB
amazon.Aditi:standard:hi-IN
```

**Simplified Format:**

For voices that only support one model, you can omit the model parameter:

```
amazon.<voice>:<language>
```

Example: `amazon.Aditi:hi-IN` (Standard model implied)

<Note>
  The `polly` engine code is being deprecated. Use `amazon` instead.
</Note>

<Warning>
  Amazon Polly has a limit of 3000 chargeable characters in a single request.
  If your TTS request is longer than 3000 characters, you will experience silence.
</Warning>

***

## Examples

See how to use Amazon Polly voices on the SignalWire platform.

<Tabs>
  <Tab title="SWML">
    Use the
    [**`languages`**](/docs/swml/reference/ai/languages#use-voice-strings)
    SWML method to set one or more voices for an [AI agent](/docs/swml/reference/ai).

    ```yaml
    version: 1.0.0
    sections:
      main:
      - ai:
          prompt:
            text: Have an open-ended conversation about flowers.
          languages:
            - name: English
              code: en-US
              voice: amazon.Ruth:neural
    ```

    Alternatively, use the [**`say_voice`** parameter](/docs/swml/reference/play#variables)
    of the [**`play`**](/docs/swml/reference/play)
    SWML method to select a voice for basic TTS.

    ```yaml
    version: 1.0.0
    sections:
      main:
      - set:
          say_voice: "amazon.Ruth:neural"
      - play: "say:Greetings. This is the Ruth voice from Amazon Polly's Neural text-to-speech model."
    ```
  </Tab>

  <Tab title="RELAY Realtime SDK">
    ```javascript
    // This example uses the Node.js SDK for SignalWire's RELAY Realtime API.
    const playback = await call.playTTS({ 
        text: "Greetings. This is the Ruth voice from Amazon Polly's Neural text-to-speech model.",
        voice: "amazon.Ruth:neural",
    });
    await playback.ended();
    ```
  </Tab>

  <Tab title="Call Flow Builder">
    ![The Call Flow Builder interface. A voice is selected in the drop-down menu.](https://files.buildwithfern.com/signalwire.docs.buildwithfern.com/docs/ff0711b6accf078bb7ffef69b47e886e8d1cd241674e12020ed6428843a7181b/assets/images/call-flow/tts/polly-cfb-voice.webp)
  </Tab>
</Tabs>

[polly]: https://docs.aws.amazon.com/polly/latest/dg/available-voices.html "Available Amazon Polly voices"