***

id: 6278079e-ea18-4634-b150-877071640502
unlisted: false
hide\_title: false
slug: /reference/ai/languages
title: languages
description: >-
Configure the spoken language of your AI Agent, as well as the TTS engine,
voice, and fillers.
max-toc-depth: 3
----------------

[tts-providers]: /docs/platform/voice/tts#providers

[voices-and-languages]: /docs/platform/voice/tts

[swaig-functions]: /docs/swml/reference/ai/swaig/functions

[deepgram-codes]: https://developers.deepgram.com/docs/models-languages-overview#nova-3

Use `ai.languages` to configure the spoken language of your AI Agent, as well as the TTS engine, voice, and fillers.

## **Properties**

<ParamField path="ai.languages" type="object[]" toc={true}>
  An array of objects that accept the following properties.
</ParamField>

<Indent>
  <ParamField path="languages[].name" type="string" required={true} toc={true}>
    Name of the language ("French", "English", etc). This value is used in the system prompt to instruct the LLM what language is being spoken.
  </ParamField>

  <ParamField path="languages[].code" type="string" required={true} toc={true}>
    Set the language code for ASR (Automatic Speech Recognition) (STT (Speech-to-text)) purposes.
    By default, SignalWire uses Deepgram's Nova-3 STT engine, so this value should match a code from Deepgram's [Nova-3 language codes table][deepgram-codes].
    <Info> If a different STT model was selected using the [`openai_asr_engine` parameter](/docs/swml/reference/ai/params#paramsopenai_asr_engine), you must select a code supported by that engine.</Info>
  </ParamField>

  <ParamField path="languages[].voice" type="string" required={true} toc={true}>
    String format: `<engine id>.<voice id>`.
    Select engine from `gcloud`, `polly`, `elevenlabs`, or `deepgram`. Select voice from [TTS provider reference][tts-providers].
    For example, `"gcloud.fr-FR-Neural2-B"`.
    See [`voice` usage](#use-voice-strings) for more details.
  </ParamField>

  <ParamField path="languages[].emotion" type="string" default="None" toc={true}>
    Enables emotion for the set TTS engine. This allows the AI to express emotions when speaking. A global emotion or specific emotions for certain topics can be set within the prompt of the AI.
    *Valid values:* `auto`
    <Warning>Only works with `Cartesia` TTS engine.</Warning>
  </ParamField>

  <ParamField path="languages[].function_fillers" type="string[]" default="None" toc={true}>
    An array of strings to be used as fillers in the conversation when the agent is calling a [`SWAIG function`][swaig-functions]. The filler is played asynchronously during the function call.
  </ParamField>

  <ParamField path="languages[].model" type="string" default="None" toc={true}>
    The model to use for the specified TTS engine (e.g. `arcana`). Check the [TTS provider reference][tts-providers] for the available models.
  </ParamField>

  <ParamField path="languages[].speech_fillers" type="string[]" default="None" toc={true}>
    An array of strings to be used as fillers in the conversation. This helps the AI break silence between responses.

    <Note>
      `speech_fillers`

       are used between every 'turn' taken by the LLM, including at the beginning of the call. For more targed fillers, consider using 

      `function_fillers`

      .
    </Note>
  </ParamField>

  <ParamField path="languages[].speed" type="string" default="None" toc={true}>
    The speed to use for the specified TTS engine. This allows the AI to speak at a different speed at different points in the conversation. The speed behavior can be defined in the prompt of the AI.
    *Valid values:* `auto`
    <Warning>Only works with [`Cartesia`](/docs/platform/voice/tts/cartesia) TTS engine.</Warning>
  </ParamField>

  <ParamField path="languages[].params" type="object" default="None" toc={true}>
    TTS engine-specific parameters for this language.
  </ParamField>

  <Indent>
    <ParamField path="params.similarity" type="number" default="0.75" toc={true}>
      The similarity slider dictates how closely the AI should adhere to the original voice when attempting to replicate it.
      The higher the similarity, the closer the AI will sound to the original voice.
      Valid values range from `0.0` to `1.0`.

      <Info>
        Only works with the ElevenLabs TTS engine.
      </Info>
    </ParamField>

    <ParamField path="params.stability" type="number" default="0.50" toc={true}>
      The stability slider determines how stable the voice is and the randomness between each generation.
      Lowering this slider introduces a broader emotional range for the voice.
      Valid values range from `0.0` to `1.0`.

