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

# Mastra 中的 Voice

Mastra 的 Voice 系统为语音交互提供统一接口，让应用能够使用文本转语音（TTS）、语音转文本（STT）和实时语音转语音（STS）能力。

## 为 Agent 添加语音能力

通过 `voice` 属性将语音 Provider 传给 Agent。根据配置的 Provider，同一属性支持文本转语音（TTS）、语音转文本（STT）和实时语音转语音（STS）。

```typescript
import { Agent } from '@mastra/core/agent'
import { OpenAIVoice } from '@mastra/voice-openai'

// Initialize OpenAI voice for TTS

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new OpenAIVoice(),
})
```

随后可以使用以下语音能力：

### 文本转语音（TTS）

使用 Mastra 的 TTS 能力将 Agent 响应转换为自然流畅的语音。 可以选择 OpenAI、ElevenLabs 等多个 Provider。

有关详细配置选项和高级功能，请参阅[文本转语音指南](https://mastra.zisheng.pro/guides/voice/text-to-speech)。

**OpenAI**:

```typescript
import { Agent } from '@mastra/core/agent'
import { OpenAIVoice } from '@mastra/voice-openai'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new OpenAIVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'default', // Optional: specify a speaker
  responseFormat: 'wav', // Optional: specify a response format
})

playAudio(audioStream)
```

有关 OpenAI 语音 Provider 的更多信息，请参阅 [OpenAI Voice 参考](https://mastra.zisheng.pro/reference/voice/openai)。

**Azure**:

```typescript
import { Agent } from '@mastra/core/agent'
import { AzureVoice } from '@mastra/voice-azure'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new AzureVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'en-US-JennyNeural', // Optional: specify a speaker
})

playAudio(audioStream)
```

有关 Azure 语音 Provider 的更多信息，请参阅 [Azure Voice 参考](https://mastra.zisheng.pro/reference/voice/azure)。

**ElevenLabs**:

```typescript
import { Agent } from '@mastra/core/agent'
import { ElevenLabsVoice } from '@mastra/voice-elevenlabs'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new ElevenLabsVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'default', // Optional: specify a speaker
})

playAudio(audioStream)
```

有关 ElevenLabs 语音 Provider 的更多信息，请参阅 [ElevenLabs Voice 参考](https://mastra.zisheng.pro/reference/voice/elevenlabs)。

**PlayAI**:

```typescript
import { Agent } from '@mastra/core/agent'
import { PlayAIVoice } from '@mastra/voice-playai'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new PlayAIVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'default', // Optional: specify a speaker
})

playAudio(audioStream)
```

有关 PlayAI 语音 Provider 的更多信息，请参阅 [PlayAI Voice 参考](https://mastra.zisheng.pro/reference/voice/playai)。

**Google**:

```typescript
import { Agent } from '@mastra/core/agent'
import { GoogleVoice } from '@mastra/voice-google'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new GoogleVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'en-US-Studio-O', // Optional: specify a speaker
})

playAudio(audioStream)
```

有关 Google 语音 Provider 的更多信息，请参阅 [Google Voice 参考](https://mastra.zisheng.pro/reference/voice/google)。

**Cloudflare**:

```typescript
import { Agent } from '@mastra/core/agent'
import { CloudflareVoice } from '@mastra/voice-cloudflare'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new CloudflareVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'default', // Optional: specify a speaker
})

playAudio(audioStream)
```

有关 Cloudflare 语音 Provider 的更多信息，请参阅 [Cloudflare Voice 参考](https://mastra.zisheng.pro/reference/voice/cloudflare)。

**Deepgram**:

```typescript
import { Agent } from '@mastra/core/agent'
import { DeepgramVoice } from '@mastra/voice-deepgram'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new DeepgramVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'aura-english-us', // Optional: specify a speaker
})

playAudio(audioStream)
```

