
Speech in, speech out, over one socket, with separate text and audio token rates and per-turn billing.
Speech in, speech out, over one socket, 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 Alibaba Cloud Qwen3.5 Omni Flash Realtime
qwen3-5-omni-flash-realtime/v1/realtimeqwen3.5-omni-flash-realtimealibaba/qwen3-5-omni-flash-realtimeLive pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.
Qwen3.5 Omni Flash Realtime holds a live conversation over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen3-5-omni-flash-realtime, not over the HTTP endpoints. Connect with the model id qwen3-5-omni-flash-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.
import asyncio, json, os, websockets
async def main():
async with websockets.connect(
"wss://api.empiriolabs.ai/v1/realtime?model=qwen3-5-omni-flash-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())Request parameters supported by the Qwen3.5 Omni Flash Realtime API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| voice | enum | Tina | Tina, Serena, Ethan, Dylan, Sunny, Peter, Kiki, Eric | Speaking voice for the session. Set it with session.update before the model produces any audio. |
| instructions | string | - | - | System guidance for how the model should behave and speak during the conversation. |
| modalities | string | ["text","audio"] | - | Which output types the model returns for a turn. Drop "audio" for a text-only reply. |
| input_audio_format | enum | pcm | pcm | Encoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz. |
| output_audio_format | enum | pcm | pcm | Encoding of the audio the model streams back: base64 16-bit PCM at 24 kHz. |
| turn_detection | string | {"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_tokens | number | - | 1 to 65536 | Largest 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... |
| temperature | number | - | 0 to 1.99 | Sampling temperature. 0 is deterministic and 1.99 is maximum randomness. When omitted, the model's own default applies. |
| top_p | number | - | 0.01 to 1 | Nucleus sampling probability mass. Lower values make outputs more focused. When omitted, the model's own default applies. |
| top_k | integer | - | 1 to 100 | Sample only from the K most likely tokens. When omitted, the model's own default applies. |
| repetition_penalty | number | - | 0.1 to 2 | Higher values discourage repeated phrasing, and 1 applies no penalty. When omitted, the model's own default applies. |
| presence_penalty | number | - | -2 to 2 | Penalty for tokens that already appeared in the generated text. Positive values encourage new topics. When omitted, the model's own default applies. |
| seed | integer | - | 0 to 2147483647 | Random seed for more reproducible sampling. Reusing a seed with the same request returns similar, not always identical, output. |
Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen3-5-omni-flash-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. 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.
On EmpirioLabs, Qwen3.5 Omni Flash Realtime is billed pay as you go: Input: audio $9.00 per 1M audio input tokens; Input $1.10 per 1M prompt tokens; Output $6.60 per 1M generated tokens, text-only replies; Output: audio $35.40 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.
Qwen3.5 Omni Flash Realtime takes Audio, Text, Image, Video as input and returns Audio, Text.
Qwen3.5 Omni Flash Realtime supports a 192K-token context window with up to 65,536 output tokens per response.
Qwen3.5 Omni Flash Realtime is served through WEBSOCKET /v1/realtime on api.empiriolabs.ai with standard bearer-token authentication.
Send qwen3-5-omni-flash-realtime as the model in your request. The alternate IDs qwen3.5-omni-flash-realtime, alibaba/qwen3-5-omni-flash-realtime also work.
Qwen3.5 Omni Flash Realtime on EmpirioLabs is served from Singapore.
Open the EmpirioLabs playground and press Start session to try it in your browser. Qwen3.5 Omni Flash 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-flash-realtime, then stream audio in both directions.
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.
Check out our pricing or reach out if you want your own model deployed on our stack.