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

# Audio

> Voice input and output for agents

Enable voice interaction with AudioAgent for speech-to-text and text-to-speech.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Audio Flow"
        I[🎤 Voice] --> A[🤖 AudioAgent]
        A --> L[💬 LLM]
        L --> S[🔊 Speech]
    end
    
    classDef input fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef agent fill:#F59E0B,stroke:#7C90A0,color:#fff
    classDef output fill:#10B981,stroke:#7C90A0,color:#fff
    
    class I input
    class A,L agent
    class S output
```

## Quick Start

<Steps>
  <Step title="Create Voice-Enabled Agent">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::{AudioAgent, AudioConfig};

    // Configure audio settings
    let config = AudioConfig::new()
        .speech_to_text(true)
        .text_to_speech(true)
        .voice("alloy");

    // Create AudioAgent (specialized agent with audio capabilities)
    let audio_agent = AudioAgent::new()
        .name("Voice Assistant")
        .instructions("You are a helpful voice assistant")
        .config(config)
        .build()?;

    // Process audio input
    let response = audio_agent.process_audio("path/to/audio.wav").await?;
    ```
  </Step>

  <Step title="Text-to-Speech Output">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::{AudioAgent, AudioConfig};

    let config = AudioConfig::new()
        .text_to_speech(true)
        .voice("nova");  // Choose voice

    let agent = AudioAgent::new()
        .name("Speaker")
        .config(config)
        .build()?;

    // Generate speech from text
    let audio_bytes = agent.speak("Hello, how can I help?").await?;
    ```
  </Step>
</Steps>

***

## AudioConfig

| Option           | Type     | Default | Description         |
| ---------------- | -------- | ------- | ------------------- |
| `speech_to_text` | `bool`   | `false` | Enable voice input  |
| `text_to_speech` | `bool`   | `false` | Enable voice output |
| `voice`          | `String` | `alloy` | Voice selection     |

### Available Voices

| Voice   | Style                  |
| ------- | ---------------------- |
| `alloy` | Professional, balanced |
| `nova`  | Warm, conversational   |
| `echo`  | Clear, articulate      |
| `onyx`  | Deep, authoritative    |

***

## Related

<CardGroup cols={2}>
  <Card title="Agent" icon="robot" href="/docs/rust/agent">
    Basic agent creation
  </Card>

  <Card title="Streaming" icon="stream" href="/docs/rust/streaming">
    Real-time responses
  </Card>
</CardGroup>