有关 Deepgram 语音 Provider 的更多信息，请参阅 [Deepgram Voice 参考](https://mastra.zisheng.pro/reference/voice/deepgram)。

**Inworld**:

```typescript
import { Agent } from '@mastra/core/agent'
import { InworldVoice } from '@mastra/voice-inworld'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new InworldVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'Dennis', // Optional: specify a speaker
})

playAudio(audioStream)
```

有关 Inworld 语音 Provider 的更多信息，请参阅 [Inworld Voice 参考](https://mastra.zisheng.pro/reference/voice/inworld)。

**Speechify**:

```typescript
import { Agent } from '@mastra/core/agent'
import { SpeechifyVoice } from '@mastra/voice-speechify'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new SpeechifyVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'matthew', // Optional: specify a speaker
})

playAudio(audioStream)
```

有关 Speechify 语音 Provider 的更多信息，请参阅 [Speechify Voice 参考](https://mastra.zisheng.pro/reference/voice/speechify)。

**Sarvam**:

```typescript
import { Agent } from '@mastra/core/agent'
import { SarvamVoice } from '@mastra/voice-sarvam'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new SarvamVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'shubh', // Optional: specify a bulbul:v3 speaker
})

playAudio(audioStream)
```

有关 Sarvam 语音 Provider 的更多信息，请参阅 [Sarvam Voice 参考](https://mastra.zisheng.pro/reference/voice/sarvam)。

**Murf**:

```typescript
import { Agent } from '@mastra/core/agent'
import { MurfVoice } from '@mastra/voice-murf'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new MurfVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'default', // Optional: specify a speaker
})

playAudio(audioStream)
```

有关 Murf 语音 Provider 的更多信息，请参阅 [Murf Voice 参考](https://mastra.zisheng.pro/reference/voice/murf)。

### 语音转文本（STT）

使用 OpenAI、ElevenLabs 等 Provider 转录语音内容。有关详细配置选项等内容，请参阅[语音转文本](https://mastra.zisheng.pro/guides/voice/speech-to-text)。

你可以从[这里](https://github.com/mastra-ai/realtime-voice-demo/raw/refs/heads/main/how_can_i_help_you.mp3)下载示例音频文件。

[](https://github.com/mastra-ai/realtime-voice-demo/raw/refs/heads/main/how_can_i_help_you.mp3)

**OpenAI**:

```typescript
import { Agent } from '@mastra/core/agent'
import { OpenAIVoice } from '@mastra/voice-openai'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new OpenAIVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

有关 OpenAI 语音 Provider 的更多信息，请参阅 [OpenAI Voice 参考](https://mastra.zisheng.pro/reference/voice/openai)。

**Azure**:

```typescript
import { createReadStream } from 'fs'
import { Agent } from '@mastra/core/agent'
import { AzureVoice } from '@mastra/voice-azure'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new AzureVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

有关 Azure 语音 Provider 的更多信息，请参阅 [Azure Voice 参考](https://mastra.zisheng.pro/reference/voice/azure)。

**ElevenLabs**:

```typescript
import { Agent } from '@mastra/core/agent'
import { ElevenLabsVoice } from '@mastra/voice-elevenlabs'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new ElevenLabsVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

有关 ElevenLabs 语音 Provider 的更多信息，请参阅 [ElevenLabs Voice 参考](https://mastra.zisheng.pro/reference/voice/elevenlabs)。

**Google**:

```typescript
import { Agent } from '@mastra/core/agent'
import { GoogleVoice } from '@mastra/voice-google'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new GoogleVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

有关 Google 语音 Provider 的更多信息，请参阅 [Google Voice 参考](https://mastra.zisheng.pro/reference/voice/google)。

**Cloudflare**:

```typescript
import { Agent } from '@mastra/core/agent'
import { CloudflareVoice } from '@mastra/voice-cloudflare'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new CloudflareVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

有关 Cloudflare 语音 Provider 的更多信息，请参阅 [Cloudflare Voice 参考](https://mastra.zisheng.pro/reference/voice/cloudflare)。

**Deepgram**:

