Alibaba Cloud Model Studio:Qwen-ASR-Realtime Python SDK - API リファレンス

from dashscope.audio.qwen_omni import OmniRealtimeConversation, OmniRealtimeCallback

class MyCallback(OmniRealtimeCallback):
    """リアルタイム認識用コールバック"""
    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',
        # 以下の URL は中国本土向けです。中国本土以外のリージョンでは、
        # wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime を使用してください。
        url='wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/realtime',
        callback=MyCallback(conversation=None)  # 一時的に None を渡し、後で注入します。
    )
# コールバックに自身を注入します。
conversation.callback.conversation = conversation

from dashscope.audio.qwen_omni import TranscriptionParams, MultiModality

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"
)