> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server. # Qwen3.8 Omni Flash Realtime > 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. ![Qwen3.8 Omni Flash Realtime](https://media.empiriolabs.ai/model-logos/qwen.png) [Alibaba Cloud](/providers/alibaba) · Audio Generation `WEBSOCKET /v1/realtime` 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. ## At a glance | Field | Value | | ------------------- | -------------------------------------------------------------------------------------- | | Model id | `qwen3-8-omni-flash-realtime` | | Model release date | 2026-09-21 | | Input modalities | Audio, Text, Video | | Output modalities | Audio, Text | | Context window | 192K | | Weight precision | - | | Max output tokens | 65,536 | | Region | Singapore | | Features | realtime, speech_to_speech, audio_in, audio_out, video, function_calling, multilingual | | Native inference | No | | New | Yes | | Supported endpoints | `WEBSOCKET /v1/realtime` | | Alternate model ids | `qwen3.8-omni-flash-realtime`, `alibaba/qwen3-8-omni-flash-realtime` | ## Pricing | Charge | Spec | Rate | | ------------- | ----------------------------- | ------ | | Input: audio | per 1M audio input tokens | \$1.86 | | Input | per 1M prompt tokens | \$0.46 | | Output | per 1M generated tokens | \$1.40 | | Output: audio | per 1M generated audio tokens | \$3.74 | ## Example request ```python import asyncio, json, os, websockets URL = "wss://api.empiriolabs.ai/v1/realtime?model=qwen3-8-omni-flash-realtime" 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 | Parameter | Type | Required | Default | Description | | --------------------- | ------ | -------- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `voice` | enum | no | `"Tina"` | Speaking voice for the session. Set it with session.update before the model produces any audio. These voices are specific to this model. · Allowed: `Tina`, `Cindy`, `Liora Mira`, `Raymond`, `Zane`, `Katerina`, `Ryan`, `Mia`, `Cici`, `Theo Calm`, `Serena`, `Maia`, `Evan`, `Qiao`, `Momo`, `Wil`, `Angel`, `Li Cassian`, `Joyner`, `Gold`, `Jennifer`, `Aiden`, `Mione`, `Sunny`, `Dylan`, `Eric`, `Peter`, `Joseph Chen`, `Marcus`, `Li`, `Rocky`, `Kiki`, `Sohee`, `Eliška`, `Alek`, `Arda`, `Dolce`, `Lenn`, `Ono Anna`, `Sonrisa`, `Bodega`, `Andre`, `Radio Gol`, `Rizky`, `Roya`, `Hana`, `Jakub`, `Griet`, `Marina`, `Siiri`, `Ingrid`, `Sigga`, `Bea`, `Chloe`, `Emilien`, `longanlingxin` | | `instructions` | string | no | - | System guidance for how the model should behave and speak during the conversation. | | `modalities` | string | no | `["text", "audio"]` | Which output types the model returns for a turn. Drop audio for a text-only reply. | | `input_audio_format` | enum | no | `"pcm16"` | Encoding of the audio you append to the input buffer: base64 16-bit PCM at 16 kHz. · Allowed: `pcm16` | | `output_audio_format` | enum | no | `"pcm24"` | Encoding of the audio the model streams back: 16-bit PCM at 24 kHz. · Allowed: `pcm24` | | `turn_detection` | string | no | `{"type": "server_vad"}` | Server-side voice activity detection. Decides when you have stopped speaking and the model should reply. It is on by default on this model. | ## Notes **Connecting** 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, and turn detection. **Sending audio and video** * Append microphone audio as `input_audio_buffer.append` events. * Append live video frames as `input_image_buffer.append` events. Frames are not message content, so an image inside a conversation item is rejected. * Voice activity detection decides when you have stopped speaking, so keep streaming for about a second after the speech ends. **Voices** 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. **Billing** 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. --- *Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/qwen3-8-omni-flash-realtime`.