Skip to main content

Non-real-time speech recognition (Qwen-Audio-3.x-ASR-Flash/Fun-ASR-Flash) Android SDK

Qwen-Audio-3.x-ASR-Flash/Fun-ASR-Flash non-real-time speech recognition Android SDK converts speech to text.

User guide: Non-real-time speech recognition. For supported audio formats, file size limits, duration limits, and other input requirements, see Audio specifications.

Quick start

  1. Get an API key: Get an API key. For security, we recommend that you configure the API key in an environment variable.
  2. Download the SDK and run the sample code:
    • Download the latest SDK bundle.
    • Extract the ZIP archive. Obtain the SDK in AAR format from app/libs and add it to your project dependencies. For Android CPP integration, use android_libs and android_include in the ZIP archive to obtain the dynamic libraries and header files.
    • Open the project in Android Studio. The sample code is in DashFunAsrFlashFileTranscriberActivity.java. Replace the API key to try the feature.

Call procedure

Synchronous mode

  1. Initialize the SDK
  2. Configure the parameters based on your business requirements
  3. Call startFileTranscriber to send a non-real-time speech recognition request and wait for the result.
  4. Use onFileTransEventCallback to listen for the EVENT_FILE_TRANS_RESULT event and obtain the final recognition result.
  5. Call release to release SDK resources

Request parameters

Connection and control parameters

Pass a JSON string to the initialize method's parameters parameter to configure these settings. Parameter example: The following JSON string is an example and does not list all parameters. Add parameters as needed in your code: 
{
    "url": "wss://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
    "apikey": "st-****",
    "device_id": "my_device_id",
    "service_mode": "1"
}
Parameters
ParameterTypeRequiredDescription
urlStringYesService endpoints:
  • wss://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
  • China (Beijing): wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
  • Singapore: wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation

Replace {WorkspaceId} with your actual Workspace ID.
apikeyStringYesAPI Key.
service_modeStringYesThe operating mode. For non-real-time speech recognition, set this parameter to "1".
device_idStringYesA unique string that identifies the end user. You can use an in-app user ID or a client-generated unique device identifier. This ID is mainly used for log tracing and troubleshooting.
debug_pathStringNoThe path for log files. This parameter takes effect only when you call initialize with save_log set to true. In this case, you must specify the log file path. Otherwise, an error occurs. Up to two log files are retained locally.
max_log_file_sizeintNoThe maximum log file size in bytes. This parameter takes effect only when you call initialize with save_log set to true. Default: 104857600 (100 * 1024 * 1024 bytes, or 100 MiB).
log_track_levelintNoThe filtering level for logs sent through the logging callback (onFileTransLogTrackCallback). Default: 2. Valid values: - 0: LOG_LEVEL_VERBOSE - 1: LOG_LEVEL_DEBUG - 2: LOG_LEVEL_INFO - 3: LOG_LEVEL_WARNING - 4: LOG_LEVEL_ERROR - 5: LOG_LEVEL_NONE (disables this feature). Note: log_track_level and level (configured through initialize method) jointly determine which logs are delivered. The numeric level of a log must be greater than or equal to both log_track_level and level for the log to be delivered. For example, if log_track_level is set to 2 (INFO) and level is set to 3 (WARNING), only WARNING and higher-severity logs (numeric level >= 3) are delivered.

Recognition parameters

Use startFileTranscriber to configure all recognition parameters. Parameter example: The following JSON string is an example and does not list all parameters. Add parameters as needed in your code: 
{
  "apikey": "st-****",
  "messages": [
    {
      "content": [
        {
          "input_audio": {
            "data": "{YOUR_AUDIO_URL}"
          },
          "type": "input_audio"
        }
      ],
      "role": "user"
    }
  ],
  "nls_config": {
    "format": "mp3",
    "model": "qwen-audio-3.0-asr-flash"
  }
}
Parameters
ParameterTypeRequiredDescription
apikeystringNoIf Connection and control parameters apikey uses temporary API key, you can update it here to prevent expiration.
nls_configobjectYesThe core speech recognition configuration object, including the model and parameters that control recognition.
nls_config.modelstringYesThe model used in the example. For model information, see Supported models and regions.
nls_config.formatstringYesThe audio format. Set this parameter to the actual format. Supported formats include wav, mp3, opus. For details, see Audio specifications.
nls_config.sample_ratestringNoThe audio sample rate in Hz. For example, 16000 indicates a sample rate of 16 kHz. For details, see Audio specifications.
nls_config.vocabulary_idstringNoThe precompiled vocabulary ID. Create a vocabulary in advance and pass its ID during recognition to use its hotwords. Use this option when the vocabulary is known, relatively stable, and reused across requests. For usage instructions, see Precompiled hotwords.
nls_config.instant_vocabularyobjectNoInstant hotwords.
Pass key-value pairs. The key is the hotword text (string) and the value is its weight (integer). You do not need to create a vocabulary in advance. Valid weights are [1, 5] or 50. Within [1, 5], a higher weight makes the model more likely to output the word. A weight of 50 specifies a super hotword and significantly increases recall. You can specify up to 50 super hotwords.
Use this option for temporary, session-level hotword optimization.
When both instant and precompiled hotwords are configured, the system merges them. If the merged list exceeds 2000 entries, it randomly selects 2000 entries. For usage instructions, see Instant hotwords.
For models and limits that apply to instant hotwords, see Instant hotwords.

