> This page is for Voice APIs.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://dev.hume.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://dev.hume.ai/_mcp/server.

# Language Model

**EVI supports specifying a language model for response generation during chat sessions.** The language model you
choose plays an important role in the sort of responses that are generated by EVI.

While EVI supports several native speech-language models which are optimized for emotional intelligence and
conversational use cases, the use of supplemental language models is also supported.

#### [API Reference](/reference/speech-to-speech-evi/configs/create-config#request.body.language_model)

See our API reference for how to specify a language model in your EVI configuration.

## Supported language models

### Hume's speech-language model

Hume offers native speech-language models. These models are multi-modal, capable of processing both language and
audio together. This allows EVI to understand and generate both language and voice in the same latent space, resulting
in more coherent and contextually aware responses.

**Hume speech-language model support by EVI version:**

<table>
  <tbody>
    <tr>
      <th>
        Model
      </th>

      <th width="20%">
        EVI 1
      </th>

      <th width="20%">
        EVI 2
      </th>

      <th width="20%">
        EVI 3
      </th>
    </tr>

    <tr>
      <td>
        `hume-evi-2`
      </td>

      <td />

      <td />

      <td />
    </tr>

    <tr>
      <td>
        `hume-evi-3`
      </td>

      <td />

      <td />

      <td />
    </tr>

    <tr>
      <td>
        `hume-evi-3-websearch`
      </td>

      <td />

      <td />

      <td />
    </tr>
  </tbody>
</table>

### External LLMs

Developers may also choose from leading external language models such as Claude, GPT, Gemini, and many others. For a
complete list of external LLMs Hume natively supports, see our [API Reference](/reference/speech-to-speech-evi/configs/create-config#request.body.language_model.model_resource).

#### Latency

The landscape of large language models (LLMs) and their providers is constantly evolving, affecting which
supplemental LLM is fastest with EVI.

The key factor influencing perceived latency using EVI is the time to first token (TTFT), with lower TTFT being
better. The model and provider combination with the smallest TTFT will be the fastest.

Notably, there's a tradeoff between speed and quality. Larger, slower models are easier to prompt. We recommend
testing various supplemental LLM options when implementing EVI.

> **Tip**
>
> [Artificial Analysis](https://artificialanalysis.ai/faq) offers a useful
> [dashboard](https://artificialanalysis.ai/models#latency) for comparing model and provider latencies.

### Custom language model

For specific application requirements, the API supports integrating custom language
models, offering flexibility to tailor conversational behavior to your domain.

#### [Custom Language Model Guide](/docs/speech-to-speech-evi/guides/custom-language-model)

See our guide for details on how to specify and use your custom language model for response generation.

## Pricing

Using an external language model incurs additional cost. You can view estimated pricing by model on the [Billing page](https://app.hume.ai/billing) when you are logged in to the Hume Platform. The cost of your external language model usage will be added to your monthly bill.

---