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

# Multilingual support

Customize your conversation experience by selecting specific speech-to-text (STT) and text-to-speech (TTS) settings. Our platform is powered by **Deepgram** for high-accuracy transcription and **ElevenLabs** for life-like vocal synthesis.

### Supported Languages

We support a wide range of global languages. Spoken interactions are processed through a dual-engine pipeline:

1. **Deepgram (STT):** Transcribes your participant's audio into text.
2. **ElevenLabs (TTS):** Converts the agent's response into natural-sounding speech.

Below is a sample list of the primary languages supported across our standard models:

| Language       | STT Code (Deepgram) | TTS Support (ElevenLabs) |
| -------------- | ------------------- | ------------------------ |
| **English**    | `en`                | Yes                      |
| **Spanish**    | `es`                | Yes                      |
| **French**     | `fr`                | Yes                      |
| **German**     | `de`                | Yes                      |
| **Hindi**      | `hi`                | Yes                      |
| **Portuguese** | `pt`                | Yes                      |
| **Chinese**    | `zh`                | Yes                      |
| **Japanese**   | `ja`                | Yes                      |
| **Korean**     | `ko`                | Yes                      |

<CardGroup cols={2}>
  <Card title="Deepgram STT" href="https://developers.deepgram.com/docs/models-languages-overview#nova-3">
    Models and supported languages
  </Card>

  <Card title="Elevenlabs TTS" href="https://elevenlabs.io/docs/overview/capabilities/text-to-speech#supported-languages">
    Models and supported languages
  </Card>
</CardGroup>

### Setting the Conversation Language for your agent

While creating an agent you have the ability to set the STT provider and select the desired language.

<CodeGroup>
  ```bash Create new Agent theme={null}
  curl --request POST \
    --url https://api.trugen.ai/v1/ext/agent \
    --header 'Content-Type: application/json' \
    --header 'x-api-key: YOUR_API_KEY' \
    --data @- <<EOF
  {
    "agent_name": "AI Agent",
    "config": { "timeout": 240 },
    "avatars": [
      {
        "config": {
          "llm": {
            "provider": "openai",
            "model": "gpt-4.1-mini",
          },
          "stt": { "provider": "deepgram", "model": "nova-3", language: "multi" },
          "tts": { "provider": "elevenlabs", "voice_id": "ZUrEGyu8GFMwnHbvLhv2" }
        },
        "persona_name": "Sample AI Agent",
        "persona_prompt": "You're a helpful AI agent."
      }
    ]
  }
  EOF
  ```
</CodeGroup>

***

> \[!TIP]
> When using `multi` mode, the ElevenLabs TTS engine will automatically adjust its output to match the detected language of the participant for a seamless localized experience.