{
  "张三": 5,
  "李四": 5
}
nls_config.language_hintsarray[string]NoThe language codes for recognition. If the language is unknown in advance, omit this parameter to let the model detect it automatically.
For Qwen-Audio-3.0-ASR-Flash models, up to four values are supported. If more are specified, only the first four take effect. For Fun-ASR-Flash models, only one value is supported. If multiple values are specified, only the first takes effect.
  • Qwen-Audio-3.x-ASR-Flash, fun-asr-flash-2026-06-15:
  • zh: Chinese
  • en: English
  • ja: Japanese
  • ko: Korean
  • vi: Vietnamese
  • th: Thai
  • id: Indonesian
  • ms: Malay
  • tl: Filipino
  • hi: Hindi
  • ar: Arabic
  • fr: French
  • de: German
  • es: Spanish
  • pt: Portuguese
  • ru: Russian
  • it: Italian
  • nl: Dutch
  • sv: Swedish
  • da: Danish
  • fi: Finnish
  • no: Norwegian
  • el: Greek
  • pl: Polish
  • cs: Czech
  • hu: Hungarian
  • ro: Romanian
  • bg: Bulgarian
  • hr: Croatian
  • sk: Slovak
messagesarray[object]YesThe list of messages. It contains the audio to recognize and optional conversation context to improve recognition.
See the following descriptions.
messages parameters:
Context improves the recognition accuracy of specialized terms. For usage instructions, see Context enhancement.Constraints: Context messages (input_text and text types) are limited to five each. If the limit is exceeded, only the five most recent messages are retained. The total context text length per turn (the sum of the user and assistant text field lengths) must not exceed 400 characters. Each character counts as one. Excess characters are truncated from the end.
When context is included, messages messages must follow a specific order. Arrange context messages by conversation turn. Within each turn, user (input_text type) must precede the corresponding assistant (text type). The input_audio user message containing input audio must be placed at the end of messages .
ParameterTypeRequiredDescription
rolestringYesThe message role. Valid values:
  • user (required): A user message. When type is input_audio, it represents the audio to recognize. When type is input_text, it represents recognition results from previous turns or a domain-specific vocabulary (optional context).
  • assistant (optional context): Large language model responses from previous turns.
contentarray[object]YesThe list of message content. See the following descriptions.
content parameters:
ParameterTypeRequiredDescription
typestringYesThe content type. Each request requires at least one input_audio message. Valid values:
  • input_audio (required): The audio input to recognize (role is user). You must also provide the input_audio object.
  • input_text (optional context): Recognition results of user speech from previous turns or a domain-specific vocabulary (role is user). You must also provide the text field.
  • text (optional context): Large language model responses from previous turns (role is assistant). You must also provide the text field.
input_audioobjectNoRequired when type is input_audio.
input_audio.datastringYesThe audio data to recognize. For supported audio formats, file size limits, duration limits, and other input requirements, see Audio specifications. The following two input methods are supported:
  • Audio file URL: Pass a publicly accessible audio file URL.
  • Base64 Data URI: Pass Base64-encoded audio as a Data URI. Concatenate the data:{MIME_TYPE};base64, prefix with the Base64-encoded audio data. Supported MIME types include audio/wav, audio/mp3.