```typescript
import { Agent } from '@mastra/core/agent'
import { DeepgramVoice } from '@mastra/voice-deepgram'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new DeepgramVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

有关 Deepgram 语音 Provider 的更多信息，请参阅 [Deepgram Voice 参考](https://mastra.zisheng.pro/reference/voice/deepgram)。

**Inworld**:

```typescript
import { Agent } from '@mastra/core/agent'
import { InworldVoice } from '@mastra/voice-inworld'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new InworldVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

有关 Inworld 语音 Provider 的更多信息，请参阅 [Inworld Voice 参考](https://mastra.zisheng.pro/reference/voice/inworld)。

**Sarvam**:

```typescript
import { Agent } from '@mastra/core/agent'
import { SarvamVoice } from '@mastra/voice-sarvam'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new SarvamVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

有关 Sarvam 语音 Provider 的更多信息，请参阅 [Sarvam Voice 参考](https://mastra.zisheng.pro/reference/voice/sarvam)。

### 语音转语音（STS）

使用语音转语音能力创建对话体验。统一 API 可实现用户与 AI Agent 之间的实时语音交互。 有关详细配置选项和高级功能，请参阅[语音转语音](https://mastra.zisheng.pro/guides/voice/speech-to-speech)。

**OpenAI**:

```typescript
import { Agent } from '@mastra/core/agent'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new OpenAIRealtimeVoice(),
})

// Listen for agent audio responses
voiceAgent.voice.on('speaker', ({ audio }) => {
  playAudio(audio)
})

// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?')

// Send continuous audio from the microphone
const micStream = getMicrophoneStream()
await voiceAgent.voice.send(micStream)
```

有关 OpenAI 语音 Provider 的更多信息，请参阅 [OpenAI Voice 参考](https://mastra.zisheng.pro/reference/voice/openai-realtime)。

**Google**:

```typescript
import { Agent } from '@mastra/core/agent'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
import { GeminiLiveVoice } from '@mastra/voice-google-gemini-live'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new GeminiLiveVoice({
    // Live API mode
    apiKey: process.env.GOOGLE_API_KEY,
    model: 'gemini-2.0-flash-exp',
    speaker: 'Puck',
    debug: true,
    // Vertex AI alternative:
    // vertexAI: true,
    // project: 'your-gcp-project',
    // location: 'us-central1',
    // serviceAccountKeyFile: '/path/to/service-account.json',
  }),
})

// Connect before using speak/send
await voiceAgent.voice.connect()

// Listen for agent audio responses
voiceAgent.voice.on('speaker', ({ audio }) => {
  playAudio(audio)
})

// Listen for text responses and transcriptions
voiceAgent.voice.on('writing', ({ text, role }) => {
  console.log(`${role}: ${text}`)
})

// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?')

// Send continuous audio from the microphone
const micStream = getMicrophoneStream()
await voiceAgent.voice.send(micStream)
```

有关 Google Gemini Live 语音 Provider 的更多信息，请参阅 [Google Gemini Live 参考](https://mastra.zisheng.pro/reference/voice/google-gemini-live)。

**AWS Nova Sonic**:

```typescript
import { Agent } from '@mastra/core/agent'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
import { NovaSonicVoice } from '@mastra/voice-aws-nova-sonic'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new NovaSonicVoice({
    region: 'us-east-1',
    speaker: 'matthew',
    // Static credentials are optional. The default AWS credential
    // provider chain is used when none are passed.
  }),
})

// Connect before using speak/send
await voiceAgent.voice.connect()

// Listen for assistant audio (Int16Array PCM)
voiceAgent.voice.on('speaking', ({ audioData }) => {
  if (audioData) playAudio(audioData)
})

// Listen for transcribed text
voiceAgent.voice.on('writing', ({ text, role }) => {
  console.log(`${role}: ${text}`)
})

// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?')

// Send continuous audio from the microphone
const micStream = getMicrophoneStream()
await voiceAgent.voice.send(micStream)
```

