选项
首页首页 Skill API开发 azure-communication-callautomation-java

azure-communication-callautomation-java

microsoft/skills microsoft/skills

使用 Azure Communication Services Call Automation Java SDK 构建服务器端调用自动化工作流,包括交互式语音应答(IVR)系统、呼叫路由、录音、双音多频(DTMF)识别、文本转语音以及基于人工智能的呼叫流程。

...展开全部
2
更新时间 2026-09-19

Azure 通信呼叫自动化 (Java)

构建服务器端呼叫自动化工作流,包括交互式语音响应 (IVR) 系统、呼叫路由、录音和基于 AI 的交互。

安装

<dependency><groupid>com.azure</groupid><artifactid>azure-communication-callautomation</artifactid><version>1.6.0</version></dependency>

客户端创建

import com.azure.communication.callautomation.CallAutomationClient;
import com.azure.communication.callautomation.CallAutomationClientBuilder;
import com.azure.core.credential.TokenCredential;
import com.azure.identity.AzureIdentityEnvVars;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.azure.identity.ManagedIdentityCredentialBuilder;

// 本地开发:使用 DefaultAzureCredential。生产环境:设置 AZURE_TOKEN_CREDENTIALS=prod 或 AZURE_TOKEN_CREDENTIALS=<特定凭据>
TokenCredential credential = new DefaultAzureCredentialBuilder()
    .requireEnvVars(AzureIdentityEnvVars.AZURE_TOKEN_CREDENTIALS)
    .build();
// 或者在生产环境中直接使用特定凭据:
// 请参阅 https://learn.microsoft.com/java/api/overview/azure/identity-readme?view=azure-java-stable#credential-classes
// TokenCredential credential = new ManagedIdentityCredentialBuilder().build();

// 使用 DefaultAzureCredential
CallAutomationClient client = new CallAutomationClientBuilder()
    .endpoint("https://<资源>.communication.azure.com")
    .credential(credential)
    .buildClient();

// 使用连接字符串
CallAutomationClient client = new CallAutomationClientBuilder()
    .connectionString("<连接字符串>")
    .buildClient();
</连接字符串></资源></特定凭据>

关键概念

用途
`CallAutomationClient`发起呼叫、接听/拒绝传入呼叫、重定向呼叫
`CallConnection`已建立呼叫中的操作(添加参与者、终止呼叫)
`CallMedia`媒体操作(播放音频、识别 DTMF/语音)
`CallRecording`开始/停止/暂停录音
`CallAutomationEventParser`解析来自 ACS 的 Webhook 事件

创建外呼

import com.azure.communication.callautomation.models.*;
import com.azure.communication.common.CommunicationUserIdentifier;
import com.azure.communication.common.PhoneNumberIdentifier;

// 呼叫 PSTN 号码
PhoneNumberIdentifier target = new PhoneNumberIdentifier("+14255551234");
PhoneNumberIdentifier caller = new PhoneNumberIdentifier("+14255550100");

CreateCallOptions options = new CreateCallOptions(
    new CommunicationUserIdentifier("<用户 ID>"),  // 源
    List.of(target))                                // 目标
    .setSourceCallerId(caller)
    .setCallbackUrl("https://your-app.com/api/callbacks");

CreateCallResult result = client.createCall(options);
String callConnectionId = result.getCallConnectionProperties().getCallConnectionId();
</用户 ID>

接听传入呼叫

// 来自 Event Grid Webhook - 传入呼叫事件
String incomingCallContext = "<来自事件的传入呼叫上下文>";

AnswerCallOptions options = new AnswerCallOptions(
    incomingCallContext,
    "https://your-app.com/api/callbacks");

AnswerCallResult result = client.answerCall(options);
CallConnection callConnection = result.getCallConnection();
</来自事件的传入呼叫上下文>

播放音频 (文本转语音)

CallConnection callConnection = client.getCallConnection(callConnectionId);
CallMedia callMedia = callConnection.getCallMedia();

