Qwen3-ASR Flash Realtime is the streaming counterpart of Qwen3-ASR Flash: audio is sent over a WebSocket connection and transcripts return continuously, with unlimited stream duration for long-running sessions.
- Input
- audio
- Output
- text
- Price
- $0.002/min
Price in context
Where the price sits among 11 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Audio
| Languages | 26 languages, one list shared by every Qwen-ASR model: Chinese (Mandarin, Sichuanese, Hokkien, Wu, Cantonese), English, Japanese, German, Korean, Russian, French, Portuguese, Arabic, Italian, Spanish, Hindi, Indonesian, Thai, Turkish, Ukrainian, Vietnamese, Czech, Danish, Filipino, Finnish, Icelandic, Malay, Norwegian, Polish, Swedish |
|---|---|
| Audio limits |
|
| Speaker diarization | No |
| Streaming transcription | Yes |
| Timestamps | No |
Model
| Modalities | audio → text |
|---|
No timestamps/hotwords/diarization on this realtime variant.
Use Qwen3-ASR Flash Realtime in 30 seconds
OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/audio/transcriptions
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.audio.transcriptions.create(
model="qwen3-asr-flash-realtime",
file=open("meeting.mp3", "rb"),
language="en",
)
print(resp.text)import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.audio.transcriptions.create({
model: "qwen3-asr-flash-realtime",
file: fs.createReadStream("meeting.mp3"),
});
console.log(resp.text);curl https://synthorai.io/v1/audio/transcriptions \
-H "Authorization: Bearer sk-syn-..." \
-F model="qwen3-asr-flash-realtime" \
-F file=@meeting.mp3package main
import (
"context"
"fmt"
"os"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
f, _ := os.Open("meeting.mp3")
resp, _ := client.Audio.Transcriptions.New(context.TODO(), openai.AudioTranscriptionNewParams{
Model: "qwen3-asr-flash-realtime",
File: f,
})
fmt.Println(resp.Text)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.audio.transcriptions.*;
import java.nio.file.Paths;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
Transcription resp = client.audio().transcriptions().create(
TranscriptionCreateParams.builder()
.model("qwen3-asr-flash-realtime")
.file(Paths.get("meeting.mp3"))
.build()).asTranscription();
System.out.println(resp.text());About Qwen3-ASR Flash Realtime
- It keeps the batch model's headline capabilities, including emotion detection alongside transcription and recognition across roughly thirty languages, from five Chinese variants through English, Japanese, Korean, and many European and Southeast Asian languages.
- It suits live captioning and voice-interactive applications.
- Two differences from the file-based sibling shape how you build on it.
- First, turn-taking is configurable in a way the other streaming models are not: a voice-activity-detection mode segments utterances automatically using an adjustable silence threshold, while a manual mode hands sentence boundaries to your client by committing the audio buffer yourself, with the documented caveat that manually driven segments must stay within about a minute of accumulated audio.
- Second, the docs state plainly that this variant does not currently return timestamps, so if you need word or sentence timing, the offline model is the one to reach for.
- Emotion recognition remains always-on across the same seven states, language detection stays automatic, and neither hotword lists nor speaker diarization are supported.
- Through Synthorai, the model is reachable via the standard OpenAI-compatible API.
FAQ
Is the Qwen3-ASR Flash Realtime API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. That's enough to try Qwen3-ASR Flash Realtime against your real workload before adding a payment method.
What is Qwen3-ASR Flash Realtime best at?
Unlimited stream duration over WebSocket; keeps emotion detection while streaming; suits live captioning and voice interaction. See the About section for the full picture from the vendor's own release notes.
How much does Qwen3-ASR Flash Realtime cost?
Qwen3-ASR Flash Realtime costs $0.002 per minute of audio transcribed on Synthorai: pay-as-you-go, no platform markup, no subscription.
Which languages does Qwen3-ASR Flash Realtime support?
Qwen3-ASR Flash Realtime supports 26 languages, one list shared by every Qwen-ASR model: Chinese (Mandarin, Sichuanese, Hokkien, Wu, Cantonese), English, Japanese, German, Korean, Russian, French, Portuguese, Arabic, Italian, Spanish, Hindi, Indonesian, Thai, Turkish, Ukrainian, Vietnamese, Czech, Danish, Filipino, Finnish, Icelandic, Malay, Norwegian, Polish, Swedish. On Synthorai you call it through POST /v1/audio/transcriptions, the OpenAI transcription API shape.
How do I get access to Qwen3-ASR Flash Realtime?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="qwen3-asr-flash-realtime", and you're done. One API key covers every model on the gateway.
Related models
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.