200 lines
6.4 KiB
Java
200 lines
6.4 KiB
Java
package com.vetti.common.ai;
|
|
|
|
import org.apache.http.HttpEntity;
|
|
import org.apache.http.client.methods.CloseableHttpResponse;
|
|
import org.apache.http.client.methods.HttpGet;
|
|
import org.apache.http.client.methods.HttpPost;
|
|
import org.apache.http.entity.ContentType;
|
|
import org.apache.http.entity.StringEntity;
|
|
import org.apache.http.impl.client.CloseableHttpClient;
|
|
import org.apache.http.impl.client.HttpClients;
|
|
import org.apache.http.util.EntityUtils;
|
|
import com.google.gson.Gson;
|
|
|
|
import java.io.FileOutputStream;
|
|
import java.io.IOException;
|
|
import java.io.InputStream;
|
|
import java.util.HashMap;
|
|
import java.util.Map;
|
|
|
|
/**
|
|
* 文本转换为语音
|
|
*/
|
|
public class ElevenLabsClient {
|
|
|
|
private static final String BASE_URL = "https://api.elevenlabs.io/v1";
|
|
private final String apiKey;
|
|
private final CloseableHttpClient httpClient;
|
|
private final Gson gson;
|
|
|
|
public ElevenLabsClient(String apiKey) {
|
|
this.apiKey = apiKey;
|
|
this.httpClient = HttpClients.createDefault();
|
|
this.gson = new Gson();
|
|
}
|
|
|
|
/**
|
|
* 将文本转换为语音并保存到文件
|
|
*
|
|
* @param text 要转换的文本
|
|
* @param voiceId 语音ID (可从ElevenLabs网站获取)
|
|
* @param outputFilePath 输出文件路径
|
|
* @throws IOException 网络请求或文件操作异常
|
|
*/
|
|
public void textToSpeech(String text, String voiceId, String outputFilePath) throws IOException {
|
|
HttpPost httpPost = new HttpPost(BASE_URL + "/text-to-speech/" + voiceId);
|
|
httpPost.setHeader("xi-api-key", apiKey);
|
|
httpPost.setHeader("Content-Type", "application/json");
|
|
|
|
Map<String, Object> payload = new HashMap<>();
|
|
payload.put("text", text);
|
|
payload.put("model_id", "eleven_monolingual_v1");
|
|
payload.put("voice_settings", new VoiceSettings(0.7, 0.5));
|
|
|
|
StringEntity entity = new StringEntity(gson.toJson(payload), ContentType.APPLICATION_JSON);
|
|
httpPost.setEntity(entity);
|
|
|
|
try (CloseableHttpResponse response = httpClient.execute(httpPost)) {
|
|
HttpEntity responseEntity = response.getEntity();
|
|
if (responseEntity != null) {
|
|
try (InputStream inputStream = responseEntity.getContent();
|
|
FileOutputStream outputStream = new FileOutputStream(outputFilePath)) {
|
|
|
|
byte[] buffer = new byte[4096];
|
|
int bytesRead;
|
|
while ((bytesRead = inputStream.read(buffer)) != -1) {
|
|
outputStream.write(buffer, 0, bytesRead);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* 获取可用的语音列表
|
|
*
|
|
* @return 语音列表响应
|
|
* @throws IOException 网络请求异常
|
|
*/
|
|
public VoicesResponse getVoices() throws IOException {
|
|
HttpGet httpGet = new HttpGet(BASE_URL + "/voices");
|
|
httpGet.setHeader("xi-api-key", apiKey);
|
|
|
|
try (CloseableHttpResponse response = httpClient.execute(httpGet)) {
|
|
HttpEntity responseEntity = response.getEntity();
|
|
String responseBody = EntityUtils.toString(responseEntity);
|
|
return gson.fromJson(responseBody, VoicesResponse.class);
|
|
}
|
|
}
|
|
|
|
// 关闭HTTP客户端
|
|
public void close() throws IOException {
|
|
httpClient.close();
|
|
}
|
|
|
|
// 语音设置内部类
|
|
private static class VoiceSettings {
|
|
private double stability;
|
|
private double similarity_boost;
|
|
|
|
public VoiceSettings(double stability, double similarity_boost) {
|
|
this.stability = stability;
|
|
this.similarity_boost = similarity_boost;
|
|
}
|
|
|
|
// getter方法
|
|
public double getStability() {
|
|
return stability;
|
|
}
|
|
|
|
public double getSimilarity_boost() {
|
|
return similarity_boost;
|
|
}
|
|
}
|
|
|
|
// 语音列表响应模型
|
|
public static class VoicesResponse {
|
|
private Voice[] voices;
|
|
|
|
public Voice[] getVoices() {
|
|
return voices;
|
|
}
|
|
|
|
public void setVoices(Voice[] voices) {
|
|
this.voices = voices;
|
|
}
|
|
|
|
public static class Voice {
|
|
private String voice_id;
|
|
private String name;
|
|
private String category;
|
|
private FineTuning fine_tuning;
|
|
|
|
public String getVoice_id() {
|
|
return voice_id;
|
|
}
|
|
|
|
public void setVoice_id(String voice_id) {
|
|
this.voice_id = voice_id;
|
|
}
|
|
|
|
public String getName() {
|
|
return name;
|
|
}
|
|
|
|
public void setName(String name) {
|
|
this.name = name;
|
|
}
|
|
|
|
public String getCategory() {
|
|
return category;
|
|
}
|
|
|
|
public void setCategory(String category) {
|
|
this.category = category;
|
|
}
|
|
|
|
public FineTuning getFine_tuning() {
|
|
return fine_tuning;
|
|
}
|
|
|
|
public void setFine_tuning(FineTuning fine_tuning) {
|
|
this.fine_tuning = fine_tuning;
|
|
}
|
|
}
|
|
}
|
|
|
|
// 使用示例
|
|
public static void main(String[] args) {
|
|
String apiKey = "sk_5240d8f56cb1eb5225fffcf903f62479884d1af5b3de6812";
|
|
ElevenLabsClient client = new ElevenLabsClient(apiKey);
|
|
|
|
try {
|
|
// 获取可用语音
|
|
VoicesResponse voicesResponse = client.getVoices();
|
|
if (voicesResponse != null && voicesResponse.getVoices() != null && voicesResponse.getVoices().length > 0) {
|
|
System.out.println("Available voices:");
|
|
for (VoicesResponse.Voice voice : voicesResponse.getVoices()) {
|
|
System.out.println(voice.getName() + " (ID: " + voice.getVoice_id() + ")");
|
|
}
|
|
|
|
// 使用第一个可用语音进行文本转语音
|
|
String firstVoiceId = voicesResponse.getVoices()[0].getVoice_id();
|
|
String text = "Come on, Baby,Come on, Baby,Come on, Baby,Come on, Baby";
|
|
String outputFile = "output.mp3";
|
|
|
|
client.textToSpeech(text, firstVoiceId, outputFile);
|
|
System.out.println("Audio saved to: " + outputFile);
|
|
}
|
|
} catch (IOException e) {
|
|
e.printStackTrace();
|
|
} finally {
|
|
try {
|
|
client.close();
|
|
} catch (IOException e) {
|
|
e.printStackTrace();
|
|
}
|
|
}
|
|
}
|
|
}
|