有关 AWS Nova Sonic 语音 Provider 的更多信息，请参阅 [AWS Nova Sonic 参考](https://mastra.zisheng.pro/reference/voice/aws-nova-sonic)。

**Inworld Realtime**:

```typescript
import { Agent } from '@mastra/core/agent'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
import { InworldRealtimeVoice } from '@mastra/voice-inworld'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new InworldRealtimeVoice({
    apiKey: process.env.INWORLD_API_KEY,
    model: 'inworld/models/gemma-4-26b-a4b-it',
    speaker: 'Sarah',
  }),
})

// Connect before using speak/send
await voiceAgent.voice.connect()

// Listen for agent audio (PCM stream)
voiceAgent.voice.on('speaker', stream => {
  playAudio(stream)
})

// Listen for text responses and transcriptions
voiceAgent.voice.on('writing', ({ text, role }) => {
  console.log(`${role}: ${text}`)
})

// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?')

// Send continuous audio from the microphone
const micStream = getMicrophoneStream()
await voiceAgent.voice.send(micStream)
```

有关 Inworld Realtime 语音 Provider 的更多信息，请参阅 [Inworld Realtime 参考](https://mastra.zisheng.pro/reference/voice/inworld-realtime)。

**xAI**:

```typescript
import { Agent } from '@mastra/core/agent'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
import { XAIRealtimeVoice } from '@mastra/voice-xai-realtime'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'xai/grok-4.3',
  voice: new XAIRealtimeVoice({
    apiKey: process.env.XAI_API_KEY,
    model: 'grok-voice-think-fast-1.0',
    speaker: 'eve',
    turnDetection: { type: 'server_vad' },
  }),
})

// Connect before using speak/send
await voiceAgent.voice.connect()

// Listen for agent audio responses
voiceAgent.voice.on('speaker', audioStream => {
  playAudio(audioStream)
})

// Listen for text responses and transcriptions
voiceAgent.voice.on('writing', ({ text, role }) => {
  console.log(`${role}: ${text}`)
})

// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?')

// Send continuous audio from the microphone
const micStream = getMicrophoneStream()
await voiceAgent.voice.send(micStream)
```

有关 xAI 语音 Provider 的更多信息，请参阅 [xAI Realtime Voice 参考](https://mastra.zisheng.pro/reference/voice/xai-realtime)。

### 实时语音

在浏览器或电话中运行可由用户打断的实时通话。Mastra 将音频循环交给 LiveKit，由它处理语音活动检测、语义轮次检测和插话；Agent 则使用自己的模型、Tool 和 memory 生成每条回复。有关设置和配置选项，请参阅[实时语音](https://mastra.zisheng.pro/guides/voice/realtime-voice)。

## Voice 配置

每个语音 Provider 都可以配置不同的模型和选项。以下是所有受支持 Provider 的详细配置选项：

**OpenAI**:

```typescript
// OpenAI Voice Configuration
const voice = new OpenAIVoice({
  speechModel: {
    name: 'gpt-3.5-turbo', // Example model name
    apiKey: process.env.OPENAI_API_KEY,
    language: 'en-US', // Language code
    voiceType: 'neural', // Type of voice model
  },
  listeningModel: {
    name: 'whisper-1', // Example model name
    apiKey: process.env.OPENAI_API_KEY,
    language: 'en-US', // Language code
    format: 'wav', // Audio format
  },
  speaker: 'alloy', // Example speaker name
})
```

有关 OpenAI 语音 Provider 的更多信息，请参阅 [OpenAI Voice 参考](https://mastra.zisheng.pro/reference/voice/openai)。

