Alibaba Cloud Model Studio:Real-time speech synthesis

import os
import dashscope

# Se a variável de ambiente não estiver configurada, substitua a linha abaixo por sua API Key do Model Studio: api_key = "sk-xxx"
# A configuração abaixo refere-se à região Pequim (China). Substitua {WorkspaceId} pelo ID real do seu workspace. O valor de region varia conforme a região.
client = dashscope.Client(
    api_key=os.environ["DASHSCOPE_API_KEY"],
    workspace="{WorkspaceId}",
    region="cn-beijing",
)

with open("output.mp3", "wb") as audio:
    # Envia o texto em segmentos e recebe o áudio segmento por segmento
    with client.audio.tts.connect(
        model="qwen-audio-3.1-tts-flash",
        voice="longanhuan_v3.1",
        format="mp3",
        sample_rate=24000,
    ) as session:
        for text in ["你好，欢迎使用阿里云百炼。", "文本可以分段发送，音频会逐段返回。"]:
            session.send_text(text)
        session.flush()  # Aciona a síntese do texto em buffer (não encerra a entrada)
        session.stop()   # Encerra a entrada e aguarda o retorno do áudio restante
        for chunk in session.audio_chunks():
            audio.write(chunk)

import com.alibaba.dashscope.audio.tts.SpeechSynthesisResult;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisAudioFormat;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisParam;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesizer;
import com.alibaba.dashscope.common.ResultCallback;
import com.alibaba.dashscope.utils.Constants;
import java.io.FileOutputStream;
import java.nio.ByteBuffer;

public class Main {
    public static void main(String[] args) throws Exception {
        Constants.baseWebsocketApiUrl = "wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference";
        try (FileOutputStream audio = new FileOutputStream("output.mp3")) {
            SpeechSynthesisParam param = SpeechSynthesisParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-audio-3.1-tts-flash")
                .voice("longanhuan_v3.1")
                .format(SpeechSynthesisAudioFormat.MP3_24000HZ_MONO_256KBPS)
                .build();
            ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<>() {
                @Override
                public void onEvent(SpeechSynthesisResult result) {
                    ByteBuffer buffer = result.getAudioFrame();
                    if (buffer != null) {
                        byte[] bytes = new byte[buffer.remaining()];
                        buffer.get(bytes);
                        try { audio.write(bytes); }
                        catch (Exception e) { throw new RuntimeException(e); }
                    }
                }
                @Override
                public void onComplete() {}
                public void onError(Exception e) { e.printStackTrace(); }
            };
            SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
            try {
                for (String text : new String[]{"你好，欢迎使用阿里云百炼。", "文本可以分段发送，音频会逐段返回。"}) {
                    synthesizer.streamingCall(text);
                }
                synthesizer.streamingComplete(60000);
            } finally {
                synthesizer.getDuplexApi().close(1000, "done");
            }
        }
    }
}

import os
import dashscope

# Se a variável de ambiente não estiver configurada, substitua a linha abaixo por sua API Key do Model Studio: api_key = "sk-xxx"
client = dashscope.Client(
    api_key=os.environ["DASHSCOPE_API_KEY"],
    workspace="{WorkspaceId}",
    region="cn-beijing",
)

with open("output.mp3", "wb") as audio:
    # Envia o texto em segmentos e recebe o áudio segmento por segmento
    with client.audio.tts.connect(
        model="cosyvoice-v3-flash",
        voice="longanyang",
        format="mp3",
        sample_rate=24000,
    ) as session:
        for text in ["你好，欢迎使用阿里云百炼。", "文本可以分段发送，音频会逐段返回。"]:
            session.send_text(text)
        session.flush()  # Aciona a síntese do texto em buffer (não encerra a entrada)
        session.stop()   # Encerra a entrada e aguarda o retorno do áudio restante
        for chunk in session.audio_chunks():
            audio.write(chunk)

import com.alibaba.dashscope.audio.tts.SpeechSynthesisResult;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisAudioFormat;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisParam;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesizer;
import com.alibaba.dashscope.common.ResultCallback;
import com.alibaba.dashscope.utils.Constants;
import java.io.FileOutputStream;
import java.nio.ByteBuffer;

public class Main {
    public static void main(String[] args) throws Exception {
        Constants.baseWebsocketApiUrl = "wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference";
        try (FileOutputStream audio = new FileOutputStream("output.mp3")) {
            SpeechSynthesisParam param = SpeechSynthesisParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("cosyvoice-v3-flash")
                .voice("longanyang")
                .format(SpeechSynthesisAudioFormat.MP3_24000HZ_MONO_256KBPS)
                .build();
            ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<>() {
                @Override
                public void onEvent(SpeechSynthesisResult result) {
                    ByteBuffer buffer = result.getAudioFrame();
                    if (buffer != null) {
                        byte[] bytes = new byte[buffer.remaining()];
                        buffer.get(bytes);
                        try { audio.write(bytes); }
                        catch (Exception e) { throw new RuntimeException(e); }
                    }
                }
                @Override
                public void onComplete() {}
                public void onError(Exception e) { e.printStackTrace(); }
            };
            SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
            try {
                for (String text : new String[]{"你好，欢迎使用阿里云百炼。", "文本可以分段发送，音频会逐段返回。"}) {
                    synthesizer.streamingCall(text);
                }
                synthesizer.streamingComplete(60000);
            } finally {
                synthesizer.getDuplexApi().close(1000, "done");
            }
        }
    }
}