Qwen-ASR realtime Python SDK

from dashscope.audio.qwen_omni import OmniRealtimeConversation, OmniRealtimeCallback

class MyCallback(OmniRealtimeCallback):
  """Callback for real-time recognition"""
  def __init__(self, conversation):
    self.conversation = conversation
    self.handlers = {
      'session.created': self._handle_session_created,
      'conversation.item.input_audio_transcription.completed': self._handle_final_text,
      'conversation.item.input_audio_transcription.text': self._handle_stash_text,
      'input_audio_buffer.speech_started': lambda r: print('======Speech Start======'),
      'input_audio_buffer.speech_stopped': lambda r: print('======Speech Stop======')
    }

  def on_open(self):
    print('Connection opened')

  def on_close(self, code, msg):
    print(f'Connection closed, code: {code}, msg: {msg}')

  def on_event(self, response):
    try:
      handler = self.handlers.get(response['type'])
      if handler:
        handler(response)
    except Exception as e:
      print(f'[Error] {e}')

  def _handle_session_created(self, response):
    print(f"Start session: {response['session']['id']}")

  def _handle_final_text(self, response):
    print(f"Final recognized text: {response['transcript']}")

  def _handle_stash_text(self, response):
    print(f"Got stash result: {response['stash']}")

conversation = OmniRealtimeConversation(
    model='qwen3-asr-flash-realtime',
    url='wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime',
    callback=MyCallback(conversation=None)  # Temporarily pass None and inject it later.
  )
# Inject self into the callback.
conversation.callback.conversation = conversation

from dashscope.audio.qwen_omni import MultiModality
from dashscope.audio.qwen_omni.omni_realtime import TranscriptionParams

transcription_params = TranscriptionParams(
  language='zh',
  sample_rate=16000,
  input_audio_format="pcm"
)

conversation.update_session(
  output_modalities=[MultiModality.TEXT],
  enable_turn_detection=True,
  turn_detection_type="server_vad",
  turn_detection_threshold=0.0,
  turn_detection_silence_duration_ms=400,
  enable_input_audio_transcription=True,
  transcription_params=transcription_params
)

transcription_params = TranscriptionParams(
  language='zh',
  sample_rate=16000,
  input_audio_format="pcm"
)