文本转语音（TTS） API
Spring AI 通过文本转语音模型和流式文本转语音模型接口。这让你能够编写跨不同TTS提供商的可移植代码。
公共接口
所有TTS提供商都实现了以下共享接口：
文本转语音模型
这文本转语音模型界面提供了将文本转换为语音的方法：
public interface TextToSpeechModel extends Model<TextToSpeechPrompt, TextToSpeechResponse>, StreamingTextToSpeechModel {
/**
* Converts text to speech with default options.
*/
default byte[] call(String text) {
// Default implementation
}
/**
* Converts text to speech with custom options.
*/
TextToSpeechResponse call(TextToSpeechPrompt prompt);
/**
* Returns the default options for this model.
*/
default TextToSpeechOptions getDefaultOptions() {
// Default implementation
}
}流式文本转语音模型
这流式文本转语音模型接口提供了实时流媒体音频的方法：
@FunctionalInterface
public interface StreamingTextToSpeechModel extends StreamingModel<TextToSpeechPrompt, TextToSpeechResponse> {
/**
* Streams text-to-speech responses with metadata.
*/
Flux<TextToSpeechResponse> stream(TextToSpeechPrompt prompt);
/**
* Streams audio bytes for the given text.
*/
default Flux<byte[]> stream(String text) {
// Default implementation
}
}编写提供者-无关代码
共享TTS接口的一个关键优势是能够编写可与任何TTS提供商无修改的代码。实际的提供商（OpenAI、ElevenLabs 等）由你的 Spring Boot 配置决定，允许你在不更改应用代码的情况下切换提供商。
基本服务示例
共享接口允许你编写适用于任何TTS提供商的代码：
@Service
public class NarrationService {
private final TextToSpeechModel textToSpeechModel;
public NarrationService(TextToSpeechModel textToSpeechModel) {
this.textToSpeechModel = textToSpeechModel;
}
public byte[] narrate(String text) {
// Works with any TTS provider
return textToSpeechModel.call(text);
}
public byte[] narrateWithOptions(String text, TextToSpeechOptions options) {
TextToSpeechPrompt prompt = new TextToSpeechPrompt(text, options);
TextToSpeechResponse response = textToSpeechModel.call(prompt);
return response.getResult().getOutput();
}
}该服务可无缝兼容 OpenAI、ElevenLabs 或其他 TTS 提供商，实际实现由您的 Spring Boot 配置决定。
高级示例：多提供者支持
你可以同时构建支持多个TTS提供商的应用程序：
@Service
public class MultiProviderNarrationService {
private final Map<String, TextToSpeechModel> providers;
public MultiProviderNarrationService(List<TextToSpeechModel> models) {
// Spring will inject all available TextToSpeechModel beans
this.providers = models.stream()
.collect(Collectors.toMap(
model -> model.getClass().getSimpleName(),
model -> model
));
}
public byte[] narrateWithProvider(String text, String providerName) {
TextToSpeechModel model = providers.get(providerName);
if (model == null) {
throw new IllegalArgumentException("Unknown provider: " + providerName);
}
return model.call(text);
}
public Set<String> getAvailableProviders() {
return providers.keySet();
}
}流媒体音频示例
共享接口还支持实时音频生成的流媒体：
@Service
public class StreamingNarrationService {
private final TextToSpeechModel textToSpeechModel;
public StreamingNarrationService(TextToSpeechModel textToSpeechModel) {
this.textToSpeechModel = textToSpeechModel;
}
public Flux<byte[]> streamNarration(String text) {
// TextToSpeechModel extends StreamingTextToSpeechModel
return textToSpeechModel.stream(text);
}
public Flux<TextToSpeechResponse> streamWithMetadata(String text, TextToSpeechOptions options) {
TextToSpeechPrompt prompt = new TextToSpeechPrompt(text, options);
return textToSpeechModel.stream(prompt);
