New Sign up free, 10 calls on us. Up to $1, no card needed.

Fun-ASR Flash

Released 2026-06

transcription

Fun-ASR Flash is the fast offline variant in Alibaba's Fun-ASR speech recognition family, built for transcribing short recordings of up to five minutes.

Input
audio
Output
text
Price
$0.0021/min

Price in context

Where the price sits among 11 comparable models

Per minute$0.0021/min
$0.002 · Fun-ASR Realtime Chirp 2 · $0.016

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, the same 30-language list as the Fun-ASR main versions: 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
  • Synchronous fast recognition, <=5 min / <=2GB per audio
  • context injection for domain terms
  • 30+ languages
  • no diarization
Speaker diarization No
Streaming transcription Yes

Model

Modalities audio → text

Fast synchronous tier of the Fun-ASR family.

per Alibaba official docs ↗

Use Fun-ASR Flash 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-flash",
    file=open("meeting.mp3", "rb"),
    language="en",
)
print(resp.text)

About Fun-ASR Flash

  • Its distinguishing feature per the official docs is prompt-based context injection: instead of maintaining hotword lists, you supply domain terminology directly in a prompt to steer recognition accuracy.
  • It is the one model in the family documented for this, accepting up to five rounds of context with a few hundred characters each, which fits terminology that shifts per call rather than per project.
  • It keeps the family's broad language coverage, spanning Chinese with regional dialects, English, Japanese, Korean, and many European and Southeast Asian languages.
  • The rest of the trade against the base model is equally concrete: calls are synchronous with streaming results rather than submit-and-poll, so a short clip returns inline instead of through a task id, but the five-minute ceiling replaces the twelve-hour one (the 2 GB file limit stays, so duration is what binds here), and speaker diarization is not available.
  • Read together, the choice within the family is clean: Fun-ASR for long, multi-speaker archives with stable vocabulary, Fun-ASR Flash for short clips that need a fast answer and per-request terminology.
  • On Synthorai it is available through the standard OpenAI-compatible API surface.

FAQ

Is the Fun-ASR Flash 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 Flash against your real workload before adding a payment method.

What is Fun-ASR Flash best at?

Prompt-based context injection instead of hotwords; transcribes short recordings up to five minutes; broad coverage including Chinese regional dialects. See the About section for the full picture from the vendor's own release notes.

How much does Fun-ASR Flash cost?

Fun-ASR Flash costs $0.0021 per minute of audio transcribed on Synthorai: pay-as-you-go, no platform markup, no subscription.

Which languages does Fun-ASR Flash support?

Fun-ASR Flash supports Multilingual with dialects, the same 30-language list as the Fun-ASR main versions: 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 Flash?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="fun-asr-flash", 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.

Get your API key Compare your cost →