Alibaba Cloud Model Studio:Qwen-Audio-3.0-ASR-Flash-Streaming/Fun-ASR real-time speech recognition Android SDK guide

This guide shows you how to use the Android SDK for Qwen-Audio-3.0-ASR-Flash-Streaming and Fun-ASR-Realtime real-time speech recognition to convert speech to text.

User guide: For model introductions and selection advice, see Speech-to-text.

Quick start

1. Obtain an API key

2. Download the SDK and run the sample code:
   • Download the latest SDK package.
   • Extract the ZIP package. The AAR-format SDK is in the app/libs directory. Add it to your project dependencies. For Android C++ integration, use android_libs and android_include from the ZIP package to get the dynamic libraries and header files.
   • Open the project in Android Studio. The sample code is in DashFunAsrSpeechTranscriberActivity.java. Replace the API key to try out the feature.

Call procedure

1. Initialize the SDK.
2. Set the parameters for your use case. Use the parameters argument of the initialize method to set the Connection and control parameters, and use the setParams method to set the Speech recognition parameters.
3. Call startDialog to start recognition.
4. In the onNuiAudioStateChanged callback, start the recording device based on the audio state.
5. Continuously supply recording data in the onNuiNeedAudioData callback, or actively push recording data by calling updateAudio.
6. In the onNuiEventCallback callback, listen for events and get the speech recognition results.
7. Call stopDialog to stop recognition, and listen for the EVENT_TRANSCRIBER_COMPLETE event to confirm that recognition has ended.
8. When you no longer need recognition, call release to release the SDK resources.

Request parameters

Connection and control parameters

To configure these parameters, pass a JSON string in the parameters argument of the initialize method.

• Example: The following is a JSON string example. Not all parameters are listed. Add others as needed when you write your code:

{
    "url": "wss://dashscope.aliyuncs.com/api-ws/v1/inference",
    "apikey": "st-****",
    "device_id": "my_device_id",
    "service_mode": "1"
}

• Parameters

  Parameter	Type	Required	Description
  url	String	Yes	Service address: wss://dashscope.aliyuncs.com/api-ws/v1/inference China (Beijing): wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference Singapore: wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference Replace {WorkspaceId} with your actual Workspace ID.
  apikey	String	Yes	The API key.
  service_mode	String	Yes	The run mode. Fixed to "1" for real-time speech recognition.
  device_id	String	Yes	A unique string that identifies the end user. You can set it to an in-app user ID or a client-generated unique device identifier. This ID is mainly used for log tracing and troubleshooting.
  audio_update_manually	String	No	Whether to enable active audio data pushing. Default: "false". If set to "true" and the SDK version supports on-device audio processing capabilities such as AEC and VAD, those capabilities are enabled by default.
  workspace	String	No	The path where on-device resource files are stored. This parameter is required when audio_update_manually is set to "true" and an on-device audio processing capability such as AEC or VAD is enabled.
  debug_path	String	No	The storage path for log files. This parameter takes effect only when save_log is set to true in the initialize method. In this case, you must set the log file path, or an error occurs. A maximum of two log files are kept locally.
  save_wav	String	No	Whether to save the debug audio file. The audio file is saved under debug_path. Default: "false". Valid values: "true": save the file. "false": do not save the file. This parameter takes effect only when save_log is set to true in the initialize method. In addition, debug_path must also be set.
  max_log_file_size	int	No	The maximum size of a log file, in bytes. This parameter takes effect only when save_log is set to true in the initialize method. Default: 104857600 (100 * 1024 * 1024 bytes, that is, 100 MiB).
  log_track_level	int	No	The filter level for the log content sent through the log callback (onNuiLogTrackCallback). 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 (set through the initialize method) together determine which logs are ultimately sent to the callback. A log is sent to the callback only when its level value is greater than or equal to both log_track_level and level. For example, if log_track_level is set to 2 (INFO) and level is set to 3 (WARNING), then only logs of WARNING level or higher (value >= 3) are sent to the callback.
  enable_reconnection	String	No	Whether to resume transmission after the network reconnects. Default: "false".
  aec_params	object	No	The advanced configuration object for on-device acoustic echo cancellation (AEC). This object takes effect only when audio_update_manually is set to "true".
  aec_params.enable_aec	boolean	No	Whether to enable on-device AEC. If audio_update_manually is set to "true" and the SDK version supports on-device AEC, this capability is enabled by default.
  aec_params.save_audio	boolean	No	Whether to save audio processed by the on-device AEC module. If save_wav is set to "true" and debug_path is specified, this feature is enabled by default and the AEC audio data is saved to debug_path.
  aec_params.enable_aec_data_callback	boolean	No	Whether to return the AEC-processed data to your application. Default: false. If enabled, receive the data from the EVENT_AEC_DATA event in onNuiAssistEventCallback.
  vad_params	object	No	The advanced configuration object for on-device voice activity detection (VAD). This object takes effect only when audio_update_manually is set to "true".
  vad_params.enable_aec	boolean	No	Whether to enable on-device VAD. If audio_update_manually is set to "true" and the SDK version supports on-device VAD, this capability is enabled by default.
  vad_params.save_audio	boolean	No	Whether to save audio processed by the on-device VAD module. If save_wav is set to "true" and debug_path is specified, this feature is enabled by default and the VAD audio data is saved to debug_path.