}
}REST 控制器示例
构建一个与提供者无关的 TTS 的 REST API：
@RestController
@RequestMapping("/api/tts")
public class TextToSpeechController {
private final TextToSpeechModel textToSpeechModel;
public TextToSpeechController(TextToSpeechModel textToSpeechModel) {
this.textToSpeechModel = textToSpeechModel;
}
@PostMapping(value = "/synthesize", produces = "audio/mpeg")
public ResponseEntity<byte[]> synthesize(@RequestBody SynthesisRequest request) {
byte[] audio = textToSpeechModel.call(request.text());
return ResponseEntity.ok()
.contentType(MediaType.parseMediaType("audio/mpeg"))
.header("Content-Disposition", "attachment; filename=\"speech.mp3\"")
.body(audio);
}
@GetMapping(value = "/stream", produces = MediaType.APPLICATION_OCTET_STREAM_VALUE)
public Flux<byte[]> streamSynthesis(@RequestParam String text) {
return textToSpeechModel.stream(text);
}
record SynthesisRequest(String text) {}
}基于配置的提供者选择
使用Spring配置文件或属性在提供商间切换：
# application-openai.yml
spring:
ai:
model:
audio:
speech: openai
openai:
api-key: ${OPENAI_API_KEY}
audio:
speech:
options:
model: gpt-4o-mini-tts
voice: alloy
# application-elevenlabs.yml
spring:
ai:
model:
audio:
speech: elevenlabs
elevenlabs:
api-key: ${ELEVENLABS_API_KEY}
tts:
options:
model-id: eleven_turbo_v2_5
voice-id: your_voice_id然后激活所需的提供者：
# Use OpenAI
java -jar app.jar --spring.profiles.active=openai
# Use ElevenLabs
java -jar app.jar --spring.profiles.active=elevenlabs使用便携式选项
为了最大化便携性，只使用公共音文本语音选项接口方法：
@Service
public class PortableNarrationService {
private final TextToSpeechModel textToSpeechModel;
public PortableNarrationService(TextToSpeechModel textToSpeechModel) {
this.textToSpeechModel = textToSpeechModel;
}
public byte[] createPortableNarration(String text) {
// Use provider's default options for maximum portability
TextToSpeechOptions defaultOptions = textToSpeechModel.getDefaultOptions();
TextToSpeechPrompt prompt = new TextToSpeechPrompt(text, defaultOptions);
TextToSpeechResponse response = textToSpeechModel.call(prompt);
return response.getResult().getOutput();
}
}使用服务提供者特定功能
当你需要提供者专属功能时，你仍然可以在维护可移植代码库的同时使用它们：
@Service
public class FlexibleNarrationService {
private final TextToSpeechModel textToSpeechModel;
public FlexibleNarrationService(TextToSpeechModel textToSpeechModel) {
this.textToSpeechModel = textToSpeechModel;
}
public byte[] narrate(String text, TextToSpeechOptions baseOptions) {
TextToSpeechOptions options = baseOptions;
// Apply provider-specific optimizations if available
if (textToSpeechModel instanceof OpenAiAudioSpeechModel) {
options = OpenAiAudioSpeechOptions.builder()
.from(baseOptions)
.model("gpt-4o-tts") // OpenAI-specific: use high-quality model
.speed(1.0)
.build();
} else if (textToSpeechModel instanceof ElevenLabsTextToSpeechModel) {
// ElevenLabs-specific options could go here
}
TextToSpeechPrompt prompt = new TextToSpeechPrompt(text, options);
TextToSpeechResponse response = textToSpeechModel.call(prompt);
return response.getResult().getOutput();
}
}服务提供者专属功能
虽然共享接口提供了可移植性，但每个提供者还通过提供者特定的选项类别提供特定功能（例如，OpenAiAudioSpeechOptions,十一实验室语音选项).这些类实现了文本语音选项在增加服务提供者专属功能时，还能提供接口。