> 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.

# Speech-to-Speech (EVI)

Hume's Empathic Voice Interface (EVI) is an advanced, real-time emotionally intelligent voice AI. EVI measures users'
nuanced vocal modulations and responds to them using a speech-language model, which guides language and speech
generation.

By processing the tune, rhythm, and timbre of speech, EVI unlocks a variety of new capabilities, like knowing when to
speak and generating more empathic language with the right tone of voice.

These features enable smoother and more satisfying voice-based interactions between humans and AI, opening new
possibilities for personal AI, customer service, accessibility, robotics, immersive gaming, VR experiences, and much
more.

To try EVI in your browser, use the [EVI Playground](https://app.hume.ai/evi/playground) in the Hume platform.

## EVI features

### Version comparison

<table>
  <tbody>
    <tr>
      <th>
         Feature 
      </th>

      <th>
         EVI 3 
      </th>

      <th>
         EVI 4-mini 
      </th>
    </tr>

    <tr>
      <td>
         Languages supported 
      </td>

      <td>
         English 
      </td>

      <td>
         English, Japanese, Korean, Spanish, French, Portuguese, Italian, German, Russian, Hindi, Arabic 
      </td>
    </tr>

    <tr>
      <td>
        Quick responses
      </td>

      <td>
        Available
      </td>

      <td>
        Unavailable
      </td>
    </tr>

    <tr>
      <td>
        Supplemental LLM
      </td>

      <td>
        Optional
      </td>

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

### Basic capabilities

<table>
  <tbody>
    <tr>
      <th width="20%">
        Feature
      </th>

      <th>
        Description
      </th>
    </tr>

    <tr>
      <td>
        **Transcription (ASR)**
      </td>

      <td>
        Fast and accurate ASR returns a full transcript of the conversation, with Hume’s expression measures tied to
        each sentence.
      </td>
    </tr>

    <tr>
      <td>
        **Text response (LLM)**
      </td>

      <td>
        Rapid language generation with our speech-language model, optionally supplemented with configurable partner
        APIs (Anthropic, OpenAI, Google, Fireworks, and more).
      </td>
    </tr>

    <tr>
      <td>
        **Voice response (TTS)**
      </td>

      <td>
        Streamed speech generation via our speech-language model.
      </td>
    </tr>

    <tr>
      <td>
        **Low latency response**
      </td>

      <td>
        Immediate response provided by the fastest models running together on one service.
      </td>
    </tr>
  </tbody>
</table>

### Empathic AI Features

<table>
  <tbody>
    <tr>
      <th width="20%">
        Feature
      </th>

      <th>
        Description
      </th>
    </tr>

    <tr>
      <td>
        **Responds at the right time**
      </td>

      <td>
        Uses your tone of voice for state-of-the-art end-of-turn detection — the true bottleneck to responding rapidly
        without interrupting you.
      </td>
    </tr>

    <tr>
      <td>
        **Understands users’ prosody**
      </td>

      <td>
        Provides streaming measurements of the tune, rhythm, and timbre of the user’s speech using Hume’s
        [prosody](https://www.hume.ai/products/speech-prosody-model) model, integrated with our speech-language model.
      </td>
    </tr>

    <tr>
      <td>
        **Forms its own natural tone of voice**
      </td>

      <td>
        Guided by the users’ prosody and language, our model responds with an empathic, naturalistic tone of voice,
        matching the users’ nuanced “vibe” (calmness, interest, excitement, etc.). It responds to frustration with an
        apologetic tone, to sadness with sympathy, and more.
      </td>
    </tr>

    <tr>
      <td>
        **Responds to expression**
      </td>

      <td>
        Powered by our empathic large language model (speech-language model), EVI crafts responses that are not just
        intelligent but attuned to what the user is expressing with their voice.
      </td>
    </tr>

    <tr>
      <td>
        **Always interruptible**
      </td>

      <td>
        Stops rapidly whenever users interject, listens, and responds with the right context based on where it left
        off.
      </td>
    </tr>

    <tr>
      <td>
        **Multi-lingual**
      </td>

      <td>
        EVI 4-mini supports English, Japanese, Korean, Spanish, French, Portuguese, Italian, German, Russian, Hindi, Arabic.
      </td>
    </tr>
  </tbody>
</table>

## Quickstart

**Kickstart your integration with our quickstart guides** for Next.js, TypeScript, and Python. Each guide walks you through
integrating the EVI API, capturing user audio, and playing back EVI's response so you can get up and running quickly.

