リアルタイム音声・動画翻訳 - Qwen

# pip install websocket-client
import json
import websocket
import os

API_KEY=os.getenv("DASHSCOPE_API_KEY")
API_URL = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime?model=qwen3.8-livetranslate-flash-realtime"

headers = [
    "Authorization: Bearer " + API_KEY
]

def on_open(ws):
    print(f"サーバーに接続しました: {API_URL}")
def on_message(ws, message):
    data = json.loads(message)
    print("受信したイベント:", json.dumps(data, indent=2))
def on_error(ws, error):
    print("エラー:", error)

ws = websocket.WebSocketApp(
    API_URL,
    header=headers,
    on_open=on_open,
    on_message=on_message,
    on_error=on_error
)

ws.run_forever()

import base64
import json
import os
import signal
import threading
import time

import pyaudio
import websocket

model = "qwen3.8-livetranslate-flash-realtime"
api_key = os.environ["DASHSCOPE_API_KEY"]
url = (
    "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com"
    f"/api-ws/v1/realtime?model={model}"
)
stop_recording = False
send_errors = []
ws = None
audio = None
input_stream = None
output_stream = None
sender = None
previous_sigint_handler = None


def receive():
    event = json.loads(ws.recv())
    if event.get("type") == "error" or event.get("code"):
        raise RuntimeError(event)
    return event


def stop_input(signum, frame):
    global stop_recording
    stop_recording = True


def send_audio():
    try:
        while not stop_recording:
            chunk = input_stream.read(1600)
            ws.send(json.dumps({
                "type": "input_audio_buffer.append",
                "audio": base64.b64encode(chunk).decode("ascii"),
            }))
    except Exception as error:
        send_errors.append(error)
    finally:
        try:
            ws.send(json.dumps({"type": "session.finish"}))
        except Exception as error:
            send_errors.append(error)
            ws.close()


def receive_translation():
    while True:
        event = receive()
        event_type = event.get("type")
        if event_type in ("response.text.delta", "response.audio_transcript.delta"):
            print(event["delta"], end="", flush=True)
        elif event_type == "response.audio.delta":
            output_stream.write(base64.b64decode(event["delta"]))
        elif event_type == "response.done":
            if event["response"]["status"] != "completed":
                raise RuntimeError(event["response"])
            print()
        elif event_type == "session.finished":
            return


try:
    ws = websocket.create_connection(
        url, header={"Authorization": f"Bearer {api_key}"}, timeout=30
    )
    while receive().get("type") != "session.created":
        pass
    ws.send(json.dumps({
        "type": "session.update",
        "session": {
            "output_modalities": ["text", "audio"],
            "translation": {"language": "en"},
        },
    }))
    while receive().get("type") != "session.updated":
        pass
    audio = pyaudio.PyAudio()
    input_stream = audio.open(
        format=pyaudio.paInt16, channels=1, rate=16000,
        input=True, frames_per_buffer=1600,
    )
    output_stream = audio.open(
        format=pyaudio.paInt16, channels=1, rate=24000, output=True,
    )
    print("話し始めてください。Ctrl+C で録音を停止し、残りの翻訳を待ちます。")
    previous_sigint_handler = signal.signal(signal.SIGINT, stop_input)
    sender = threading.Thread(target=send_audio, daemon=True)
    sender.start()
    receive_translation()
    stop_recording = True
    sender.join()
    if send_errors:
        raise send_errors[0]
except Exception:
    if send_errors:
        raise send_errors[0]
    raise
finally:
    stop_recording = True
    if ws is not None:
        ws.close()
    if sender is not None:
        sender.join()
    for stream in (input_stream, output_stream):
        if stream is not None:
            stream.stop_stream()
            stream.close()
    if audio is not None:
        audio.terminate()
    if previous_sigint_handler is not None:
        signal.signal(signal.SIGINT, previous_sigint_handler)

speaker_by_source = {}
source_by_translation = {}
source_text = {}
translation_text = {}


def show_subtitle(translation_id):
    source_id = source_by_translation.get(translation_id)
    if source_id not in speaker_by_source or translation_id not in translation_text:
        return
    print({
        "speaker_id": speaker_by_source[source_id],
        "source": source_text.get(source_id, ""),
        "translation": translation_text[translation_id],
    })


def handle_speaker_event(event):
    event_type = event.get("type")
    if event_type in ("response.text.delta", "response.audio_transcript.delta"):
        item_id = event["item_id"]
        translation_text[item_id] = translation_text.get(item_id, "") + event["delta"]
        show_subtitle(item_id)
        return
    if event_type == "conversation.item.created":
        item = event["item"]
        if any(part.get("type") == "input_audio" for part in item.get("content", [])):
            return
        source_id = event.get("previous_item_id")
        if item.get("role") == "assistant" and source_id is not None:
            source_by_translation[item["id"]] = source_id
            show_subtitle(item["id"])
        return
    if event_type == "input_audio_buffer.speech_started" and "speaker_id" in event:
        source_id = event["item_id"]
        speaker_by_source[source_id] = event["speaker_id"]
    elif event_type == "conversation.item.input_audio_transcription.delta":
        source_id = event["item_id"]
        source_text[source_id] = source_text.get(source_id, "") + event["delta"]
    elif event_type == "conversation.item.input_audio_transcription.completed":
        source_id = event["item_id"]
        source_text[source_id] = event["transcript"]
    else:
        return
    for translation_id, mapped_source in source_by_translation.items():
        if mapped_source == source_id:
            show_subtitle(translation_id)

import io
from PIL import Image

IMAGE_PATH = "medical-mask.png"
# IMAGE_PATH = "masquerade-mask.png"
with Image.open(IMAGE_PATH) as image:
    buffer = io.BytesIO()
    image.convert("RGB").save(buffer, format="JPEG")
image_bytes = buffer.getvalue()
if len(image_bytes) > 500_000:
    raise ValueError("JPEG > 500 KB")
image_b64 = base64.b64encode(image_bytes).decode("ascii")


def send_audio():
    try:
        last_image_time = None
        while not stop_recording:
            chunk = input_stream.read(1600)
            ws.send(json.dumps({
                "type": "input_audio_buffer.append",
                "audio": base64.b64encode(chunk).decode("ascii"),
            }))
            now = time.monotonic()
            if last_image_time is None or now - last_image_time >= 0.5:
                ws.send(json.dumps({
                    "type": "input_image_buffer.append",
                    "image": image_b64,
                }))
                last_image_time = now
    except Exception as error:
        send_errors.append(error)
    finally:
        try:
            ws.send(json.dumps({"type": "session.finish"}))
        except Exception as error:
            send_errors.append(error)
            ws.close()