> Discover all available pages from the documentation index: https://mastra.zisheng.pro/zh-TW/llms.txt

# voice.answer()

`answer()` 方法用於即時語音 Provider，以觸發 AI 產生回應。當語音對語音的對話需要在收到使用者輸入後，明確指示 AI 回應時，此方法特別實用。

## 用法範例

```typescript
import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
import { getMicrophoneStream } from '@mastra/node-audio'
import Speaker from '@mastra/node-speaker'

const speaker = new Speaker({
  sampleRate: 24100, // Audio sample rate in Hz - standard for high-quality audio on MacBook Pro
  channels: 1, // Mono audio output (as opposed to stereo which would be 2)
  bitDepth: 16, // Bit depth for audio quality - CD quality standard (16-bit resolution)
})

// Initialize a real-time voice provider
const voice = new OpenAIRealtimeVoice({
  realtimeConfig: {
    model: 'gpt-5.1',
    apiKey: process.env.OPENAI_API_KEY,
  },
  speaker: 'alloy', // Default voice
})
// Connect to the real-time service
await voice.connect()
// Register event listener for responses
voice.on('speaker', stream => {
  // Handle audio response
  stream.pipe(speaker)
})
// Send user audio input
const microphoneStream = getMicrophoneStream()
await voice.send(microphoneStream)
// Trigger the AI to respond
await voice.answer()
```

## 參數

**options** (`Record<string, unknown>`): 回應專用的 Provider 選項

## 回傳值

回傳 `Promise<void>`，並在回應已觸發時 resolve。

## 注意事項

- 此方法僅由支援語音對語音功能的即時語音 Provider 實作
- 若對不支援此功能的語音 Provider 呼叫此方法，系統會記錄警告並立即 resolve
- 回應音訊通常會透過 'speaking' 事件發出，而非直接回傳
- 對於支援此功能的 Provider，你可以使用此方法傳送特定回應，而不讓 AI 產生回應
- 此方法通常會與 `send()` 搭配使用，以建立對話流程