Qwen-Audio-3.0-ASR-Flash-Streaming/Fun-ASR real-time speech recognition Android SDK guide

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. In the onNuiNeedAudioData callback, continuously supply recording data.

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.

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	The service address. Fixed to wss://dashscope.aliyuncs.com/api-ws/v1/inference.
  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.
  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.

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": {
              "speech_noise_threshold": 0.0
          }
      }
  }

• 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 wav mp3 opus speex aac amr Important opus/speex: Must use Ogg encapsulation. wav: Must use PCM encoding. amr: Only the AMR-NB type is supported.
  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.
  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	Important Takes 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): The connection is disconnected due to timeout after 60 seconds, even if silent audio is sent continuously. 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.parameters.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 configured together with precompiled hot words, only the instant hot words take effect. For usage details, see Instant hotwords. Important Only 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
  nls_config.parameters	object	No	Additional parameters, in JSON object format.
  nls_config.parameters.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.parameters.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.

NativeNui

INativeNuiCallback: listener callbacks

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

NuiEvent: event types