Qwen3.5 Omni Plus Realtime API

Speech in, speech out, over one socket, on the larger Omni tier, with separate text and audio token rates and per-turn billing.

Alibaba Cloud Audio Generation 192K context Singapore Proprietary Endpoint

About Qwen3.5 Omni Plus Realtime

Speech in, speech out, over one socket, on the larger Omni tier, with separate text and audio token rates and per-turn billing.

Session is configured with session.update events over the socket rather than request parameters. Text and audio tokens bill at separate rates, and a spoken reply bills its audio tokens only.

Also known as Qwen3.5 Omni Realtime, Alibaba Cloud Qwen3.5 Omni Plus Realtime

realtime speech to speech audio in audio out video function calling multilingual

Qwen3.5 Omni Plus Realtime specs

Model ID
qwen3-5-omni-plus-realtime
Author
Alibaba Cloud
Category
Audio Generation
Released
-
Context window
192K tokens
Max output
65,536 tokens
Input
AudioTextImageVideo
Output
AudioText
Region
Singapore
Endpoints
WEBSOCKET/v1/realtime
Alternate model IDs
qwen3.5-omni-plus-realtimealibaba/qwen3-5-omni-plus-realtime

Qwen3.5 Omni Plus Realtime API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.

Type
Spec
Rate
Input: audio
per 1M audio input tokens
$33.00
Input
per 1M prompt tokens
$4.20
Output
per 1M generated tokens, text-only replies
$24.80
Output: audio
per 1M generated audio tokens
$124.00
Compare on the full pricing page

How to call the Qwen3.5 Omni Plus Realtime API

Qwen3.5 Omni Plus Realtime holds a live conversation over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen3-5-omni-plus-realtime, not over the HTTP endpoints. Connect with the model id qwen3-5-omni-plus-realtime 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. Get an API key from the EmpirioLabs dashboard.

Python (websockets)
import asyncio, json, os, websockets

async def main():
    async with websockets.connect(
        "wss://api.empiriolabs.ai/v1/realtime?model=qwen3-5-omni-plus-realtime",
        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())
Full Qwen3.5 Omni Plus Realtime API reference

Qwen3.5 Omni Plus Realtime API parameters

Request parameters supported by the Qwen3.5 Omni Plus Realtime API on EmpirioLabs. Defaults apply when a field is omitted.

ParameterTypeDefaultRange / valuesDescription
voiceenumTinaTina, Serena, Ethan, Dylan, Sunny, Peter, Kiki, EricSpeaking voice for the session. Set it with session.update before the model produces any audio.
instructionsstring--System guidance for how the model should behave and speak during the conversation.
modalitiesstring["text","audio"]-Which output types the model returns for a turn. Drop "audio" for a text-only reply.
input_audio_formatenumpcmpcmEncoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz. With the beta version of the protocol, set session.audio.input.format before the...
output_audio_formatenumpcmpcmEncoding of the audio the model streams back: base64 16-bit PCM at 24 kHz. With the beta version of the protocol, set session.audio.output.format before the first...
turn_detectionstring{"type":"server_vad"}-Voice activity detection: decides when you have finished speaking and the model should reply. It is on by default as server_vad, which ends your turn after a pause....
max_response_output_tokensnumber-1 to 65536Largest number of output tokens one reply may use: from 1 to 65536, where a larger number runs at 65536, or "inf" for the model's own limit. Also accepted as...
temperaturenumber-0 to 1.99Sampling temperature. 0 is deterministic and 1.99 is maximum randomness. When omitted, the model's own default applies.
top_pnumber-0.01 to 1Nucleus sampling probability mass. Lower values make outputs more focused. When omitted, the model's own default applies.
top_kinteger-1 to 100Sample only from the K most likely tokens. When omitted, the model's own default applies.
repetition_penaltynumber-0.1 to 2Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies.
presence_penaltynumber--2 to 2Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies.
seedinteger-0 to 2147483647Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output.

Good to know

Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen3-5-omni-plus-realtime, authenticated with the ordinary Authorization Bearer header. Configure the session with session.update over the socket: voice, instructions, modalities, turn detection, sampling and the reply length limit, max_response_output_tokens. Send camera or video frames as JPEG images with input_image_buffer.append, after the first audio. For WAV or another sample rate with the beta version of the protocol, set session.audio.input.format and session.audio.output.format before the first audio. This model's voices differ from the earlier Omni generation, so set one it accepts or leave the default; an unknown voice ends the session rather than returning an error. Text and audio tokens are priced separately, a spoken reply is billed for its audio output tokens only, and each completed turn is billed on its own from the usage the model reports.

Qwen3.5 Omni Plus Realtime API: common questions

How much does the Qwen3.5 Omni Plus Realtime API cost?

On EmpirioLabs, Qwen3.5 Omni Plus Realtime is billed pay as you go: Input: audio $33.00 per 1M audio input tokens; Input $4.20 per 1M prompt tokens; Output $24.80 per 1M generated tokens, text-only replies; Output: audio $124.00 per 1M generated audio tokens. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.

What inputs and outputs does Qwen3.5 Omni Plus Realtime support?

Qwen3.5 Omni Plus Realtime takes Audio, Text, Image, Video as input and returns Audio, Text.

What is the context window of Qwen3.5 Omni Plus Realtime?

Qwen3.5 Omni Plus Realtime supports a 192K-token context window with up to 65,536 output tokens per response.

Which endpoint does Qwen3.5 Omni Plus Realtime use?

Qwen3.5 Omni Plus Realtime is served through WEBSOCKET /v1/realtime on api.empiriolabs.ai with standard bearer-token authentication.

What is the model ID for Qwen3.5 Omni Plus Realtime?

Send qwen3-5-omni-plus-realtime as the model in your request. The alternate IDs qwen3.5-omni-plus-realtime, alibaba/qwen3-5-omni-plus-realtime also work.

Where is Qwen3.5 Omni Plus Realtime served from?

Qwen3.5 Omni Plus Realtime on EmpirioLabs is served from Singapore.

Can I try Qwen3.5 Omni Plus Realtime in the browser before integrating?

Open the EmpirioLabs playground and press Start session to try it in your browser. Qwen3.5 Omni Plus Realtime runs over a WebSocket rather than a request and response, so to build with it start from the realtime voice quickstart. Connect from your server with your EmpirioLabs API key and the model id qwen3-5-omni-plus-realtime, then stream audio in both directions.

How do I get a Qwen3.5 Omni Plus Realtime API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make. You can also choose a plan with weekly allowances.

Compare Qwen3.5 Omni Plus Realtime with other models

All model comparisons

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.