使用 AOQ 接入 qwen-audio-3.0-tts-flash 實現語音合成

import android.content.Context;

import com.alibaba.aoq.clientsdk.AoqClientEngine;
import com.alibaba.aoq.clientsdk.AoqClientListener;

import org.json.JSONException;
import org.json.JSONObject;

import java.nio.charset.StandardCharsets;
import java.util.UUID;

public final class TtsClient {
    private AoqClientEngine engine;
    private String taskId;
    private String pendingText;
    private String pendingVoice;
    private boolean connected;
    private boolean taskActive;

    public TtsClient(Context context, AoqClientEngine.AoqConnectConfig connectConfig) {
        AoqClientListener listener = new AoqClientListener() {
            @Override
            public void onConnectionStatusChange(AoqClientEngine.AoqConnectionStatus status) {
                if (status == AoqClientEngine.AoqConnectionStatus.AoqConnectionStatusConnected) {
                    connected = true;
                } else if (status == AoqClientEngine.AoqConnectionStatus
                        .AoqConnectionStatusDisconnected) {
                    connected = false;
                }
            }

            @Override
            public void onDataMsg(AoqClientEngine.AoqDataMsg msg) {
                try {
                    JSONObject event = new JSONObject(
                            new String(msg.data, StandardCharsets.UTF_8));
                    String eventName = event.optJSONObject("header") == null
                            ? "" : event.optJSONObject("header").optString("event");
                    if ("task-started".equals(eventName)) {
                        sendContinueTask();
                        sendFinishTask();
                    } else if ("task-finished".equals(eventName)
                            || "task-failed".equals(eventName)) {
                        taskActive = false;
                    }
                } catch (JSONException e) {
                    throw new IllegalArgumentException("Invalid server event", e);
                }
            }
        };

        AoqClientEngine.AoqCreateConfig createConfig = new AoqClientEngine.AoqCreateConfig();
        createConfig.workDir = context.getFilesDir().getAbsolutePath();
        engine = AoqClientEngine.createEngine(context, createConfig, listener);

        // 樣本參數，應與 run-task 中的輸出音頻格式一致。
        AoqClientEngine.AoqAudioCodecConfig audioDecoderConfig =
                new AoqClientEngine.AoqAudioCodecConfig();
        audioDecoderConfig.trackType = AoqClientEngine.AoqTrackType.AoqTrackTypeAudio;
        audioDecoderConfig.codecType = AoqClientEngine.AoqEncoderType.AoqEncoderTypeAudioPCM;
        audioDecoderConfig.sampleRate = 24000;
        audioDecoderConfig.channel = 1;
        engine.setAudioDecoderConfig(audioDecoderConfig);

        AoqClientEngine.AoqAudioPlaybackConfig playbackConfig =
                new AoqClientEngine.AoqAudioPlaybackConfig();
        playbackConfig.channel = 1;
        playbackConfig.isDefaultSpeaker = true;
        engine.startAudioPlayer(playbackConfig);

        AoqClientEngine.AoqTrackParam publishDataTrack =
                new AoqClientEngine.AoqTrackParam();
        publishDataTrack.trackType = AoqClientEngine.AoqTrackType.AoqTrackTypeData;
        connectConfig.publishTracks.add(publishDataTrack);

        AoqClientEngine.AoqTrackParam subscribeAudioTrack =
                new AoqClientEngine.AoqTrackParam();
        subscribeAudioTrack.trackType = AoqClientEngine.AoqTrackType.AoqTrackTypeAudio;
        connectConfig.subscribeTracks.add(subscribeAudioTrack);

        AoqClientEngine.AoqTrackParam subscribeDataTrack =
                new AoqClientEngine.AoqTrackParam();
        subscribeDataTrack.trackType = AoqClientEngine.AoqTrackType.AoqTrackTypeData;
        connectConfig.subscribeTracks.add(subscribeDataTrack);

        engine.connect(connectConfig);
    }

    public void synthesize(String text, String voice) {
        if (!connected || taskActive) {
            throw new IllegalStateException("The connection is not ready or a task is active.");
        }
        taskId = UUID.randomUUID().toString();
        pendingText = text;
        pendingVoice = voice;
        taskActive = true;
        sendRunTask();
    }

    private void sendRunTask() {
        try {
            JSONObject header = new JSONObject()
                    .put("action", "run-task")
                    .put("task_id", taskId)
                    .put("streaming", "duplex");
            JSONObject parameters = new JSONObject()
                    .put("text_type", "PlainText")
                    .put("voice", pendingVoice)
                    .put("format", "pcm")
                    .put("sample_rate", 24000);
            JSONObject payload = new JSONObject()
                    .put("task_group", "audio")
                    .put("task", "tts")
                    .put("function", "SpeechSynthesizer")
                    .put("model", "qwen-audio-3.0-tts-flash")
                    .put("input", new JSONObject())
                    .put("parameters", parameters);
            JSONObject runTask = new JSONObject().put("header", header).put("payload", payload);
            AoqClientEngine.AoqDataMsg dataMessage = new AoqClientEngine.AoqDataMsg();
            dataMessage.data = runTask.toString().getBytes(StandardCharsets.UTF_8);
            engine.sendDataMsg(dataMessage);
        } catch (JSONException e) {
            throw new IllegalStateException("Failed to create run-task", e);
        }
    }

    private void sendContinueTask() {
        try {
            JSONObject header = new JSONObject()
                    .put("action", "continue-task")
                    .put("task_id", taskId)
                    .put("streaming", "duplex");
            JSONObject payload = new JSONObject()
                    .put("input", new JSONObject().put("text", pendingText));
            JSONObject continueTask = new JSONObject()
                    .put("header", header)
                    .put("payload", payload);
            AoqClientEngine.AoqDataMsg dataMessage = new AoqClientEngine.AoqDataMsg();
            dataMessage.data = continueTask.toString().getBytes(StandardCharsets.UTF_8);
            engine.sendDataMsg(dataMessage);
        } catch (JSONException e) {
            throw new IllegalStateException("Failed to create continue-task", e);
        }
    }

    private void sendFinishTask() {
        try {
            JSONObject header = new JSONObject()
                    .put("action", "finish-task")
                    .put("task_id", taskId)
                    .put("streaming", "duplex");
            JSONObject finishTask = new JSONObject()
                    .put("header", header)
                    .put("payload", new JSONObject().put("input", new JSONObject()));
            AoqClientEngine.AoqDataMsg dataMessage = new AoqClientEngine.AoqDataMsg();
            dataMessage.data = finishTask.toString().getBytes(StandardCharsets.UTF_8);
            engine.sendDataMsg(dataMessage);
        } catch (JSONException e) {
            throw new IllegalStateException("Failed to create finish-task", e);
        }
    }

    public void close() {
        engine.disconnect();
        AoqClientEngine.destroy();
    }
}