**Azure**:

```typescript
// Azure Voice Configuration
const voice = new AzureVoice({
  speechModel: {
    name: 'en-US-JennyNeural', // Example model name
    apiKey: process.env.AZURE_SPEECH_KEY,
    region: process.env.AZURE_SPEECH_REGION,
    language: 'en-US', // Language code
    style: 'cheerful', // Voice style
    pitch: '+0Hz', // Pitch adjustment
    rate: '1.0', // Speech rate
  },
  listeningModel: {
    name: 'en-US', // Example model name
    apiKey: process.env.AZURE_SPEECH_KEY,
    region: process.env.AZURE_SPEECH_REGION,
    format: 'simple', // Output format
  },
})
```

有关 Azure 语音 Provider 的更多信息，请参阅 [Azure Voice 参考](https://mastra.zisheng.pro/reference/voice/azure)。

**ElevenLabs**:

```typescript
// ElevenLabs Voice Configuration
const voice = new ElevenLabsVoice({
  speechModel: {
    voiceId: 'your-voice-id', // Example voice ID
    model: 'eleven_multilingual_v2', // Example model name
    apiKey: process.env.ELEVENLABS_API_KEY,
    language: 'en', // Language code
    emotion: 'neutral', // Emotion setting
  },
  // ElevenLabs may not have a separate listening model
})
```

有关 ElevenLabs 语音 Provider 的更多信息，请参阅 [ElevenLabs Voice 参考](https://mastra.zisheng.pro/reference/voice/elevenlabs)。

**PlayAI**:

```typescript
// PlayAI Voice Configuration
const voice = new PlayAIVoice({
  speechModel: {
    name: 'playai-voice', // Example model name
    speaker: 'emma', // Example speaker name
    apiKey: process.env.PLAYAI_API_KEY,
    language: 'en-US', // Language code
    speed: 1.0, // Speech speed
  },
  // PlayAI may not have a separate listening model
})
```

有关 PlayAI 语音 Provider 的更多信息，请参阅 [PlayAI Voice 参考](https://mastra.zisheng.pro/reference/voice/playai)。

**Google**:

```typescript
// Google Voice Configuration
const voice = new GoogleVoice({
  speechModel: {
    name: 'en-US-Studio-O', // Example model name
    apiKey: process.env.GOOGLE_API_KEY,
    languageCode: 'en-US', // Language code
    gender: 'FEMALE', // Voice gender
    speakingRate: 1.0, // Speaking rate
  },
  listeningModel: {
    name: 'en-US', // Example model name
    sampleRateHertz: 16000, // Sample rate
  },
})
```

有关 Google 语音 Provider 的更多信息，请参阅 [Google Voice 参考](https://mastra.zisheng.pro/reference/voice/google)。

**Cloudflare**:

```typescript
// Cloudflare Voice Configuration
const voice = new CloudflareVoice({
  speechModel: {
    name: 'cloudflare-voice', // Example model name
    accountId: process.env.CLOUDFLARE_ACCOUNT_ID,
    apiToken: process.env.CLOUDFLARE_API_TOKEN,
    language: 'en-US', // Language code
    format: 'mp3', // Audio format
  },
  // Cloudflare may not have a separate listening model
})
```

有关 Cloudflare 语音 Provider 的更多信息，请参阅 [Cloudflare Voice 参考](https://mastra.zisheng.pro/reference/voice/cloudflare)。

**Deepgram**:

```typescript
// Deepgram Voice Configuration
const voice = new DeepgramVoice({
  speechModel: {
    name: 'nova-2', // Example model name
    speaker: 'aura-english-us', // Example speaker name
    apiKey: process.env.DEEPGRAM_API_KEY,
    language: 'en-US', // Language code
    tone: 'formal', // Tone setting
  },
  listeningModel: {
    name: 'nova-2', // Example model name
    format: 'flac', // Audio format
  },
})
```

有关 Deepgram 语音 Provider 的更多信息，请参阅 [Deepgram Voice 参考](https://mastra.zisheng.pro/reference/voice/deepgram)。