Example (URL): https://example.com/audio/sample.wav
Example (Base64): data:audio/wav;base64,{BASE64_ENCODED_DATA}
textstringNoRequired when type is input_text, provide recognition results of user speech from previous turns or a domain-specific vocabulary. When type is text, provide large language model responses from previous turns. Text length is counted in characters, with each character counting as one. The total length of all messages' text fields in each context turn must not exceed 400 characters. Excess characters are truncated from the end.

Key interfaces

NativeNui

initialize

Initialize the speech recognition SDK instance. The SDK uses a singleton. Do not initialize it again before calling release. This method blocks. Call it from a non-UI thread. Method signature 
public synchronized int initialize(final INativeFileTransCallback callback,
                                   String parameters,
                                   final Constants.LogLevel level,
                                   final boolean save_log)
Parameters
ParameterTypeDescription
callbackINativeFileTransCallbackThe implementation of the event and data callback interface.
parametersStringA JSON string containing authentication, connection, and debugging parameters. See Connection and control parameters.
levelConstants.LogLevelThe level of logs printed by the SDK.
save_logbooleanWhether to save logs locally. If set to true, use Connection and control parameters to set debug_path to specify the path, and use max_log_file_size to set the file size.

setParams

Use this method to set or update nls_config separately. You do not need to call this method if all parameters are provided in startFileTranscriber in a single call. Method signature 
public synchronized int setParams(String params);
Parameters
ParameterTypeDescription
paramsStringRecognition parameters in nls_config and messages parameters.
Example: 
{
  "messages": [
    {
      "content": [
        {
          "input_audio": {
            "data": "{YOUR_AUDIO_URL}"
          },
          "type": "input_audio"
        }
      ],
      "role": "user"
    }
  ],
  "nls_config": {
    "format": "mp3",
    "model": "qwen-audio-3.0-asr-flash"
  }
}

startFileTranscriber

Start recognition. Method signature 
public synchronized int startFileTranscriber(String params, byte[ ] task_id)
Parameters
ParameterTypeDescription
paramsStringRecognition parameters. Example: 
{
  "apikey": "st-****",
  "messages": [
    {
      "content": [
        {
          "input_audio": {
            "data": "{YOUR_AUDIO_URL}"
          },
          "type": "input_audio"
        }
      ],
      "role": "user"
    }
  ],
  "nls_config": {
    "format": "mp3",
    "model": "qwen-audio-3.0-asr-flash"
  }
}
task_idbyte[ ]You can ignore this parameter and pass null.

queryFileTranscriber

This non-real-time speech recognition feature only supports synchronous requests. You can ignore this method.

cancelFileTranscriber

Immediately cancel the current task. Method signature 
public synchronized int cancelFileTranscriber(String task_id)
Parameters
ParameterTypeDescription
task_idStringThe ID of the task to cancel, obtained from EVENT_FILE_TRANS_UPLOADED.

release

Release all internal SDK resources. After this call, the SDK instance becomes unavailable. To use it again, call initialize to initialize it again. Method signature 
public synchronized int release();

GetVersion

Get the current SDK version. Method signature 
public synchronized String GetVersion();
Return value The current SDK version.

INativeFileTransCallback: Callbacks

onFileTransEventCallback: Listen for events and recognition results

Method signature 
void onFileTransEventCallback(NuiEvent event, final int resultCode, final int arg2, AsrResult asrResult, String taskId);
Parameters
ParameterTypeDescription
eventNuiEventThe callback event.
resultCodeintValid only when the EVENT_ASR_ERROR event occurs.
asrResultAsrResultThe speech recognition result.
taskIdStringThe task ID.
arg2intReserved.

onFileTransLogTrackCallback: Listen for tracing logs

This callback receives detailed internal SDK logs for troubleshooting and debugging. 
default void onFileTransLogTrackCallback(Constants.LogLevel level, String log)

Event types

EventDescription
EVENT_FILE_TRANS_CONNECTEDSuccessfully connected to the service.
EVENT_FILE_TRANS_UPLOADEDThe audio file was uploaded successfully. You can obtain the current task_id at this point.
EVENT_FILE_TRANS_RESULTThe final recognition result.
EVENT_ASR_ERRORAn error occurred during speech recognition.
API Usage
Text Generation
Image Generation
Video Generation
World models
3D Model Generation
Audio
  • Audio generation
Real-time Multimodal
Realtime API
Text Embedding
Translation models
Decision Model
More Models
Toolkit/Framework
TokenPlan
Model Production
File Management
Billing
Model Management
More