# ai.languages Use ai.languages to configure the spoken language of your AI Agent, as well as the TTS engine, voice, and fillers. | Name | Type | Default | Description | |:-|:|:--|:-| | languagesOptional | object | - | An object that accepts the [languages parameters](#languages-parameters). | Use ai.languages to configure the spoken language of your AI Agent, as well as the TTS engine, voice, and fillers. ## **Parameters for the languages object** {#languages-parameters} | Name | Type | Default | Description | |:|:|:-|:--| | nameRequired | string | English | Name of the language (French, English, etc). | | codeRequired | string | en-US | The language code for the chosen voice, specified by the selected [TTS provider](/docs/guides/voice-api/getting-started-with-voice/voice-languages-and-codes/index.mdx). For example, fr-FR. | | [voice](#use-voice-strings)Required | string | [Standard-tier](guides/voice-api/getting-started-with-voice/voice-languages-and-codes/index.mdx) voice picked by SignalWire | String format:
Select engine from gcloud, polly, elevenlabs, or deepgram. Select voice from [TTS provider reference](/docs/guides/voice-api/getting-started-with-voice/voice-languages-and-codes/index.mdx#tts-providers).
For example, gcloud.fr-FR-Neural2-B. | | function_fillersOptional | string[] | None | An array of strings to be used as fillers in the conversation when the agent is calling a [SWAIG function](./ai_swaig/functions/index.mdx). | | speech_fillersOptional | string[] | None | An array of strings to be used as fillers in the conversation. This helps the AI break silence between responses. | | fillersOptional | string[] | None | An array of strings to be used as fillers in the conversation and when the agent is calling a [SWAIG function](./ai_swaig/functions/index.mdx).**Deprecated**: Use speech_fillers and function_fillers instead. | | engineOptional | string | gcloud | The engine to use for the language. For example, elevenlabs.**Deprecated.** Set the engine with the [voice](#use-voice-strings) parameter. | ### Use voice strings Compose the voice string using the