**Inworld**:

```typescript
// Inworld Voice Configuration
const voice = new InworldVoice({
  speechModel: {
    name: 'inworld-tts-2',
    apiKey: process.env.INWORLD_API_KEY,
  },
  listeningModel: {
    name: 'groq/whisper-large-v3',
    apiKey: process.env.INWORLD_API_KEY,
  },
  speaker: 'Dennis',
  audioEncoding: 'MP3',
  sampleRateHertz: 48000,
  language: 'en-US',
})

// Per-call options: `deliveryMode` is honored only by `inworld-tts-2`.
const audioStream = await voice.speak('Hello!', {
  deliveryMode: 'BALANCED', // 'STABLE' | 'BALANCED' | 'CREATIVE'
  language: 'en-US', // BCP-47 per-call override
})
```

有关 Inworld 语音 Provider 的更多信息，请参阅 [Inworld Voice 参考](https://mastra.zisheng.pro/reference/voice/inworld)。

**Speechify**:

```typescript
// Speechify Voice Configuration
const voice = new SpeechifyVoice({
  speechModel: {
    name: 'speechify-voice', // Example model name
    speaker: 'matthew', // Example speaker name
    apiKey: process.env.SPEECHIFY_API_KEY,
    language: 'en-US', // Language code
    speed: 1.0, // Speech speed
  },
  // Speechify may not have a separate listening model
})
```

有关 Speechify 语音 Provider 的更多信息，请参阅 [Speechify Voice 参考](https://mastra.zisheng.pro/reference/voice/speechify)。

**Sarvam**:

```typescript
// Sarvam Voice Configuration
const voice = new SarvamVoice({
  speechModel: {
    model: 'bulbul:v3', // TTS model (bulbul:v2 or bulbul:v3)
    apiKey: process.env.SARVAM_API_KEY,
    language: 'en-IN', // BCP-47 language code
  },
  listeningModel: {
    model: 'saarika:v2.5', // STT model (saarika:v2.5 or saaras:v3)
    apiKey: process.env.SARVAM_API_KEY,
  },
  speaker: 'shubh', // Default bulbul:v3 speaker
})
```

有关 Sarvam 语音 Provider 的更多信息，请参阅 [Sarvam Voice 参考](https://mastra.zisheng.pro/reference/voice/sarvam)。

**Murf**:

```typescript
// Murf Voice Configuration
const voice = new MurfVoice({
  speechModel: {
    name: 'murf-voice', // Example model name
    apiKey: process.env.MURF_API_KEY,
    language: 'en-US', // Language code
    emotion: 'happy', // Emotion setting
  },
  // Murf may not have a separate listening model
})
```

有关 Murf 语音 Provider 的更多信息，请参阅 [Murf Voice 参考](https://mastra.zisheng.pro/reference/voice/murf)。

**OpenAI Realtime**:

```typescript
// OpenAI Realtime Voice Configuration
const voice = new OpenAIRealtimeVoice({
  speechModel: {
    name: 'gpt-3.5-turbo', // Example model name
    apiKey: process.env.OPENAI_API_KEY,
    language: 'en-US', // Language code
  },
  listeningModel: {
    name: 'whisper-1', // Example model name
    apiKey: process.env.OPENAI_API_KEY,
    format: 'ogg', // Audio format
  },
  speaker: 'alloy', // Example speaker name
})
```

有关 OpenAI Realtime 语音 Provider 的更多信息，请参阅 [OpenAI Realtime Voice 参考](https://mastra.zisheng.pro/reference/voice/openai-realtime)。