// 播放文本转语音
TextSource textSource = new TextSource()
    .setText("欢迎致电 Contoso。按 1 进入销售部,按 2 进入技术支持部。")
    .setVoiceName("en-US-JennyNeural");

PlayOptions playOptions = new PlayOptions(
    List.of(textSource),
    List.of(new CommunicationUserIdentifier("<目标用户>")));

callMedia.play(playOptions);

// 播放音频文件
FileSource fileSource = new FileSource()
    .setUrl("https://storage.blob.core.windows.net/audio/greeting.wav");

callMedia.play(new PlayOptions(List.of(fileSource), List.of(target)));
</目标用户>

识别 DTMF 输入

// 识别 DTMF 音调
DtmfTone stopTones = DtmfTone.POUND;

CallMediaRecognizeDtmfOptions recognizeOptions = new CallMediaRecognizeDtmfOptions(
    new CommunicationUserIdentifier("<目标用户>"),
    5)  // 收集的最大音调数
    .setInterToneTimeout(Duration.ofSeconds(5))
    .setStopTones(List.of(stopTones))
    .setInitialSilenceTimeout(Duration.ofSeconds(15))
    .setPlayPrompt(new TextSource().setText("请输入您的账户号码,然后按井号键。"));

callMedia.startRecognizing(recognizeOptions);
</目标用户>

识别语音

// 带有 AI 的语音识别
CallMediaRecognizeSpeechOptions speechOptions = new CallMediaRecognizeSpeechOptions(
    new CommunicationUserIdentifier("<目标用户>"))
    .setEndSilenceTimeout(Duration.ofSeconds(2))
    .setSpeechLanguage("en-US")
    .setPlayPrompt(new TextSource().setText("今天我能为您做什么?"));

callMedia.startRecognizing(speechOptions);
</目标用户>

呼叫录音

CallRecording callRecording = client.getCallRecording();

// 开始录音
StartRecordingOptions recordingOptions = new StartRecordingOptions(
    new ServerCallLocator("<服务器呼叫 ID>"))
    .setRecordingChannel(RecordingChannel.MIXED)
    .setRecordingContent(RecordingContent.AUDIO_VIDEO)
    .setRecordingFormat(RecordingFormat.MP4);

RecordingStateResult recordingResult = callRecording.start(recordingOptions);
String recordingId = recordingResult.getRecordingId();

// 暂停/恢复/停止
callRecording.pause(recordingId);
callRecording.resume(recordingId);
callRecording.stop(recordingId);

// 下载录音(在 RecordingFileStatusUpdated 事件之后)
callRecording.downloadTo(recordingUrl, Paths.get("recording.mp4"));
</服务器呼叫 ID>

向呼叫添加参与者

CallConnection callConnection = client.getCallConnection(callConnectionId);

CommunicationUserIdentifier participant = new CommunicationUserIdentifier("<用户 ID>");
AddParticipantOptions addOptions = new AddParticipantOptions(participant)
    .setInvitationTimeout(Duration.ofSeconds(30));

AddParticipantResult result = callConnection.addParticipant(addOptions);
</用户 ID>

转接呼叫

// 盲转接
PhoneNumberIdentifier transferTarget = new PhoneNumberIdentifier("+14255559999");
TransferCallToParticipantResult result = callConnection.transferCallToParticipant(transferTarget);

处理事件 (Webhook)

import com.azure.communication.callautomation.CallAutomationEventParser;
import com.azure.communication.callautomation.models.events.*;