Speech recognition parameters

To configure these parameters, pass a JSON string in the params argument of the setParams method.

• Example: The following is a JSON string example. Not all parameters are listed. Add others as needed when you write your code:

{
    "service_type": 4,
    "nls_config": {
        "model": "qwen-audio-3.0-asr-flash-streaming",
        "sr_format": "pcm",
        "sample_rate": "16000"
    }
}

• Parameters

  Top-level parameter	Type	Required	Description
  service_type	int	Yes	The speech service type. Fixed to 4 for real-time speech recognition.
  nls_config	object	Yes	The core configuration object for speech recognition. It contains key parameters such as model selection and recognition-quality controls.
  nls_config.model	string	Yes	The model name. The Qwen-Audio-3.0-ASR-Flash-Streaming and Fun-ASR-Realtime model series are supported. For details, see Supported models and regions.
  nls_config.sr_format	string	Yes	The audio format. Valid values: pcm opus ImportantFor Opus audio, pass PCM audio to the SDK. The SDK encodes it as Opus internally.
  nls_config.sample_rate	int	Yes	The sample rate, in Hz. Valid values: 8 kHz models support only 8000 Hz; other models support any sample rate. Important8000 Hz is not supported when an on-device audio processing capability such as AEC or VAD is enabled.
  nls_config.semantic_punctuation_enabled	boolean	No	Whether to enable semantic segmentation. Default value: false. true: Enables semantic segmentation and disables VAD segmentation. false (default): Enables VAD segmentation and disables semantic segmentation. Semantic segmentation is more accurate and is better suited to meeting transcription scenarios. VAD (Voice Activity Detection) segmentation has lower latency and is better suited to interactive scenarios.
  nls_config.max_sentence_silence	int	No	The VAD silence threshold for segmentation, in ms. When the silence after a segment of speech exceeds this threshold, the system determines that the sentence has ended. When semantic_punctuation_enabled is set to true, this parameter is not used as the criterion for returning sentence_end, but setting it too low may affect recognition performance. Default value: 1300. Valid values: [200, 6000].
  nls_config.multi_threshold_mode_enabled	boolean	No	ImportantTakes effect only when semantic_punctuation_enabled is false. Whether to enable multi-threshold mode. When enabled, this prevents VAD segments from becoming too long. Default value: false.
  nls_config.heartbeat	boolean	No	Whether to enable heartbeat packets. Default value: false. true: Keeps the connection to the server alive even when silent audio is sent continuously. false (default): Even when silent audio is continuously sent, the connection times out and closes after a period of time. Silent audio refers to content in an audio file or data stream that contains no sound signal. You can generate silent audio in several ways, such as using audio editing software like Audacity or Adobe Audition, or using a command-line tool like FFmpeg.
  nls_config.vocabulary_id	string	No	The ID of a precompiled hot word list. Generate this ID in advance by calling the create hot word list API. Pass the ID during recognition to use the hot words in the list. Suitable for scenarios where the vocabulary is known and relatively stable, and where you need to reuse the same word list across requests. For usage details, see Precompiled hotwords.
  nls_config.instant_vocabulary	object	No	Instant hot words. Passed as key-value pairs, where the key is the hot word text (string) and the value is the hot word weight (integer). No hot word list needs to be created in advance. The weight ranges from [1, 5] or is set to 50: a value in [1, 5] makes the model more likely to output the word as the value increases; a value of 50 designates a super hot word, which greatly improves recall, but the number of super hot words cannot exceed 50. Suitable for temporary, session-level hot word optimization. When instant and precompiled hotwords are configured together, the system merges both sets. If the merged set contains more than 2000 hotwords, the system randomly selects 2000 to use. For usage details, see Instant hotwords. ImportantOnly qwen-audio-3.0-asr-flash-streaming supports instant hot words.
  nls_config.language_hints	array[string]	No	The language of the audio to recognize. There is no default value; if not set, the model detects the language automatically. For the Qwen-Audio-3.0-ASR-Flash-Streaming model series, you can set up to 4 values; if you set more than 4, only the first 4 take effect. For the Fun-ASR-Realtime model series, you can set only 1 value; if you set multiple values, only the first one takes effect. Click to view the supported language codes qwen-audio-3.0-asr-flash-streaming, fun-asr-realtime, fun-asr-realtime-2025-11-07: 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 fun-asr-realtime-2026-02-28: zh: Chinese en: English ja: Japanese fun-asr-realtime-2025-09-15: zh: Chinese en: English fun-asr-flash-8k-realtime, fun-asr-flash-8k-realtime-2026-01-28: zh: Chinese fun-asr-mtl-realtime, fun-asr-mtl-realtime-2025-12-10: zh: Chinese en: English ja: Japanese ko: Korean vi: Vietnamese id: Indonesian th: Thai
  nls_config.speech_noise_threshold	float	No	The threshold for distinguishing speech from noise, used to adjust the sensitivity of Voice Activity Detection (VAD). Valid values: [-1.0, 1.0]. Value descriptions: The closer the value is to -1: The noise threshold decreases, so noise is more likely to be recognized as speech, which may cause more noise to be transcribed. The closer the value is to +1: The noise threshold increases, so speech is more likely to be misjudged as noise, which may cause some speech to be filtered out. This is an advanced configuration parameter. Adjusting it can significantly affect recognition results. Recommendations: Thoroughly test and verify the results before adjusting. Adjust in small increments based on the actual audio environment (a step of 0.1 is recommended).
  nls_config.special_word_filter	object	No	Specifies the sensitive words to process during speech recognition, and supports setting different processing methods for different sensitive words. For details, see Sensitive word filtering.
  nls_config.enable_connection_fast_check	boolean	No	Whether to quickly detect network outages and report them as soon as possible. Default: false.

