> Fetch clean Markdown by appending `.md` to any page URL under https://signalwire.com/docs or requesting it with the HTTP header `Accept: text/markdown`. The root index at https://signalwire.com/docs/llms.txt lists the available documentation indexes.

# Google Cloud

> Learn how to use Google Cloud TTS voices on the SignalWire platform.

Google Cloud offers a number of robust text-to-speech
[voice models](https://cloud.google.com/text-to-speech/docs/voice-types).
SignalWire supports all Google Cloud voices in both General Availability and Preview
[launch stages](https://cloud.google.com/products?hl=en#product-launch-stages),
except for the Studio model.

## Models

Google Cloud offers multiple TTS model types with varying quality and pricing:

| Model Type | Description                                      |
| ---------- | ------------------------------------------------ |
| `Standard` | Basic, budget-friendly TTS model                 |
| `WaveNet`  | Deep learning-based, natural and lifelike speech |
| `Neural2`  | Advanced model with human-like pronunciation     |
| `Polyglot` | Multi-language variants of specific voices       |

The model type is encoded in the voice name (e.g., `en-US-Neural2-A`, `es-ES-Wavenet-B`).

* [Standard](https://cloud.google.com/text-to-speech/docs/voice-types#standard_voices)
  is a basic, reliable, and budget-friendly text-to-speech model.
  The Standard model is less natural-sounding than WaveNet and Neural2, but more cost-effective.
* [WaveNet](https://cloud.google.com/text-to-speech/docs/voice-types#wavenet_voices)
  is powered by deep learning technology and offers more natural and lifelike speech output.
* [Neural2](https://cloud.google.com/text-to-speech/docs/voice-types#neural2_voices)
  is based on the same technology used to create Custom Voices
  and prioritizes natural and human-like pronunciation and intonation.
* [Polyglot](https://cloud.google.com/text-to-speech/docs/polyglot?hl=en#overview)
  voices have variants in multiple languages. For example, at time of writing,
  the `polyglot-1` voice has variants for English (Australia), English (US), French, German, Spanish (Spain), and Spanish (US).

## Voices

Browse Google's table of [supported voices](https://cloud.google.com/text-to-speech/docs/voices) and copy the **Voice name** value to use as the voice ID.

## Billing

Google Cloud TTS usage on SignalWire is billed according to the following SKU codes:

| Billing SKU  | Models            | Description                                |
| ------------ | ----------------- | ------------------------------------------ |
| `gcloud`     | Standard, WaveNet | Traditional and WaveNet model billing      |
| `gcloud_cog` | Neural2, Polyglot | Cognitive services (Neural2) model billing |

The billing SKU is automatically determined by the voice model type. Neural2 and Polyglot voices use the `gcloud_cog` SKU, while Standard and WaveNet voices use the `gcloud` SKU.

Consult the [Voice API Pricing](https://signalwire.com/pricing/voice) page for current rates.

## Usage

Copy the voice name in whole from the **Voice name** column of Google's table of
[supported voices](https://cloud.google.com/text-to-speech/docs/voices) — that is the voice half of
the string, not a complete voice string on its own.
Google Cloud voice IDs encode language and model information,
so no modification is needed to make these selections.
Prepend `gcloud.` and the string is ready for use.
For example: `gcloud.en-GB-Wavenet-A`

Google Cloud voice IDs conform to the following format:

```
gcloud.<voice>
```

Where `<voice>` is the complete voice name from Google's [supported voices table](https://cloud.google.com/text-to-speech/docs/voices).

**Voice name pattern:**

Google Cloud voice names follow: `<language>-<model>-<variant>`

* `language`: Language code (e.g., `en-US`, `es-ES`, `ja-JP`)
* `model`: Model type (e.g., `Standard`, `Wavenet`, `Neural2`, `Polyglot`)
* `variant`: Voice variant letter (e.g., `A`, `B`, `C`)

**Examples:**

```
gcloud.en-US-Neural2-A
gcloud.en-GB-Wavenet-B
gcloud.es-ES-Neural2-A
gcloud.ja-JP-Neural2-B
gcloud.fr-FR-Wavenet-C
gcloud.de-DE-Standard-A
gcloud.en-US-Polyglot-1
```

**Case insensitivity:**

Voice IDs are case-insensitive. These are equivalent:

```
gcloud.en-US-Neural2-A
gcloud.en-us-neural2-a
```

**Note:** Google Cloud voice IDs already encode language and model information.

## Languages

Sample all available voices with
[Google's supported voices and languages reference](https://cloud.google.com/text-to-speech/docs/voices).
Copy the voice identifier string in whole from the **Voice name** column, then prepend `gcloud.` to
get the string SignalWire accepts — the voice name on its own resolves against a default engine that
can change.

Unlike the other supported engines, Google Cloud voice identifier strings include both voice and language keys,
following the pattern `<language>-<model>-<variant>`.
Prefixed with the engine, complete voice strings look like this:

* English (UK) WaveNet female voice: `gcloud.en-GB-Wavenet-A`
* Spanish (Spain) Neural2 male voice: `gcloud.es-ES-Neural2-B`
* Mandarin Chinese Standard female voice: `gcloud.cmn-CN-Standard-D`

---

## Examples

Learn how to use Google Cloud voices on the SignalWire platform.

#### 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: gcloud.en-US-Neural2-A
```

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: "gcloud.en-US-Neural2-A"
  - play: "say:Greetings. This is the 2-A US English voice from Google Cloud's Neural2 text-to-speech model."
```

#### 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 2-A US English voice from Google Cloud's Neural2 text-to-speech model.",
    voice: "gcloud.en-US-Neural2-A",
});
await playback.ended();
```

#### Call Flow Builder

In a **Play Audio or TTS** node, choose **Text to Speech** and select the Google Cloud voice `gcloud.en-US-Neural2-A`.

> Text-to-speech