# Hume AI (/en/ai/models/tts/humeai)

> For AI agents: see the complete documentation index at [llms.txt](/llms.txt).

Hume AI provides emotion-aware text-to-speech technology that generates natural, expressive voices with emotional intelligence. The platform offers both curated voices from the Voice Library and support for custom voice creation, enabling personalized audio experiences.

<CalloutContainer type="info">
  <CalloutTitle>
    Info
  </CalloutTitle>

  <CalloutDescription>
    This integration is fully supported for use with Conversational AI Engine. While it has completed functional validation, it is newer to the platform, and additional provider-specific edge cases may be identified as usage scales across a broader range of applications and workloads.
  </CalloutDescription>
</CalloutContainer>

### Sample configuration [#sample-configuration]

The following examples show how to configure Hume AI TTS when starting a conversational AI agent.

<Tabs defaultValue="python" groupId="ai-sdk-language">
  <TabsList>
    <TabsTrigger value="python">
      Python SDK
    </TabsTrigger>

    <TabsTrigger value="typescript">
      TypeScript SDK
    </TabsTrigger>

    <TabsTrigger value="go">
      Go SDK
    </TabsTrigger>

    <TabsTrigger value="rest-api">
      REST API
    </TabsTrigger>
  </TabsList>

  <TabsContent value="python">
    ```python
    from agora_agent import Agent
    from agora_agent.agentkit.vendors import HumeAITTS

    # client is your configured Agora client
    agent = (
        Agent(client)
        .with_stt(...)  # configure your STT vendor
        .with_llm(...)  # configure your LLM vendor
        .with_tts(HumeAITTS(
            key='your-hume-key',
            voice_id='your-voice-id',
            provider='HUME_AI',
        ))
    )
    ```
  </TabsContent>

  <TabsContent value="typescript">
    ```typescript
    import { Agent, HumeAITTS } from 'agora-agents';

    // client is your configured Agora client
    const agent = new Agent({ client })
      .withStt(/* configure your STT vendor */)
      .withLlm(/* configure your LLM vendor */)
      .withTts(new HumeAITTS({
        key: 'your-hume-key',
        voiceId: 'your-voice-id',
        provider: 'HUME_AI',
      }));
    ```
  </TabsContent>

  <TabsContent value="go">
    ```go
    import "github.com/AgoraIO/agora-agents-go/v2/agentkit/vendors"

    // client is your configured Agora client
    agent := agentkit.NewAgent(client).WithStt(/* configure your STT vendor */).
      WithLlm(/* configure your LLM vendor */).
      WithTts(
        vendors.NewHumeAITTS(vendors.HumeAITTSOptions{
            Key:      "your-hume-key",
            VoiceID:  "your-voice-id",
            Provider: "HUME_AI",
        }),
    )
    ```
  </TabsContent>

  <TabsContent value="rest-api">
    Use the following `tts` configuration in your request:

    ```json
    "tts": {
        "vendor": "humeai",
        "params": {
            "key": "<API_KEY>",
            "voice_id": "<your_voice_id>",
            "base_url": "https://api.hume.ai",
            "provider": "HUME_AI",
            "speed": 1,
            "trailing_silence": 0.35
        }
    }
    ```
  </TabsContent>
</Tabs>

<CalloutContainer type="warning">
  <CalloutTitle>
    Caution
  </CalloutTitle>

  <CalloutDescription>
    The parameters listed on this page are validated for use with Conversational AI Engine. Required parameters must be provided as documented. Any additional parameters are passed through directly to the underlying vendor without validation. For a full list of supported options, refer to the [Hume AI TTS documentation](https://dev.hume.ai/docs/text-to-speech-tts/overview).
  </CalloutDescription>
</CalloutContainer>

### Key parameters [#key-parameters]

<ParameterList title="params" required="true">
  <Parameter name="key" type="string" required="true">
    The API key used for authentication with Hume AI's services. Get your API key from the Hume AI console.
  </Parameter>

  <Parameter name="voice_id" type="string" required="true">
    The identifier of the voice to use for speech synthesis. Choose from available voices in your Hume AI dashboard.
  </Parameter>

  <Parameter name="base_url" type="string" required="false">
    The base URL for the Hume AI API. For example, `https://api.hume.ai`.
  </Parameter>

  <Parameter name="provider" type="string" defaultValue="CUSTOM_VOICE" possibleValues="HUME_AI, CUSTOM_VOICE" required="true">
    The voice provider type.

    * `"HUME_AI"`: Use a pre-built voice from Hume's curated Voice Library.
    * `"CUSTOM_VOICE"`: Use your own custom-trained voice.
  </Parameter>

  <Parameter name="speed" type="number" defaultValue="1" possibleValues="0.25 to 3.0" required="false">
    Controls the playback speed of the generated speech. Higher values increase speech rate.
  </Parameter>

  <Parameter name="trailing_silence" type="number" defaultValue="0.35" possibleValues="0 to 5" required="false">
    Duration of silence (in seconds) to add at the end of each utterance. Useful for natural conversation pacing.
  </Parameter>
</ParameterList>