Key interfaces

NativeNui

initialize

Initializes a speech recognition SDK instance. The SDK is a singleton. Do not initialize it more than once before you call release.

This method blocks, so call it on a non-UI thread.

• Method signature

public synchronized int initialize(final INativeNuiCallback callback,
                                   String parameters,
                                   final Constants.LogLevel level,
                                   final boolean save_log)

• Parameters

  Parameter	Type	Description
  callback	INativeNuiCallback	The implementation of the event and data callback interface.
  parameters	String	A JSON string that contains the authentication, connection, and debug parameters. See Connection and control parameters.
  level	Constants.LogLevel	Controls the print level of the SDK's own logs.
  save_log	boolean	Whether to save local logs. If set to true, specify the path through debug_path in the Connection and control parameters, and optionally set the file size through max_log_file_size.

• Return value

  An error code. See Error code reference.

setParams

Sets the Speech recognition parameters in JSON format. Call this method before startDialog.

• Method signature

public synchronized int setParams(String params)

• Parameters

  Parameter	Type	Description
  params	String	Speech recognition parameters.

• Return value

  An error code. See Error code reference.

startDialog

Starts recognition.

• Method signature

public synchronized int startDialog(VadMode vad_mode, String dialog_params)

• Parameters

  Parameter	Type	Description
  vad_mode	VadMode	The VAD mode. Fixed to VadMode.TYPE_P2T.
  dialog_params	String	If the apikey parameter in Connection and control parameters uses a temporary API key, you can update it here when it expires. To improve recognition accuracy by using context, update the context here. The content is in JSON format: { "apikey": "st-****", "input_context": [ { "role": "user", "content": [ { "text": "xxxxx", "type": "input_text" } ] } ] }

• Return value

  An error code. See Error code reference.

stopDialog

Ends recognition. After you call this method, the server returns the final recognition result and ends the task.

• Method signature

public synchronized int stopDialog();

• Return value

  An error code. See Error code reference.

cancelDialog

Ends recognition immediately. After you call this method, the task ends at once without waiting for the server to return the final recognition result.

• Method signature

public synchronized int cancelDialog();

• Return value

  An error code. See Error code reference.

updateAction

Sends an action command during an interaction to update runtime behavior, such as recognition context.

• Method signature

public synchronized int updateAction(String params);

• Parameters

  Parameter	Type	Description
  params	String	A JSON string used to update runtime behavior, such as recognition context.
  params.type	String	Set to "action".
  params.command	String	The runtime command. Valid values: context: Immediately updates the context to improve recognition accuracy. play_start: When on-device AEC is used, notifies the SDK that the player has started playing audio. play_over: When on-device AEC is used, notifies the SDK that the player has finished playing audio.
  params.context	String	When command is set to context, immediately updates the context to improve recognition accuracy. The value is a JSON string, as shown in the following example.

