SpringBoot集成免费的EdgeTTS实现文本转语音

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

unified-tts.host=https://unifiedtts.com
unified-tts.api-key=your-api-key-here

@Data
@ConfigurationProperties(prefix = "unified-tts")
public class UnifiedTtsProperties {

    private String host;
    private String apiKey;

}

@Data
@AllArgsConstructor
@NoArgsConstructor
public class UnifiedTtsRequest {
    
    private String model;
    private String voice;
    private String text;
    private Double speed;
    private Double pitch;
    private Double volume;
    private String format;

}

@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;
    }
}

@Service
public class UnifiedTtsService {

    private final RestClient restClient;
    private final UnifiedTtsProperties properties;

    public UnifiedTtsService(RestClient restClient, UnifiedTtsProperties properties) {
        this.restClient = restClient;
        this.properties = properties;
    }

    /**
     * 调用 UnifiedTTS 同步 TTS 接口，返回音频字节数据。
     *
     * <p>请求头：
     * <ul>
     *   <li>Content-Type: application/json</li>
     *   <li>X-API-Key: 来自配置的 API Key</li>
     *   <li>Accept: 接受二进制流或常见 mp3/mpeg 音频类型</li>
     * </ul>
     *
     * @param request 模型、音色、文本、速度/音调/音量、输出格式等参数
     * @return 音频二进制字节（例如 mp3）
     * @throws IllegalStateException 当服务端返回非 2xx 或无内容时抛出
     */
    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());
    }

    /**
     * 调用合成并将音频写入指定文件。
     *
     * <p>若输出路径的父目录不存在，会自动创建；失败时抛出运行时异常。
     *
     * @param request TTS 请求参数
     * @param outputPath 目标文件路径（例如 output.mp3）
     * @return 实际写入的文件路径
     */
    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);
        }
    }
}

@SpringBootTest
class UnifiedTtsServiceTest {

    @Autowired
    private UnifiedTtsService unifiedTtsService;

    @Test
    void testRealSynthesizeAndDownloadToFile() throws Exception {
        UnifiedTtsRequest req = new UnifiedTtsRequest(
            "edge-tts",
            "en-US-JennyNeural",
            "Hello, this is a test of text to speech synthesis.",
            1.0,
            1.0,
            1.0,
            "mp3"
        );

        // 调用真实接口，断言返回结构
        UnifiedTtsResponse resp = unifiedTtsService.synthesize(req);
        assertNotNull(resp);
        assertTrue(resp.isSuccess(), "Response should be success");
        assertNotNull(resp.getData(), "Response data should not be null");
        assertNotNull(resp.getData().getAudioUrl(), "audio_url should be present");

        // 在当前工程目录下生成测试结果目录并写入文件
        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);
        System.out.println("UnifiedTTS test output: " + written.toAbsolutePath());
        assertTrue(Files.exists(written), "Output file should exist");
        assertTrue(Files.size(written) > 0, "Output file size should be > 0");
    }
}