环境信息：

  jdk  java21

  spring-ai-alibaba 版本为1.0.0.2

  spring-ai 版本为 1.0.0

  spring-boot  版本为    3.5.7

  项目接入oss 

1.依赖包
<!-- https://mvnrepository.com/artifact/com.alibaba/dashscope-sdk-java -->
<dependency>
    <groupId>com.alibaba</groupId>
    <artifactId>dashscope-sdk-java</artifactId>
    <version>2.22.0</version>
</dependency>
<dependency>
    <groupId>com.fasterxml.jackson.core</groupId>
    <artifactId>jackson-databind</artifactId>
    <version>2.15.2</version>
</dependency>

2.代码内容

import com.alibaba.dashscope.audio.asr.transcription.Transcription;

import com.alibaba.dashscope.audio.asr.transcription.TranscriptionParam;

import com.alibaba.dashscope.audio.asr.transcription.TranscriptionQueryParam;

import com.alibaba.dashscope.audio.asr.transcription.TranscriptionResult;

import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisParam;

import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesizer;

import com.fasterxml.jackson.databind.JsonNode;

import com.fasterxml.jackson.databind.ObjectMapper;

import com.google.gson.JsonObject;

import com.pennon.agent.service.OssService; import lombok.extern.slf4j.Slf4j;

import org.springframework.beans.factory.annotation.Autowired;

import org.springframework.beans.factory.annotation.Value;

import org.springframework.stereotype.Component;

import java.io.ByteArrayInputStream;

import java.io.InputStream;

import java.net.URI;

import java.net.http.HttpClient;

import java.net.http.HttpRequest;

import java.net.http.HttpResponse;

import java.nio.ByteBuffer;

import java.util.Arrays;

import java.util.HashMap;

import java.util.Map;

@Slf4j

@Component

public class TextAudioConvertUtils {

//文本转语音模型

private static String model = "cosyvoice-v1";

// 音色

private static String voice = "longjielidou";

@Value("${spring.ai.dashscope.api-key}")

private String apiKey;

@Value("${upload.path.urlPrefix}")

private String urlPrefix;

@Autowired private OssService ossService;

//文本转语音

public Map<String, Object> getAudioOssUrl(String text, String sessionId, String batchNumber) {
    // 请求参数
    SpeechSynthesisParam param =
            SpeechSynthesisParam.builder()
                                // 若没有将API Key配置到环境变量中，需将下面这行代码注释放开，并将your-api-key替换为自己的API Key
                                .apiKey(apiKey)
                                .model(model) // 模型
                                .voice(voice) // 音色
                                .build();

    // 同步模式：禁用回调（第二个参数为null）
    SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, null);
    ByteBuffer audio = null;
    try {
        // 阻塞直至音频返回
        audio = synthesizer.call(text);
    } catch (Exception e) {
        throw new RuntimeException(e);
    } finally {
        // 任务结束关闭websocket连接
        synthesizer.getDuplexApi().close(1000, "bye");
    }
    if (audio != null) {
        // 首次发送文本时需建立 WebSocket 连接，因此首包延迟会包含连接建立的耗时
        log.info(
                "[Metric] requestId为："
                        + synthesizer.getLastRequestId()
                        + "首包延迟（毫秒）为："
                        + synthesizer.getFirstPackageDelay());

        //字节流语音转换
        byte[] array = audio.array();
        InputStream inputStream = new ByteArrayInputStream(array);

        String fileName = sessionId + ":" + System.currentTimeMillis() + ":" + batchNumber + ".mp3";

        //上传到oss
        Map<String, Object> resultMap = ossService.uploadFile(inputStream, fileName, urlPrefix);
        return resultMap;
    }
    return new HashMap<>();
}

// 语音翻译为文本

public String getTextByAudioOssUrl(String ossUrl) throws Exception {
    TranscriptionParam param =
            TranscriptionParam.builder()
                              // 若没有将API Key配置到环境变量中，需将apiKey替换为自己的API Key
                              .apiKey(apiKey)
                              .model("paraformer-v2")
                              // “language_hints”只支持paraformer-v2模型
                              .parameter("language_hints", new String[]{"zh", "en"})
                              .fileUrls(Arrays.asList(ossUrl))
                              .build();

    Transcription transcription = new Transcription();
    // 提交转写请求
    TranscriptionResult result = transcription.asyncCall(param);
    log.info("RequestId: " + result.getRequestId());
    // 阻塞等待任务完成并获取结果
    result = transcription.wait(
            TranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId()));
    // 打印结果
    JsonObject output = result.getOutput();
    ObjectMapper mapper = new ObjectMapper();
    JsonNode root = mapper.readTree(String.valueOf(output));

    JsonNode urlJsonString = root.path("results").get(0).path("transcription_url");
    String urlJson = urlJsonString.textValue();

    // 1. 发送 HTTP GET 请求获取 JSON
    HttpRequest request = HttpRequest.newBuilder()
                                     .uri(URI.create(urlJson))
                                     .GET()
                                     .build();

    HttpResponse<String> response = HttpClient.newHttpClient().send(request, HttpResponse.BodyHandlers.ofString());

    if (response.statusCode() != 200) {
        log.info("解析转语音结果请求失败: " + response.statusCode());
    }

    String jsonContent = response.body();

    // 2. 解析 JSON 并提取 text
    JsonNode rootText = mapper.readTree(jsonContent);

    // 获取 transcripts[0].text
    JsonNode transcriptNode = rootText.path("transcripts").get(0);
    if (transcriptNode.isMissingNode()) {
        log.info("未找到 transcripts 数据");
    }

    String fullText = transcriptNode.path("text").asText().trim();
    log.info("转写文本: " + fullText);
    String finalText = fullText.toString().trim();
    return finalText;
}