Alibaba (Qwen) / qwen3-asr-flash-realtime

Qwen3 ASR Flash Realtime

Qwen3 ASR Flash Realtime handles speech recognition or audio understanding for transcription, captions, and realtime voice apps.

Speech to text

Context

tokens

Input

$0.00012

/ second

Output

$0.00012

/ second

Quality

#56

Elo 1131

Overview

What this model is good for

Qwen3 ASR Flash Realtime handles speech recognition or audio understanding for transcription, captions, and realtime voice apps.

Model capabilities

Audio input

Can process audio input as part of speech or multimodal workflows.

Streaming

Supports streamed responses for chat, assistants, and interfaces that need visible incremental output.

Model maker

Model maker and access

This section shows the model maker, SeaLink model ID, protocol, and pricing information.

Alibaba (Qwen)

Called through SeaLink's unified account, balance, and OpenAI-compatible API.

Protocol

Audio API

Base URL: https://test.sealink.io/v1

Pricing

Pricing and cost sense

Prices come from the current model catalog. Simple estimates help users judge whether the model fits production volume.

Input$0.00012/ second

Output$0.00012/ second

Actual billing follows usage logs and billing records; caching and media pricing depend on the endpoint.

API

Copy into your code

The model page should make it clear which model to copy, which base URL to use, and where to get an API Key.

model

qwen3-asr-flash-realtime

base_url

https://test.sealink.io/v1

Auth

Bearer $SEALINK_API_KEY

cURL

curl https://test.sealink.io/v1/audio/transcriptions \
  -H "Authorization: Bearer $SEALINK_API_KEY" \
  -F model="qwen3-asr-flash-realtime" \
  -F file_url="https://example.com/audio.mp3"

Python (OpenAI SDK)

import requests

resp = requests.post(
    "https://test.sealink.io/v1/audio/transcriptions",
    headers={"Authorization": "Bearer <your-sealink-key>"},
    data={"model": "qwen3-asr-flash-realtime", "file_url": "https://example.com/audio.mp3"},
)
resp.raise_for_status()
print(resp.json()["text"])

Node.js (OpenAI SDK)

const form = new FormData();
form.append("model", "qwen3-asr-flash-realtime");
form.append("file_url", "https://example.com/audio.mp3");

const resp = await fetch("https://test.sealink.io/v1/audio/transcriptions", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.SEALINK_API_KEY}` },
  body: form,
});
console.log((await resp.json()).text);