// 在您的 Webhook 端点中
public void handleCallback(String requestBody) {
    List<callautomationeventbase> events = CallAutomationEventParser.parseEvents(requestBody);

    for (CallAutomationEventBase event : events) {
        if (event instanceof CallConnected) {
            CallConnected connected = (CallConnected) event;
            System.out.println("呼叫已连接: " + connected.getCallConnectionId());
        } else if (event instanceof RecognizeCompleted) {
            RecognizeCompleted recognized = (RecognizeCompleted) event;
            // 处理 DTMF 或语音识别结果
            DtmfResult dtmfResult = (DtmfResult) recognized.getRecognizeResult();
            String tones = dtmfResult.getTones().stream()
                .map(DtmfTone::toString)
                .collect(Collectors.joining());
            System.out.println("收到 DTMF: " + tones);
        } else if (event instanceof PlayCompleted) {
            System.out.println("音频播放完成");
        } else if (event instanceof CallDisconnected) {
            System.out.println("呼叫结束");
        }
    }
}
</callautomationeventbase>

挂断呼叫

// 挂断所有参与者的呼叫
callConnection.hangUp(true);

// 仅挂断此分支
callConnection.hangUp(false);

错误处理

import com.azure.core.exception.HttpResponseException;

try {
    client.answerCall(options);
} catch (HttpResponseException e) {
    if (e.getResponse().getStatusCode() == 404) {
        System.out.println("未找到呼叫或呼叫已结束");
    } else if (e.getResponse().getStatusCode() == 400) {
        System.out.println("无效请求: " + e.getMessage());
    }
}

环境变量

AZURE_COMMUNICATION_ENDPOINT=https://<资源>.communication.azure.com  # 所有身份验证方法必需
AZURE_COMMUNICATION_CONNECTION_STRING=endpoint=https://...;accesskey=...  # Entra ID 身份验证的替代方案
CALLBACK_BASE_URL=https://your-app.com/api/callbacks  # Webhook 回调必需
AZURE_TOKEN_CREDENTIALS=prod  # 仅在生产环境中使用 DefaultAzureCredential 时必需
</资源>

触发短语

  • "call automation Java", "IVR Java", "interactive voice response"
  • "call recording Java", "DTMF recognition Java"
  • "text to speech call", "speech recognition call"
  • "answer incoming call", "transfer call Java"
  • "Azure Communication Services call automation"
在 GitHub 上查看
---
name: azure-communication-callautomation-java
description: Build server-side call automation workflows with Azure Communication Services Call Automation Java SDK, including IVR systems, call routing, recording, DTMF recognition, text-to-speech, and AI-powered call flows.
license: MIT
---

# Azure Communication Call Automation (Java)

Build server-side call automation workflows including IVR systems, call routing, recording, and AI-powered interactions.

## Installation

```xml
<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-communication-callautomation</artifactId>
    <version>1.6.0</version>
</dependency>
```

## Client Creation

```java
import com.azure.communication.callautomation.CallAutomationClient;
import com.azure.communication.callautomation.CallAutomationClientBuilder;
import com.azure.core.credential.TokenCredential;
import com.azure.identity.AzureIdentityEnvVars;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.azure.identity.ManagedIdentityCredentialBuilder;

// Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
TokenCredential credential = new DefaultAzureCredentialBuilder()
    .requireEnvVars(AzureIdentityEnvVars.AZURE_TOKEN_CREDENTIALS)
    .build();
// Or use a specific credential directly in production:
// See https://learn.microsoft.com/java/api/overview/azure/identity-readme?view=azure-java-stable#credential-classes
// TokenCredential credential = new ManagedIdentityCredentialBuilder().build();

// With DefaultAzureCredential
CallAutomationClient client = new CallAutomationClientBuilder()
    .endpoint("https://<resource>.communication.azure.com")
    .credential(credential)
    .buildClient();

// With connection string
CallAutomationClient client = new CallAutomationClientBuilder()
    .connectionString("<connection-string>")
    .buildClient();
```

## Key Concepts

| Class | Purpose |
|-------|---------|
| `CallAutomationClient` | Make calls, answer/reject incoming calls, redirect calls |
| `CallConnection` | Actions in established calls (add participants, terminate) |
| `CallMedia` | Media operations (play audio, recognize DTMF/speech) |
| `CallRecording` | Start/stop/pause recording |
| `CallAutomationEventParser` | Parse webhook events from ACS |

