Type
Spec
Rate
Input: audio
per 1M audio input tokens
$12.80
Input
per 1M prompt tokens
$1.60
Output
per 1M generated tokens, text-only replies
$12.80
Output: audio
per 1M generated audio tokens
$48.00
Web search
per call when invoked
$0.00
Qwen Audio 3.1 Realtime Plus and Qwen Audio 3.0 Realtime Plus side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Alibaba Cloud Audio GenerationQwen Audio 3.1 Realtime Plus and Qwen Audio 3.0 Realtime Plus are both Alibaba Cloud models in the Audio Generation category, available through the EmpirioLabs API.
| Spec | Qwen Audio 3.1 Realtime Plus | Qwen Audio 3.0 Realtime Plus |
|---|---|---|
| Model ID | qwen-audio-3-1-realtime-plus | qwen-audio-3-0-realtime-plus |
| Author | Alibaba Cloud | Alibaba Cloud |
| Released | Sep 20, 2026 | Aug 10, 2026 |
| Context window | 240K tokens | 16K tokens |
| Max output | 16,384 tokens | 8,192 tokens |
| Input | Audio Text | Audio Text |
| Output | Audio Text | Audio Text |
| Region | Singapore | Singapore |
| Endpoints | WEBSOCKET /v1/realtime | WEBSOCKET /v1/realtime |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Qwen Audio 3.1 Realtime Plus | Qwen Audio 3.0 Realtime Plus |
|---|---|---|
| voice | longanqian_v3.1, longanhuan_v3.1, longanlingxin_v3.1, longanf... Default: longanqian_v3.1 | longanqian, longanlingxin, longanlufeng, longanlingxi, longan... Default: longanqian |
| instructions | string | string |
| input_language | auto, zh, en, ja, ko, vi, th, id, ar, fr, de, es, pt, ru, it Default: auto | - |
| output_language | auto, zh, en, ja, ko, vi, th, id, ar, fr, de, es, pt, ru, it Default: auto | - |
| speed | 0.5 to 2 | 0.5 to 2 |
| enable_speech_emotion | boolean Default: true | boolean Default: true |
| max_history_turns | 1 to 50 | 1 to 50 |
| enable_search | boolean Default: false | boolean Default: false |
| modalities | string Default: ["text","audio"] | string Default: ["text","audio"] |
| input_audio_format | pcm16 Default: pcm16 | pcm16 Default: pcm16 |
| output_audio_format | pcm24 Default: pcm24 | pcm24 Default: pcm24 |
| turn_detection | string Default: {"type":"server_vad"} | string Default: {"type":"server_vad"} |
Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-1-realtime-plus, authenticated with the ordinary Authorization Bearer header. Configure the session with session.update over the socket: voice, instructions, modalities, turn detection, languages and delivery.
Set input_language to the language you speak, which the transcript of your speech is written in, and output_language to the language the spoken reply is read in. Each takes auto or one of zh, en, ja, ko, vi, th, id, ar, fr, de, es, pt, ru and it. The output language does not translate the reply, so ask for its language in your instructions too. speed (0.5 to 2) sets the speaking rate, enable_speech_emotion the expressive delivery, and max_history_turns (1 to 50) how many earlier exchanges the model reads.
The voices on this model are its own set. Pick one from the voice list rather than carrying a voice across from another model, or leave it unset and the default is supplied for you.
Web search is off by default. Turn it on with enable_search. It cannot be enabled in the same session as function calling, and search results are added to the conversation and count as input tokens.
Audio and text tokens are priced separately in both directions. A spoken reply is billed for its audio output tokens only, and the text output rate applies to replies with no audio. Each completed turn is billed on its own from the usage the model reports.
Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen-audio-3-0-realtime-plus, authenticated with the ordinary Authorization Bearer header. Configure the session with session.update over the socket: voice, instructions, modalities, turn detection and delivery.
speed (0.5 to 2) sets the speaking rate, enable_speech_emotion the expressive delivery, and max_history_turns (1 to 50) how many earlier exchanges the model reads. Ask for the reply's language in your instructions.
The voices on this model are its own set. Pick one from the voice list rather than carrying a voice across from another model, or leave it unset and the default is supplied for you.
Web search is off by default. Turn it on with enable_search. It cannot be enabled in the same session as function calling, and search results are added to the conversation and count as input tokens.
Audio and text tokens are priced separately in both directions. A spoken reply is billed for its audio output tokens only, and the text output rate applies to replies with no audio. Each completed turn is billed on its own from the usage the model reports.
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. Both models are called through the same endpoint. Set model to qwen-audio-3-1-realtime-plus or qwen-audio-3-0-realtime-plus. 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())Prompt tests and comparison runs that cover both models.
Qwen Audio 3.1 Realtime Plus is the newer release (Sep 20, 2026); Qwen Audio 3.0 Realtime Plus was released on Aug 10, 2026. Qwen Audio 3.1 Realtime Plus has the larger context window: 240K tokens, against 16K for Qwen Audio 3.0 Realtime Plus. Qwen Audio 3.1 Realtime Plus returns up to 16,384 output tokens per response, Qwen Audio 3.0 Realtime Plus up to 8,192. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Qwen Audio 3.1 Realtime Plus is the newer release (Sep 20, 2026); Qwen Audio 3.0 Realtime Plus was released on Aug 10, 2026.
Both models list the same rate for Input: audio (per 1M audio input tokens) and Input (per 1M prompt tokens). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use WEBSOCKET /v1/realtime with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and press Start session to try it in your browser.
Check out our pricing or reach out if you want your own model deployed on our stack.
