SpringBoot集成MiniMax和CosyVoice实现文本转语音功能

<dependencies>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>

    <dependency>
        <groupId>org.projectlombok</groupId>
        <artifactId>lombok</artifactId>
    </dependency>
</dependencies>

unified-tts.host=https://unifiedtts.com
unified-tts.api-key=${UNIFIEDTTS_API_KEY}

// src/main/java/com/example/tts/config/UnifiedTtsProperties.java
@Data
@ConfigurationProperties(prefix = "unified-tts")
public class UnifiedTtsProperties {
    private String host;
    private String apiKey;
}

// src/main/java/com/example/tts/dto/UnifiedTtsRequest.java
@Data
@AllArgsConstructor
@NoArgsConstructor
public class UnifiedTtsRequest {
    private String model;   // 例：minimax-tts 或 cosyvoice-tts
    private String voice;   // 例：zh_female_1（按模型支持的音色选择）
    private String text;
    private Double speed;   // 语速（可选）
    private Double pitch;   // 音高（可选）
    private Double volume;  // 音量（可选）
    private String format;  // mp3/wav/ogg
}

// src/main/java/com/example/tts/dto/UnifiedTtsResponse.java
@Data
@AllArgsConstructor
@NoArgsConstructor
public class UnifiedTtsResponse {
    private boolean success;
    private String message;
    private long timestamp;
    private UnifiedTtsResponseData data;

    @Data
    @AllArgsConstructor
    @NoArgsConstructor
    public static class UnifiedTtsResponseData {
        @JsonProperty("request_id")
        private String requestId;

        @JsonProperty("audio_url")
        private String audioUrl;

        @JsonProperty("file_size")
        private long fileSize;
    }
}

// src/main/java/com/example/tts/service/UnifiedTtsService.java
package com.example.tts.service;

import com.example.tts.dto.UnifiedTtsRequest;
import com.example.tts.config.UnifiedTtsProperties;
import org.springframework.http.MediaType;
import org.springframework.http.ResponseEntity;
import org.springframework.stereotype.Service;
import org.springframework.web.client.RestClient;

import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;

@Service
public class UnifiedTtsService {

    private final RestClient restClient;
    private final UnifiedTtsProperties properties;

    public UnifiedTtsService(UnifiedTtsProperties properties) {
        this.properties = properties;
        this.restClient = RestClient.builder()
                .baseUrl(properties.getHost())
                .build();
    }

    public byte[] synthesize(UnifiedTtsRequest request) {
        ResponseEntity<byte[]> response = restClient
                .post()
                .uri("/api/v1/common/tts-sync")
                .contentType(MediaType.APPLICATION_JSON)
                .accept(MediaType.APPLICATION_OCTET_STREAM, MediaType.valueOf("audio/mpeg"), MediaType.valueOf("audio/mp3"))
                .header("X-API-Key", properties.getApiKey())
                .body(request)
                .retrieve()
                .toEntity(byte[].class);

        if (response.getStatusCode().is2xxSuccessful() && response.getBody() != null) {
            return response.getBody();
        }
        throw new IllegalStateException("UnifiedTTS synthesize failed: " + response.getStatusCode());
    }

    public Path synthesizeToFile(UnifiedTtsRequest request, Path outputPath) {
        byte[] data = synthesize(request);
        try {
            if (outputPath.getParent() != null) {
                Files.createDirectories(outputPath.getParent());
            }
            Files.write(outputPath, data);
            return outputPath;
        } catch (IOException e) {
            throw new RuntimeException("Failed to write TTS output to file: " + outputPath, e);
        }
    }
}

// src/test/java/com/example/tts/UnifiedTtsServiceTest.java
@SpringBootTest
class UnifiedTtsServiceTest {

    @Autowired
    private UnifiedTtsService unifiedTtsService;

    @Test
    void testSynthesizeToFileWithMiniMax() throws Exception {
        UnifiedTtsRequest req = new UnifiedTtsRequest(
            "speech-02-turbo",
            "Chinese (Mandarin)_Gentle_Youth",
            "你好，欢迎使用 UnifiedTTS 的 MiniMax 模型配音。",
            1.0,
            0.0,
            1.0,
            "mp3"
        );

        Path projectDir = Paths.get(System.getProperty("user.dir"));
        Path resultDir = projectDir.resolve("test-result");
        Files.createDirectories(resultDir);
        Path out = resultDir.resolve(System.currentTimeMillis() + ".mp3");

        Path written = unifiedTtsService.synthesizeToFile(req, out);
        assertTrue(Files.exists(written), "Output file should exist");
        assertTrue(Files.size(written) > 0, "Output file size should be > 0");
    }
}