通义千问的语音合成模型

#  DashScope SDK 版本不低于 1.24.6
import os
import requests
import dashscope

text = "那我来给大家推荐一款T恤，这款呢真的是超级好看，这个颜色呢很显气质，而且呢也是搭配的绝佳单品，大家可以闭眼入，真的是非常好看，对身材的包容性也很好，不管啥身材的宝宝呢，穿上去都是很好看的。推荐宝宝们下单哦。"
# SpeechSynthesizer接口使用方法：dashscope.audio.qwen_tts.SpeechSynthesizer.call(...)
response = dashscope.MultiModalConversation.call(
    model="qwen3-tts-flash",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    text=text,
    voice="Cherry",
    language_type="Chinese", # 建议与文本语种一致，以获得正确的发音和自然的语调。
    stream=False
)
audio_url = response.output.audio.url
save_path = "downloaded_audio.wav"  # 自定义保存路径

try:
    response = requests.get(audio_url)
    response.raise_for_status()  # 检查请求是否成功
    with open(save_path, 'wb') as f:
        f.write(response.content)
    print(f"音频文件已保存至：{save_path}")
except Exception as e:
    print(f"下载失败：{str(e)}")
    

//  DashScope SDK 版本不低于2.21.9
// 2.20.7 及以上版本支持指定 Dylan、Jada与 Sunny 三种音色
import com.alibaba.dashscope.aigc.multimodalconversation.AudioParameters;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.protocol.Protocol;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.URL;

public class Main {
    private static final String MODEL = "qwen3-tts-flash";
    public static void call() throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model(MODEL)
                .text("Today is a wonderful day to build something people love!")
                .voice(AudioParameters.Voice.CHERRY)
                .languageType("English") // 建议与文本语种一致，以获得正确的发音和自然的语调。
                .build();
        MultiModalConversationResult result = conv.call(param);
        String audioUrl = result.getOutput().getAudio().getUrl();
        System.out.print(audioUrl);

        // 下载音频文件到本地
        try (InputStream in = new URL(audioUrl).openStream();
             FileOutputStream out = new FileOutputStream("downloaded_audio.wav")) {
            byte[] buffer = new byte[1024];
            int bytesRead;
            while ((bytesRead = in.read(buffer)) != -1) {
                out.write(buffer, 0, bytesRead);
            }
            System.out.println("\n音频文件已下载到本地: downloaded_audio.wav");
        } catch (Exception e) {
            System.out.println("\n下载音频文件时出错: " + e.getMessage());
        }
    }
    public static void main(String[] args) {
        try {
            call();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl -X POST 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen3-tts-flash",
    "input": {
        "text": "那我来给大家推荐一款T恤，这款呢真的是超级好看，这个颜色呢很显气质，而且呢也是搭配的绝佳单品，大家可以闭眼入，真的是非常好看，对身材的包容性也很好，不管啥身材的宝宝呢，穿上去都是很好看的。推荐宝宝们下单哦。",
        "voice": "Cherry",
        "language_type": "Chinese"
    }
}'

#  DashScope SDK 版本不低于 1.24.6
# coding=utf-8
#
# Installation instructions for pyaudio:
# APPLE Mac OS X
#   brew install portaudio
#   pip install pyaudio
# Debian/Ubuntu
#   sudo apt-get install python-pyaudio python3-pyaudio
#   or
#   pip install pyaudio
# CentOS
#   sudo yum install -y portaudio portaudio-devel && pip install pyaudio
# Microsoft Windows
#   python -m pip install pyaudio

import os
import dashscope
import pyaudio
import time
import base64
import numpy as np

p = pyaudio.PyAudio()
# 创建音频流
stream = p.open(format=pyaudio.paInt16,
                channels=1,
                rate=24000,
                output=True)


text = "你好啊，我是通义千问"
response = dashscope.MultiModalConversation.call(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-tts-flash",
    text=text,
    voice="Cherry",
    language_type="Chinese",  # 建议与文本语种一致，以获得正确的发音和自然的语调。
    stream=True
)

for chunk in response:
    audio = chunk.output.audio
    if audio.data is not None:
        wav_bytes = base64.b64decode(audio.data)
        audio_np = np.frombuffer(wav_bytes, dtype=np.int16)
        # 直接播放音频数据
        stream.write(audio_np.tobytes())
    if chunk.output.finish_reason == "stop":
        print("finish at: {} ", chunk.output.audio.expires_at)
time.sleep(0.8)
# 清理资源
stream.stop_stream()
stream.close()
p.terminate()

// DashScope SDK 版本不低于2.21.9
// 2.20.7 及以上版本支持指定 Dylan、Jada与 Sunny 三种音色
import com.alibaba.dashscope.aigc.multimodalconversation.AudioParameters;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.protocol.Protocol;
import io.reactivex.Flowable;
import javax.sound.sampled.*;
import java.util.Base64;

public class Main {
    private static final String MODEL = "qwen3-tts-flash";
    public static void streamCall() throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model(MODEL)
                .text("Today is a wonderful day to build something people love!")
                .voice(AudioParameters.Voice.CHERRY)
                .languageType("English") // 建议与文本语种一致，以获得正确的发音和自然的语调。
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(r -> {
            try {
                // 1. 获取Base64编码的音频数据
                String base64Data = r.getOutput().getAudio().getData();
                byte[] audioBytes = Base64.getDecoder().decode(base64Data);

                // 2. 配置音频格式（根据API返回的音频格式调整）
                AudioFormat format = new AudioFormat(
                        AudioFormat.Encoding.PCM_SIGNED,
                        24000, // 采样率（需与API返回格式一致）
                        16,    // 采样位数
                        1,     // 声道数
                        2,     // 帧大小（位数/字节数）
                        16000, // 数据传输率
                        false  // 是否压缩
                );

                // 3. 实时播放音频数据
                DataLine.Info info = new DataLine.Info(SourceDataLine.class, format);
                try (SourceDataLine line = (SourceDataLine) AudioSystem.getLine(info)) {
                    if (line != null) {
                        line.open(format);
                        line.start();
                        line.write(audioBytes, 0, audioBytes.length);
                        line.drain();
                    }
                }
            } catch (LineUnavailableException e) {
                e.printStackTrace();
            }
        });
    }
    public static void main(String[] args) {
        try {
            streamCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl -X POST 'https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-H 'X-DashScope-SSE: enable' \
-d '{
    "model": "qwen3-tts-flash",
    "input": {
        "text": "那我来给大家推荐一款T恤，这款呢真的是超级好看，这个颜色呢很显气质，而且呢也是搭配的绝佳单品，大家可以闭眼入，真的是非常好看，对身材的包容性也很好，不管啥身材的宝宝呢，穿上去都是很好看的。推荐宝宝们下单哦。",
        "voice": "Cherry",
        "language_type": "Chinese"
    }
}'