Qwen Audio 3.1 ASR Message

Alibaba Cloud · Transcription

WEBSOCKET /v1/realtime

Transcription tuned for voice messages and voice input over a socket, returning each utterance as one complete transcript when the speaker pauses.

At a glance

Pricing

Example request

import asyncio, json, os, websockets
URL = "wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-1-asr-message"
async def main():
    async with websockets.connect(
        URL,
        additional_headers=[("Authorization", f"Bearer {os.environ['EMPIRIOLABS_API_KEY']}")],
        max_size=None,
    ) as ws:
        print(json.loads(await ws.recv())["type"])  # session.created
        await ws.send(json.dumps({
            "type": "conversation.item.create",
            "item": {"type": "message", "role": "user",
                     "content": [{"type": "input_text", "text": "Say hello."}]},
        }))
        await ws.send(json.dumps({"type": "response.create"}))
        async for raw in ws:
            event = json.loads(raw)
            if event["type"] == "response.done":
                break
asyncio.run(main())

Parameters

Notes

Connecting

Voice message transcription over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-1-asr-message, authenticated with the ordinary Authorization Bearer header.

Sending audio

Stream 16 kHz mono pcm16 audio with input_audio_buffer.append. Voice activity detection decides where each utterance ends, so there is no commit to send.

What comes back

Each utterance arrives whole, as one conversation.item.input_audio_transcription.completed event once the speaker pauses. This model does not send partial results while the speaker is talking; for live captions, use qwen-audio-3-1-asr-stream.

Billing

Input and output tokens are priced per 1M, and each completed utterance is billed on its own from the usage the model reports.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/qwen-audio-3-1-asr-message.