Qwen-Audio-3.0-ASR-Flash-Filetrans/Fun-ASR non-real-time speech recognition Java SDK

import com.alibaba.dashscope.audio.asr.transcription.*;
import com.alibaba.dashscope.utils.Constants;
import com.google.gson.*;

import java.util.Arrays;

public class Main {
    public static void main(String[] args) {
        // The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ across regions.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
        // Create the transcription request parameters
        TranscriptionParam param =
                TranscriptionParam.builder()
                        // The API Key differs between the Singapore and Beijing regions. Get an API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
                        // If you have not configured the environment variable, replace the following line with your Model Studio API Key: .apiKey("sk-xxx")
                        //.apiKey("apikey")
                        .model("qwen-audio-3.0-asr-flash-filetrans") // This uses qwen-audio-3.0-asr-flash-filetrans as an example; change the model name as needed. Model list: https://www.alibabacloud.com/help/zh/model-studio/models
                        .fileUrls(
                                Arrays.asList(
                                        "{YOUR_AUDIO_URL}"))
                        .build();
        try {
            Transcription transcription = new Transcription();
            // Submit the transcription request
            TranscriptionResult result = transcription.asyncCall(param);
            System.out.println("RequestId: " + result.getRequestId());
            // Block and wait for the task to complete, then get the result
            result = transcription.wait(
                    TranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId()));
            // Print the result
            System.out.println(new GsonBuilder().setPrettyPrinting().create().toJson(result.getOutput()));
        } catch (Exception e) {
            System.out.println("error: " + e);
        }
        System.exit(0);
    }
}

import com.alibaba.dashscope.audio.asr.transcription.*;
import com.alibaba.dashscope.common.TaskStatus;
import com.alibaba.dashscope.utils.Constants;
import com.google.gson.*;

import java.util.Arrays;

public class Main {
    public static void main(String[] args) {
        // The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ across regions.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
        // Create the transcription request parameters
        TranscriptionParam param =
                TranscriptionParam.builder()
                        // The API Key differs between the Singapore and Beijing regions. Get an API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
                        // If you have not configured the environment variable, replace the following line with your Model Studio API Key: .apiKey("sk-xxx")
                        //.apiKey("apikey")
                        .model("qwen-audio-3.0-asr-flash-filetrans") // This uses qwen-audio-3.0-asr-flash-filetrans as an example; change the model name as needed. Model list: https://www.alibabacloud.com/help/zh/model-studio/models
                        .fileUrls(
                                Arrays.asList(
                                        "{YOUR_AUDIO_URL}"))
                        .build();
        try {
            Transcription transcription = new Transcription();
            // Submit the transcription request
            TranscriptionResult result = transcription.asyncCall(param);
            System.out.println("RequestId: " + result.getRequestId());
            // Poll for the task result in a loop until the task finishes
            while (true) {
                result = transcription.fetch(TranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId()));
                if (result.getTaskStatus() == TaskStatus.SUCCEEDED || result.getTaskStatus() == TaskStatus.FAILED) {
                    break;
                }
                Thread.sleep(1000);
            }
            // Print the result
            System.out.println(new GsonBuilder().setPrettyPrinting().create().toJson(result.getOutput()));
        } catch (Exception e) {
            System.out.println("error: " + e);
        }
        System.exit(0);
    }
}

{
    "file_url":"{YOUR_AUDIO_URL}",
    "properties":{
        "audio_format":"pcm_s16le",
        "channels":[
            0
        ],
        "original_sampling_rate":16000,
        "original_duration_in_milliseconds":3834
    },
    "transcripts":[
        {
            "channel_id":0,
            "content_duration_in_milliseconds":3720,
            "text":"Hello world, this is Alibaba Speech Lab.",
            "sentences":[
                {
                    "begin_time":100,
                    "end_time":3820,
                    "text":"Hello world, this is Alibaba Speech Lab.",
                    "sentence_id":1,
                    "speaker_id":0, //This field is displayed only when automatic speaker diarization is enabled
                    "words":[
                        {
                            "begin_time":100,
                            "end_time":596,
                            "text":"Hello ",
                            "punctuation":""
                        },
                        {
                            "begin_time":596,
                            "end_time":844,
                            "text":"world",
                            "punctuation":", "
                        }
                        // Other content is omitted here
                    ]
                }
            ]
        }
    ]
}