## Create Outbound Call

```java
import com.azure.communication.callautomation.models.*;
import com.azure.communication.common.CommunicationUserIdentifier;
import com.azure.communication.common.PhoneNumberIdentifier;

// Call to PSTN number
PhoneNumberIdentifier target = new PhoneNumberIdentifier("+14255551234");
PhoneNumberIdentifier caller = new PhoneNumberIdentifier("+14255550100");

CreateCallOptions options = new CreateCallOptions(
    new CommunicationUserIdentifier("<user-id>"),  // Source
    List.of(target))                                // Targets
    .setSourceCallerId(caller)
    .setCallbackUrl("https://your-app.com/api/callbacks");

CreateCallResult result = client.createCall(options);
String callConnectionId = result.getCallConnectionProperties().getCallConnectionId();
```

## Answer Incoming Call

```java
// From Event Grid webhook - IncomingCall event
String incomingCallContext = "<incoming-call-context-from-event>";

AnswerCallOptions options = new AnswerCallOptions(
    incomingCallContext,
    "https://your-app.com/api/callbacks");

AnswerCallResult result = client.answerCall(options);
CallConnection callConnection = result.getCallConnection();
```

## Play Audio (Text-to-Speech)

```java
CallConnection callConnection = client.getCallConnection(callConnectionId);
CallMedia callMedia = callConnection.getCallMedia();

// Play text-to-speech
TextSource textSource = new TextSource()
    .setText("Welcome to Contoso. Press 1 for sales, 2 for support.")
    .setVoiceName("en-US-JennyNeural");

PlayOptions playOptions = new PlayOptions(
    List.of(textSource),
    List.of(new CommunicationUserIdentifier("<target-user>")));

callMedia.play(playOptions);

// Play audio file
FileSource fileSource = new FileSource()
    .setUrl("https://storage.blob.core.windows.net/audio/greeting.wav");

callMedia.play(new PlayOptions(List.of(fileSource), List.of(target)));
```

## Recognize DTMF Input

```java
// Recognize DTMF tones
DtmfTone stopTones = DtmfTone.POUND;

CallMediaRecognizeDtmfOptions recognizeOptions = new CallMediaRecognizeDtmfOptions(
    new CommunicationUserIdentifier("<target-user>"),
    5)  // Max tones to collect
    .setInterToneTimeout(Duration.ofSeconds(5))
    .setStopTones(List.of(stopTones))
    .setInitialSilenceTimeout(Duration.ofSeconds(15))
    .setPlayPrompt(new TextSource().setText("Enter your account number followed by pound."));

callMedia.startRecognizing(recognizeOptions);
```

## Recognize Speech

```java
// Speech recognition with AI
CallMediaRecognizeSpeechOptions speechOptions = new CallMediaRecognizeSpeechOptions(
    new CommunicationUserIdentifier("<target-user>"))
    .setEndSilenceTimeout(Duration.ofSeconds(2))
    .setSpeechLanguage("en-US")
    .setPlayPrompt(new TextSource().setText("How can I help you today?"));

callMedia.startRecognizing(speechOptions);
```

## Call Recording

```java
CallRecording callRecording = client.getCallRecording();

// Start recording
StartRecordingOptions recordingOptions = new StartRecordingOptions(
    new ServerCallLocator("<server-call-id>"))
    .setRecordingChannel(RecordingChannel.MIXED)
    .setRecordingContent(RecordingContent.AUDIO_VIDEO)
    .setRecordingFormat(RecordingFormat.MP4);

RecordingStateResult recordingResult = callRecording.start(recordingOptions);
String recordingId = recordingResult.getRecordingId();

// Pause/resume/stop
callRecording.pause(recordingId);
callRecording.resume(recordingId);
callRecording.stop(recordingId);

// Download recording (after RecordingFileStatusUpdated event)
callRecording.downloadTo(recordingUrl, Paths.get("recording.mp4"));
```

