Qwen Audio 3.1 APIs

About Qwen Audio 3.1 APIs

Qwen Audio 3.1 on EmpirioLabs brings together 2 audio generation model APIs from Alibaba Cloud, including Qwen Audio 3.1 Realtime Plus, Qwen Audio 3.1 Realtime Flash. Each model keeps its own dedicated page with live pricing, parameters, docs, and playground access.

Use the same EmpirioLabs API key and endpoint pattern across the family, then switch behavior by changing the model id in your request.

Qwen Audio 3.1 models (2)

Qwen Audio 3.1 Realtime Plus

Duplex speech conversation over one socket, with 88 voices, native web search, tool calling, and separate text and audio token rates.

Qwen Audio 3.1 Realtime Flash

Duplex speech conversation over one socket, with 88 voices, native web search that works alongside tool calling, and separate text and audio token rates.

Qwen Audio 3.1 API pricing

Compare the family at a glance, then open a model page for the complete live rate card and parameters.

How to call Qwen Audio 3.1 models

Qwen Audio 3.1 Realtime Plus holds a live conversation over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-1-realtime-plus, not over the HTTP endpoints. Connect with the model id qwen-audio-3-1-realtime-plus and send your EmpirioLabs API key as an Authorization: Bearer header on the handshake. Audio travels both ways as base64 16-bit PCM. A browser cannot set headers on a WebSocket, so open this connection from your server and relay audio to the browser over your own socket. For this family, swap the model value for any supported id: qwen-audio-3-1-realtime-plus qwen-audio-3-1-realtime-flash. Get an API key from the EmpirioLabs dashboard.

import asyncio, json, os, websockets

async def main():
    async with websockets.connect(
        "wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-1-realtime-plus",
        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.audio.delta":
                ...  # base64 audio chunk, append to your playback buffer
            elif event["type"] == "response.done":
                break

asyncio.run(main())

Qwen Audio 3.1 examples and comparisons

See prompt tests, output notes, and comparison runs that mention this model family.

Guides Qwen Audio 3.1 Realtime Flash vs 3.1 Realtime Plus vs 3.0 Realtime Plus and Flash: one spoken question We asked the four Qwen Audio realtime models the same spoken question over a WebSocket, one shot each. Hear every reply,... API Access How to Use the Qwen Audio 3.1 Realtime Flash API Qwen Audio 3.1 Realtime Flash is a voice conversation model you talk to over a WebSocket, with 88 voices, 14 languages,... Guides Qwen Audio 3.0 ASR vs Qwen Audio 3.1 ASR vs StepAudio 3 ASR Max vs Deepgram Nova-3: one voicemail We gave Qwen Audio 3.0 ASR, Qwen Audio 3.1 ASR, StepAudio 3 ASR Max and Deepgram Nova-3 the same voicemail with a name,...

Qwen Audio 3.1 APIs: common questions

What is the Qwen Audio 3.1 API?

Qwen Audio 3.1 on EmpirioLabs is a family of 2 Audio Generation model APIs from Alibaba Cloud: Qwen Audio 3.1 Realtime Plus, Qwen Audio 3.1 Realtime Flash. You use one EmpirioLabs API key and choose the model id that fits the request.

Which Qwen Audio 3.1 model should I use?

Start with the model whose dedicated page matches your speed, quality, and pricing needs, then test it in the EmpirioLabs playground. The comparison cards above link to each model's live rate card and quickstart.

Can I switch between Qwen Audio 3.1 models without rebuilding my integration?

Yes. The family is designed around the same EmpirioLabs API pattern, so most integrations switch by changing the model value. Check the model page before shipping if you rely on a model-specific parameter.

How is Qwen Audio 3.1 pricing shown?

Pricing is pay as you go. The cards on this page show a short live-catalog summary, and each model page shows the complete rate card that matches API billing.

Can I try Qwen Audio 3.1 in the browser?

Yes. Open any model page in this family and use its playground link to test prompts and parameters in the browser before integrating the API.