{
  "context": [
    {
      "role": "user",
      "content": [
        {
          "text": "xxx",
          "type": "input_text"
        }
      ]
    }
  ]
}

• Return value

  An error code. See Error code reference.

updateAudio

When audio_update_manually is set to "true", call this method to actively push recording data instead of supplying the data through onNuiNeedAudioData.

• Method signature

public synchronized int updateAudio(byte[] data, int len,
                                    boolean first_pack);

• Parameters

  Parameter	Type	Description
  data	byte[]	The audio data to push.
  len	int	The number of bytes of audio data to push.
  first_pack	boolean	Ignore this parameter.

• Return value

  An error code. See Error code reference.

updateRefAudio

When audio_update_manually is set to "true" and on-device AEC is enabled, call this method to push the audio played by the player as the reference signal.

• Method signature

public synchronized int updateRefAudio(byte[] data, int len,
                                       boolean first_pack);

• Parameters

  Parameter	Type	Description
  data	byte[]	The audio data to push.
  len	int	The number of bytes of audio data to push.
  first_pack	boolean	Ignore this parameter.

• Return value

  An error code. See Error code reference.

release

Releases all internal resources of the SDK. After you call this method, the SDK instance becomes unavailable. To use it again, you must reinitialize it by calling initialize.

• Method signature

public synchronized int release();

• Return value

  An error code. See Error code reference.

GetVersion

Gets the current SDK version information.

• Method signature

public synchronized String GetVersion();

• Return value

  The current SDK version information.

INativeNuiCallback: listener callbacks

onNuiEventCallback: listen for events and speech recognition results

• Method signature

void onNuiEventCallback(NuiEvent event, final int resultCode, final int arg2, KwsResult kwsResult, AsrResult asrResult);

• Parameters

  Parameter	Type	Description
  event	NuiEvent	The callback event.
  resultCode	int	The error code. Valid when the EVENT_ASR_ERROR event occurs.
  arg2	int	A reserved parameter.
  asrResult	AsrResult	The speech recognition result.
  kwsResult	KwsResult	The voice wake-up feature. You do not need to use this parameter.

onNuiAudioStateChanged: listen for the audio state

The SDK uses this callback to notify you when to start or stop recording.

• Method signature

void onNuiAudioStateChanged(AudioState state);

• AudioState states

  State	Description
  STATE_OPEN	The interaction has started. You can open the recording device and start recording.
  STATE_PAUSE	The interaction has stopped. You can stop recording.
  STATE_CLOSE	The SDK instance has been released. You can fully close the recording device.

onNuiNeedAudioData: supply the audio data to recognize

After recognition starts, this callback is triggered continuously. Supply the audio data to recognize in this callback.

• Method signature

int onNuiNeedAudioData(byte[] buffer, int len);

• Parameters

  Parameter	Type	Description
  buffer	byte[]	The audio data to fill.
  len	int	The number of bytes of audio data to fill.

• Return value

  The number of bytes actually filled.

onNuiAssistEventCallback: receive auxiliary events and data

This callback receives auxiliary events and related data from the SDK.

• Method signature

void onNuiAssistEventCallback_(int event, byte[] info, int info_len,
                               byte[] data);

• Parameters

  Parameter	Type	Description
  event	int	A NuiEvent event.
  info	String	Ignore this parameter.
  info_len	int	Ignore this parameter.
  data	byte[]	Auxiliary data, such as audio data processed by AEC.

onNuiLogTrackCallback: listen for trace logs

This callback receives detailed internal logs from the SDK to help with troubleshooting and debugging.

default void onNuiLogTrackCallback(Constants.LogLevel level, String log)

NuiEvent: event types

Event	Description
EVENT_TRANSCRIBER_STARTED	The task started successfully.
EVENT_VAD_START	Triggered right after the task starts. This does not mean that the start of speech is detected.
EVENT_VAD_END	The end of speech is detected.
EVENT_ASR_PARTIAL_RESULT	An intermediate speech recognition result.
EVENT_ASR_WARN	A warning that does not interrupt speech recognition occurred, such as a network outage when reconnection is enabled.
EVENT_ASR_ERROR	An error occurred during speech recognition.
EVENT_MIC_ERROR	Triggered when no audio data is received for 2 consecutive seconds.
EVENT_SENTENCE_END	The end of a sentence is detected. A complete recognition result for the sentence is returned.
EVENT_TRANSCRIBER_COMPLETE	Speech recognition has ended.
EVENT_AEC_DATA	Audio data processed by AEC.