Fun-ASR Realtime is Alibaba's streaming speech recognition model: audio is streamed in over a persistent connection and text is streamed back with low latency, with no cap on stream duration.
- 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 | Multilingual with dialects, 30 languages: Chinese (Mandarin, Cantonese, Wu, Hokkien, Hakka, Gan, Xiang, Jin plus regional accents), English, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Hindi, Arabic, French, German, Spanish, Portuguese, Russian, Italian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Polish, Czech, Hungarian, Romanian, Bulgarian, Croatian, Slovak |
|---|---|
| Audio limits |
|
| Speaker diarization | No |
| Streaming transcription | Yes |
| Timestamps | Yes |
Model
| Modalities | audio → text |
|---|
Docs also describe 7-state emotion recognition on the realtime guide.
Use Fun-ASR 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="fun-asr-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: "fun-asr-realtime",
file: fs.createReadStream("meeting.mp3"),
});
console.log(resp.text);curl https://synthorai.io/v1/audio/transcriptions \
-H "Authorization: Bearer sk-syn-..." \
-F model="fun-asr-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: "fun-asr-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("fun-asr-realtime")
.file(Paths.get("meeting.mp3"))
.build()).asTranscription();
System.out.println(resp.text());About Fun-ASR Realtime
- The official docs position it for live captions, voice assistants, and meeting transcription, and it carries the Fun-ASR family's strengths of hotword customization plus multilingual coverage including Chinese regional dialects, English, Japanese, and Korean.
- The realtime surface adds controls the file-based models do not need: semantic punctuation, punctuation prediction on by default, an adjustable maximum sentence silence that decides when an utterance is closed, a speech-noise threshold for tuning against background sound, and word-level timestamps emitted as the stream runs.
- Audio arrives as PCM, WAV, MP3, Opus, Speex, AAC or AMR at 8 or 16 kHz.
- Two limits are worth designing around: speaker diarization is not available on the realtime path (for who-said-what you need the recording-file models), and language coverage varies sharply by dated snapshot rather than being uniform across the family, so pin the snapshot your language set depends on.
- Emotion labelling, the Qwen3-ASR line's differentiator, is not offered here either, and context-based accuracy tuning is available only on some snapshots.
- Synthorai makes it callable through the same OpenAI-compatible interface used for the rest of its audio catalog.
FAQ
Is the Fun-ASR 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 Fun-ASR Realtime against your real workload before adding a payment method.
What is Fun-ASR Realtime best at?
Streaming transcription with no duration cap; built for live captions and meetings; hotword customization with multilingual coverage. See the About section for the full picture from the vendor's own release notes.
How much does Fun-ASR Realtime cost?
Fun-ASR Realtime costs $0.002 per minute of audio transcribed on Synthorai: pay-as-you-go, no platform markup, no subscription.
Which languages does Fun-ASR Realtime support?
Fun-ASR Realtime supports Multilingual with dialects, 30 languages: Chinese (Mandarin, Cantonese, Wu, Hokkien, Hakka, Gan, Xiang, Jin plus regional accents), English, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Hindi, Arabic, French, German, Spanish, Portuguese, Russian, Italian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Polish, Czech, Hungarian, Romanian, Bulgarian, Croatian, Slovak. On Synthorai you call it through POST /v1/audio/transcriptions, the OpenAI transcription API shape.
How do I get access to Fun-ASR Realtime?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="fun-asr-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.