**xAI Realtime**:

```typescript
// xAI Realtime Voice Configuration
const voice = new XAIRealtimeVoice({
  apiKey: process.env.XAI_API_KEY,
  model: 'grok-voice-think-fast-1.0',
  speaker: 'eve',
  instructions: 'You are a concise voice assistant.',
  turnDetection: {
    type: 'server_vad',
    threshold: 0.85,
    silence_duration_ms: 1000,
    prefix_padding_ms: 333,
  },
  audio: {
    input: { format: { type: 'audio/pcm', rate: 24000 } },
    output: { format: { type: 'audio/pcm', rate: 24000 } },
  },
  serverTools: [
    { type: 'web_search' },
    {
      type: 'mcp',
      server_url: 'https://mcp.example.com/mcp',
      server_label: 'business-tools',
    },
  ],
})
```

有关 xAI 实时语音 Provider 的更多信息，请参阅 [xAI Realtime Voice 参考](https://mastra.zisheng.pro/reference/voice/xai-realtime)。

**Google Gemini Live**:

```typescript
// Google Gemini Live Voice Configuration
const voice = new GeminiLiveVoice({
  speechModel: {
    name: 'gemini-2.0-flash-exp', // Example model name
    apiKey: process.env.GOOGLE_API_KEY,
  },
  speaker: 'Puck', // Example speaker name
  // Google Gemini Live is a realtime bidirectional API without separate speech and listening models
})
```

有关 Google Gemini Live 语音 Provider 的更多信息，请参阅 [Google Gemini Live 参考](https://mastra.zisheng.pro/reference/voice/google-gemini-live)。

**AWS Nova Sonic**:

```typescript
// AWS Nova Sonic Voice Configuration
const voice = new NovaSonicVoice({
  region: 'us-east-1',
  speaker: 'matthew',
  sessionConfig: {
    inferenceConfiguration: {
      temperature: 0.7,
      maxTokens: 1024,
    },
    turnDetectionConfiguration: {
      endpointingSensitivity: 'MEDIUM',
    },
  },
  // AWS Nova Sonic is a realtime bidirectional API without separate speech and listening models
})
```

有关 AWS Nova Sonic 语音 Provider 的更多信息，请参阅 [AWS Nova Sonic 参考](https://mastra.zisheng.pro/reference/voice/aws-nova-sonic)。

**Inworld Realtime**:

```typescript
// Inworld Realtime Voice Configuration
const voice = new InworldRealtimeVoice({
  apiKey: process.env.INWORLD_API_KEY,
  model: 'inworld/models/gemma-4-26b-a4b-it',
  speaker: 'Sarah',
  // Typed Inworld realtime knobs (semantic VAD, playback speed, MCP tool routing, ...)
  session: {
    audio: {
      output: { speed: 1.1 },
      input: { turn_detection: { type: 'semantic_vad', eagerness: 'high' } },
    },
  },
})
```

有关 Inworld Realtime 语音 Provider 的更多信息，请参阅 [Inworld Realtime 参考](https://mastra.zisheng.pro/reference/voice/inworld-realtime)。

**AI SDK**:

```typescript
// AI SDK Voice Configuration
import { CompositeVoice } from '@mastra/core/voice'
import { openai } from '@ai-sdk/openai'
import { elevenlabs } from '@ai-sdk/elevenlabs'

// Use AI SDK models directly - no need to install separate packages
const voice = new CompositeVoice({
  input: openai.transcription('whisper-1'), // AI SDK transcription
  output: elevenlabs.speech('eleven_turbo_v2'), // AI SDK speech
})

// Works seamlessly with your agent
const voiceAgent = new Agent({
  id: 'aisdk-voice-agent',
  name: 'AI SDK Voice Agent',
  instructions: 'You are a helpful assistant with voice capabilities.',
  model: 'openai/gpt-5.6-sol',
  voice,
})
```

### 使用多个语音 Provider

此示例演示如何在 Mastra 中创建并使用两个不同的语音 Provider：使用 OpenAI 进行语音转文本（STT），使用 PlayAI 进行文本转语音（TTS）。