Build web applications using our React client SDK in Next.js.

Develop server-side or frontend applications using our TypeScript SDK.

Create integrations in Python using our Python SDK.

## Building with EVI

**EVI chat sessions run over a real-time WebSocket connection**, enabling fluid, interactive dialogue. Users speak
naturally while EVI analyzes their vocal expression and responds with emotionally intelligent speech.

### Authentication

REST endpoints support the [API key authentication](/docs/introduction/api-key#api-key-authentication) strategy.
specify your API key in the `X-HUME-API-KEY` header of your request.

The EVI WebSocket endpoint supports both the API key and [Token
authentication](/docs/introduction/api-key#token-authentication) strategies, specify your [API
key](/reference/speech-to-speech-evi/chat#request.query.api_key) or [Access
token](/reference/speech-to-speech-evi/chat#request.query.access_token) in the query parameters of your
request.

### Configuration

Before starting a session, you’ll need a voice and a configuration.

* [Design](/docs/voice/voice-design) a voice, [clone](/docs/voice/voice-cloning) an existing one, or select one from
  Hume’s extensive [Voice Library](https://app.hume.ai/voices).
* [Build an EVI configuration](/docs/speech-to-speech-evi/configuration/build-a-configuration) to define system
  behavior, voice selection, and other settings.

### Connection

The [EVI Playground](https://app.hume.ai/evi/playground) is the easiest way to test your configuration. It lets
you speak directly with EVI using your selected voice and settings, without writing any code.

To begin a conversation, connect using the [EVI WebSocket URL](/reference/speech-to-speech-evi/chat) start
streaming the user's audio input, via [audio\_input](/reference/speech-to-speech-evi/chat#send.AudioInput)
messages. EVI responds in real time with a sequence of structured messages:

* [user\_message](/reference/speech-to-speech-evi/chat#receive.UserMessage): Message containing a
  transcript of the user's message along with their vocal expression measures
* [assistant\_message](/reference/speech-to-speech-evi/chat#receive.AssistantMessage): Message containing
  EVI's response content.
* [audio\_output](/reference/speech-to-speech-evi/chat#receive.AudioOutput): EVI’s response audio
  corresponding with the `assistant_message`
* [assistant\_end](/reference/speech-to-speech-evi/chat#receive.AssistantEnd): Message denoting the end of
  EVI's response.

## Developer tools

**Hume provides a suite of developer tools to integrate and customize EVI.**

Connect with EVI via WebSocket, including message formats and response types.

Manage EVI configurations and access your chat history.

Use official SDKs to streamline integration in Python and web-based projects.

Browse example projects demonstrating EVI integration in different frameworks.

## API limits

The following limits apply to Hume’s Speech-to-Speech (EVI) API.

<table>
  <tbody>
    <tr>
      <th width="44%">
        Limit
      </th>

      <th>
        Value
      </th>
    </tr>

    <tr>
      <td>
        Concurrent sessions
      </td>

      <td>
        Defined by your 

        [subscription tier](https://www.hume.ai/pricing)
      </td>
    </tr>

    <tr>
      <td>
        Maximum session duration
      </td>

      <td>
        30 minutes
      </td>
    </tr>

    <tr>
      <td>
        Maximum message size (WebSocket)
      </td>

      <td>
        16 MB
      </td>
    </tr>

    <tr>
      <td>
        Request rate limit (HTTP)
      </td>

      <td>
        100 requests/second
      </td>
    </tr>
  </tbody>
</table>

**The EVI API supports thousands of concurrent sessions.** To increase limits:

1. Upgrade your account to **Business** or **Enterprise**.
2. Submit the [Sales & Partnerships form](https://www.hume.ai/sales-and-partnerships-form).

***