      <Info>
        Only works with the ElevenLabs TTS engine.
      </Info>
    </ParamField>
  </Indent>

  <ParamField path="languages[].fillers" type="string[]" deprecated={true} default="None" toc={true}>
    An array of strings to be used as fillers in the conversation and when the agent is calling a [`SWAIG function`][swaig-functions]. **Deprecated**: Use `speech_fillers` and `function_fillers` instead.
  </ParamField>

  <ParamField path="languages[].engine" type="string" deprecated={true} default="gcloud" toc={true}>
    The engine to use for the language. For example, `"elevenlabs"`. **Deprecated.** Set the engine with the [`voice`](#use-voice-strings) parameter.
  </ParamField>
</Indent>

## Use `voice` strings

Compose the `voice` string using the `<engine id>.<voice id>` syntax.

First, select your engine using the `gcloud`, `polly`, `elevenlabs`, or `deepgram` identifier.
Append a period (`.`), and then the specific voice ID (for example, `en-US-Casual-K`) from the TTS provider.
Refer to SignalWire's [Supported Voices and Languages][tts-providers]
for guides on configuring voice ID strings for each provider.

## **Supported voices and languages**

SignalWire's cloud platform integrates with leading text-to-speech providers.
For a comprehensive list of supported engines, languages, and voices, refer to our documentation on
[Supported Voices and Languages][voices-and-languages].

## **Examples**

### Set a single language

SWML will automatically assign the language (and other required parameters) to the defaults in the above table if left unset.
This example uses `ai.language` to configure a specific English-speaking voice from ElevenLabs.

<CodeBlocks>
  <CodeBlock title="YAML">
    ```yaml
    languages:
      - name: English
        code: en-US
        voice: elevenlabs.rachel
        speech_fillers:
          - one moment please,
          - hmm...
          - let's see,
    ```
  </CodeBlock>

  <CodeBlock title="JSON">
    ```json
    {
      "languages": [
        {
          "name": "English",
          "code": "en-US",
          "voice": "elevenlabs.rachel",
          "speech_fillers": [
            "one moment please,",
            "hmm...",
            "let's see,"
          ]
        }
      ]
    }
    ```
  </CodeBlock>
</CodeBlocks>

### Set multiple languages

SWML will automatically assign the language (and other required parameters) to the defaults in the above table if left unset.
This example uses `ai.language` to configure multiple languages using different TTS engines.

<CodeBlocks>
  <CodeBlock title="YAML">
    ```yaml
    languages:
      - name: Mandarin
        code: cmn-TW
        voice: gcloud.cmn-TW-Standard-A
      - name: English
        code: en-US
        voice: elevenlabs.rachel
    ```
  </CodeBlock>

  <CodeBlock title="JSON">
    ```json
    {
      "languages": [
        {
          "name": "Mandarin",
          "code": "cmn-TW",
          "voice": "gcloud.cmn-TW-Standard-A"
        },
        {
          "name": "English",
          "code": "en-US",
          "voice": "elevenlabs.rachel"
        }
      ]
    }
    ```
  </CodeBlock>
</CodeBlocks>

### Configure per-language ElevenLabs parameters

Configure different stability and similarity values for each language using `languages[].params`:

<CodeBlocks>
  <CodeBlock title="YAML">
    ```yaml
    ai:
      languages:
        - name: English
          code: en-US
          voice: elevenlabs.josh
          params:
            stability: 0.6
            similarity: 0.8
        - name: Spanish
          code: es-ES
          voice: elevenlabs.maria
          params:
            stability: 0.4
            similarity: 0.9
    ```
  </CodeBlock>

  <CodeBlock title="JSON">
    ```json
    {
      "ai": {
        "languages": [
          {
            "name": "English",
            "code": "en-US",
            "voice": "elevenlabs.josh",
            "params": {
              "stability": 0.6,
              "similarity": 0.8
            }
          },
          {
            "name": "Spanish",
            "code": "es-ES",
            "voice": "elevenlabs.maria",
            "params": {
              "stability": 0.4,
              "similarity": 0.9
            }
          }
        ]
      }
    }
    ```
  </CodeBlock>
</CodeBlocks>