Model Marketplace

Qwen3.8-Omni-Flash-Realtime

Copy success!
Add to Compare

Overview

Qwen3.8-Omni-Flash-Realtime enables full-duplex audio-video interaction through multiple realtime protocols and is designed for smart devices, robotics, and interactive agents. It supports multichannel audio input and various channel layouts. Video representations can be configured from fine-grained to aggregated modes based on the desired balance between accuracy and computational cost. The model supports audio input in over 60 languages and speech output in over 30 languages. Its tool capabilities include function calling and MCP service integration, with a complete event flow covering tool discovery, invocation approval, and tool-result continuation. While delivering fast realtime responses, it can orchestrate complex business logic and work with hundreds of tools, while also offering expressive and diverse voice generation.

Input

TextImageAudioVideo

Output

TextAudio

Features

Prefix Completion

Enable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.View docs

Function Calling

Use function calling to connect large language models with external tools and systems.View docs

Cache

Context Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.View docs

Structured Outputs

Structured Outputs help ensure the model returns a JSON string in the expected format.View docs

Batches

Asynchronously process requests in batches to reduce costs.View docs

Web Search

Enable web search so the model can answer with real-time retrieved data.View docs

Fine-tuning

Train models on sample data to better adapt them to specific tasks.View docs

Pricing

  • Input: Audio
    $0.93Per 1M tokens
  • Input: Text
    $0.7Per 1M tokens
  • Output: Text&Audio (Output text is not charged)
    $1.87Per 1M tokens
  • input：Text/Image/Video
    $0.23Per 1M tokens

Rate Limits

  • TPMTokens Per Minute
    2M
  • RPMRequests Per Minute
    60

API Reference

Call API
Copy success!
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768
# Dependencies: dashscope >= 1.23.9, pyaudio
import os
import base64
import time

import pyaudio
from dashscope.audio.qwen_omni import MultiModality, AudioFormat, OmniRealtimeCallback, OmniRealtimeConversation
import dashscope


url = f'wss://maas.qwencloudapi.com/api-ws/v1/realtime'
# API key: if DASHSCOPE_API_KEY is not set, use: dashscope.api_key = "sk-xxx"
dashscope.api_key = os.getenv('DASHSCOPE_API_KEY')
# Voice
voice = 'Ethan'
# Model
model = 'qwen3.8-omni-flash-realtime'
# Assistant instructions
instructions = (
    "You are Xiaoyun, a personal assistant. Answer the user's questions in a humorous and witty way."
)
class SimpleCallback(OmniRealtimeCallback):
    def __init__(self, pya):
        self.pya = pya
        self.out = None
    def on_open(self):
        # Initialize audio output stream
        self.out = self.pya.open(
            format=pyaudio.paInt16,
            channels=1,
            rate=24000,
            output=True
        )
    def on_event(self, response):
        if response['type'] == 'response.audio.delta':
            # Play audio
            self.out.write(base64.b64decode(response['delta']))
        elif response['type'] == 'conversation.item.input_audio_transcription.completed':
            # Print user transcript
            print(f"[User] {response['transcript']}")
        elif response['type'] == 'response.audio_transcript.done':
            # Print assistant transcript
            print(f"[LLM] {response['transcript']}")

# 1. Initialize audio device
pya = pyaudio.PyAudio()
# 2. Create callback and conversation
callback = SimpleCallback(pya)
conv = OmniRealtimeConversation(model=model, callback=callback, url=url)
# 3. Connect and configure session
conv.connect()
conv.update_session(output_modalities=[MultiModality.AUDIO, MultiModality.TEXT], voice=voice, instructions=instructions)
# 4. Initialize microphone input stream
mic = pya.open(format=pyaudio.paInt16, channels=1, rate=16000, input=True)
# 5. Main loop: stream microphone audio
print("Conversation started. Speak into the microphone (Ctrl+C to exit)...")
try:
    while True:
        audio_data = mic.read(3200, exception_on_overflow=False)
        conv.append_audio(base64.b64encode(audio_data).decode())
        time.sleep(0.01)
except KeyboardInterrupt:
    # Clean up
    conv.close()
    mic.close()
    callback.out.close()
    pya.terminate()
    print("\nConversation ended.")