Speech and live video frames in, speech out over one socket, with 56 voices, tool calling during the conversation, and separate text and audio token rates.
Alibaba Cloud Audio Generation 192K context Released Sep 21, 2026 Singapore Proprietary Endpoint NewSpeech and live video frames in, speech out over one socket, with 56 voices, tool calling during the conversation, and separate text and audio token rates.
Session is configured with session.update events over the socket rather than request parameters. Text and audio tokens bill at separate rates.
Also known as Alibaba Cloud Qwen3.8 Omni Flash Realtime
qwen3-8-omni-flash-realtime/v1/realtimeqwen3.8-omni-flash-realtimealibaba/qwen3-8-omni-flash-realtimeLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Qwen3.8 Omni Flash Realtime holds a live conversation over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen3-8-omni-flash-realtime, not over the HTTP endpoints. Connect with the model id qwen3-8-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=qwen3-8-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 Qwen3.8 Omni Flash Realtime API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| voice | enum | Tina | Tina, Cindy, Liora Mira, Raymond, Zane, Katerina, Ryan, Mia, ... | Speaking voice for the session. Set it with session.update before the model produces any audio. These voices are specific to this model. |
| 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 | pcm16 | pcm16 | Encoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz. |
| output_audio_format | enum | pcm24 | pcm24 | Encoding of the audio the model streams back: 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. |
| video_representation_compact | enum | - | none, normal | How the model reads the video frames you send: none keeps full detail, and normal reads the same frames for a quarter of the input tokens when fine detail is not... |
Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen3-8-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.
The voices on this model are not the same set as the Qwen3.5 Omni realtime models. Pick one from the voice list rather than carrying a voice across, or leave it unset and the default is supplied for you.
Audio and text tokens are priced separately in both directions, and each completed turn is billed on its own from the usage the model reports.
On EmpirioLabs, Qwen3.8 Omni Flash Realtime is billed pay as you go: Input: audio $1.86 per 1M audio input tokens; Input $0.46 per 1M prompt tokens; Output $1.40 per 1M generated tokens; Output: audio $3.74 per 1M generated audio tokens. The live rate card on this page always matches what the API charges.
Qwen3.8 Omni Flash Realtime supports a 192K-token context window with up to 65,536 output tokens per response.
Qwen3.8 Omni Flash Realtime is served through WEBSOCKET /v1/realtime on api.empiriolabs.ai with standard bearer-token authentication.
Open the EmpirioLabs playground and press Start session to try it in your browser. Qwen3.8 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 qwen3-8-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.
Check out our pricing or reach out if you want your own model deployed on our stack.
