voice.connect()
connect() 方法用于建立 WebSocket 或 WebRTC 连接,以实现实时语音对语音通信。在使用其他实时功能(如 send() 或 answer())之前,必须调用此方法。
🌐 The connect() method establishes a WebSocket or WebRTC connection for real-time speech-to-speech communication. This method must be called before using other real-time features like send() or answer().
使用示例Direct link to 使用示例
🌐 Usage Example
import { OpenAIRealtimeVoice } from "@mastra/voice-openai-realtime";
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-realtime",
apiKey: process.env.OPENAI_API_KEY,
options: {
sessionConfig: {
turn_detection: {
type: "server_vad",
threshold: 0.6,
silence_duration_ms: 1200,
},
},
},
},
speaker: "alloy", // Default voice
});
// Connect to the real-time service
await voice.connect();
// Now you can use real-time features
voice.on("speaker", (stream) => {
stream.pipe(speaker);
});
// With connection options
await voice.connect({
timeout: 10000, // 10 seconds timeout
reconnect: true,
});
参数Direct link to 参数
🌐 Parameters
options?:
返回值Direct link to 返回值
🌐 Return Value
返回一个 Promise<void>,当连接成功建立时会被解析。
🌐 Returns a Promise<void> that resolves when the connection is successfully established.
特定于提供商的选项Direct link to 特定于提供商的选项
🌐 Provider-Specific Options
每个实时语音提供商可能对 connect() 方法支持不同的选项:
🌐 Each real-time voice provider may support different options for the connect() method:
OpenAI 实时Direct link to OpenAI 实时
🌐 OpenAI Realtime
options.timeout?:
options.reconnect?:
与复合语音一起使用Direct link to 与复合语音一起使用
🌐 Using with CompositeVoice
在使用 CompositeVoice 时,connect() 方法会委托给配置的实时提供程序:
🌐 When using CompositeVoice, the connect() method delegates to the configured real-time provider:
import { CompositeVoice } from "@mastra/core/voice";
import { OpenAIRealtimeVoice } from "@mastra/voice-openai-realtime";
const realtimeVoice = new OpenAIRealtimeVoice();
const voice = new CompositeVoice({
realtime: realtimeVoice,
});
// This will use the OpenAIRealtimeVoice provider
await voice.connect();
注意Direct link to 注意
🌐 Notes
- 该方法仅由支持语音到语音功能的实时语音提供商实现
- 如果调用不支持此功能的语音提供商,它将记录一条警告并立即完成。
- 在使用其他实时方法如
send()或answer()之前,必须先建立连接 - 完成语音实例后,调用
close()来正确清理资源 - 一些提供商可能会在连接丢失时自动重新连接,这取决于它们的实现方式
- 连接错误通常会作为异常抛出,应该被捕获和处理
相关方法Direct link to 相关方法
🌐 Related Methods
- voice.send() - 将音频数据发送到语音提供商
- voice.answer() - 触发语音提供商进行响应
- voice.close() - 断开与实时服务的连接
- voice.on() - 为语音事件注册一个事件监听器