首先使用所需配置创建语音 Provider 实例。

```typescript
import { OpenAIVoice } from '@mastra/voice-openai'
import { PlayAIVoice } from '@mastra/voice-playai'
import { CompositeVoice } from '@mastra/core/voice'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'

// Initialize OpenAI voice for STT
const input = new OpenAIVoice({
  listeningModel: {
    name: 'whisper-1',
    apiKey: process.env.OPENAI_API_KEY,
  },
})

// Initialize PlayAI voice for TTS
const output = new PlayAIVoice({
  speechModel: {
    name: 'playai-voice',
    apiKey: process.env.PLAYAI_API_KEY,
  },
})

// Combine the providers using CompositeVoice
const voice = new CompositeVoice({
  input,
  output,
})

// Implement voice interactions using the combined voice provider
const audioStream = getMicrophoneStream() // Assume this function gets audio input
const transcript = await voice.listen(audioStream)

// Log the transcribed text
console.log('Transcribed text:', transcript)

// Convert text to speech
const responseAudio = await voice.speak(`You said: ${transcript}`, {
  speaker: 'default', // Optional: specify a speaker,
  responseFormat: 'wav', // Optional: specify a response format
})

// Play the audio response
playAudio(responseAudio)
```

### 使用 AI SDK 模型 Provider

也可以直接将 AI SDK 模型与 `CompositeVoice` 配合使用：

```typescript
import { CompositeVoice } from '@mastra/core/voice'
import { openai } from '@ai-sdk/openai'
import { elevenlabs } from '@ai-sdk/elevenlabs'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'

// Use AI SDK models directly - no provider setup needed
const voice = new CompositeVoice({
  input: openai.transcription('whisper-1'), // AI SDK transcription
  output: elevenlabs.speech('eleven_turbo_v2'), // AI SDK speech
})

// Works the same way as Mastra providers
const audioStream = getMicrophoneStream()
const transcript = await voice.listen(audioStream)

console.log('Transcribed text:', transcript)

// Convert text to speech
const responseAudio = await voice.speak(`You said: ${transcript}`, {
  speaker: 'Rachel', // ElevenLabs voice
})

playAudio(responseAudio)
```

还可以混合使用 AI SDK 模型和 Mastra Provider：

```typescript
import { CompositeVoice } from '@mastra/core/voice'
import { PlayAIVoice } from '@mastra/voice-playai'
import { groq } from '@ai-sdk/groq'

const voice = new CompositeVoice({
  input: groq.transcription('whisper-large-v3'), // AI SDK for STT
  output: new PlayAIVoice(), // Mastra provider for TTS
})
```

有关 CompositeVoice 的更多信息，请参阅 [CompositeVoice 参考](https://mastra.zisheng.pro/reference/voice/composite-voice)。

## 更多资源

- [CompositeVoice](https://mastra.zisheng.pro/reference/voice/composite-voice)
- [MastraVoice](https://mastra.zisheng.pro/reference/voice/mastra-voice)
- [OpenAI Voice](https://mastra.zisheng.pro/reference/voice/openai)
- [OpenAI Realtime Voice](https://mastra.zisheng.pro/reference/voice/openai-realtime)
- [xAI Realtime Voice](https://mastra.zisheng.pro/reference/voice/xai-realtime)
- [Azure Voice](https://mastra.zisheng.pro/reference/voice/azure)
- [Google Voice](https://mastra.zisheng.pro/reference/voice/google)
- [Google Gemini Live Voice](https://mastra.zisheng.pro/reference/voice/google-gemini-live)
- [AWS Nova Sonic Voice](https://mastra.zisheng.pro/reference/voice/aws-nova-sonic)
- [Deepgram Voice](https://mastra.zisheng.pro/reference/voice/deepgram)
- [Inworld Voice](https://mastra.zisheng.pro/reference/voice/inworld)
- [LiveKit](https://mastra.zisheng.pro/reference/voice/livekit)
- [PlayAI Voice](https://mastra.zisheng.pro/reference/voice/playai)
- [Voice 示例](https://github.com/mastra-ai/voice-examples)