## Add Participant to Call

```java
CallConnection callConnection = client.getCallConnection(callConnectionId);

CommunicationUserIdentifier participant = new CommunicationUserIdentifier("<user-id>");
AddParticipantOptions addOptions = new AddParticipantOptions(participant)
    .setInvitationTimeout(Duration.ofSeconds(30));

AddParticipantResult result = callConnection.addParticipant(addOptions);
```

## Transfer Call

```java
// Blind transfer
PhoneNumberIdentifier transferTarget = new PhoneNumberIdentifier("+14255559999");
TransferCallToParticipantResult result = callConnection.transferCallToParticipant(transferTarget);
```

## Handle Events (Webhook)

```java
import com.azure.communication.callautomation.CallAutomationEventParser;
import com.azure.communication.callautomation.models.events.*;

// In your webhook endpoint
public void handleCallback(String requestBody) {
    List<CallAutomationEventBase> events = CallAutomationEventParser.parseEvents(requestBody);
    
    for (CallAutomationEventBase event : events) {
        if (event instanceof CallConnected) {
            CallConnected connected = (CallConnected) event;
            System.out.println("Call connected: " + connected.getCallConnectionId());
        } else if (event instanceof RecognizeCompleted) {
            RecognizeCompleted recognized = (RecognizeCompleted) event;
            // Handle DTMF or speech recognition result
            DtmfResult dtmfResult = (DtmfResult) recognized.getRecognizeResult();
            String tones = dtmfResult.getTones().stream()
                .map(DtmfTone::toString)
                .collect(Collectors.joining());
            System.out.println("DTMF received: " + tones);
        } else if (event instanceof PlayCompleted) {
            System.out.println("Audio playback completed");
        } else if (event instanceof CallDisconnected) {
            System.out.println("Call ended");
        }
    }
}
```

## Hang Up Call

```java
// Hang up for all participants
callConnection.hangUp(true);

// Hang up only this leg
callConnection.hangUp(false);
```

## Error Handling

```java
import com.azure.core.exception.HttpResponseException;

try {
    client.answerCall(options);
} catch (HttpResponseException e) {
    if (e.getResponse().getStatusCode() == 404) {
        System.out.println("Call not found or already ended");
    } else if (e.getResponse().getStatusCode() == 400) {
        System.out.println("Invalid request: " + e.getMessage());
    }
}
```

## Environment Variables

```bash
AZURE_COMMUNICATION_ENDPOINT=https://<resource>.communication.azure.com  # Required for all auth methods
AZURE_COMMUNICATION_CONNECTION_STRING=endpoint=https://...;accesskey=...  # Alternative to Entra ID auth
CALLBACK_BASE_URL=https://your-app.com/api/callbacks  # Required for webhook callbacks
AZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production
```

## Trigger Phrases

- "call automation Java", "IVR Java", "interactive voice response"
- "call recording Java", "DTMF recognition Java"
- "text to speech call", "speech recognition call"
- "answer incoming call", "transfer call Java"
- "Azure Communication Services call automation"

所有文件

0 个文件

安装 azure-communication-callautomation-java

将技能文件下载并解压至你的 .claude/skills/ 目录。

下载ZIP

克隆仓库并复制技能文件到您的项目中。

git clone https://github.com/microsoft/skills/tree/main/.github/plugins/azure-sdk-java/skills/azure-communication-callautomation-java # Copy SKILL.md to your .claude/skills/ directory

复制 复制
快速设置: 将技能文件夹复制到 .claude/skills/ 目录。Claude 将自动检测并使用该技能。

相关技能

brightdata-cli
更新时间 2026-06-29
agentwallet
更新时间 2026-07-07
humanize
更新时间 2026-07-07
korean-stock-search
更新时间 2026-07-08
OR