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

Fun-ASR vs Fun-ASR Flash

vs

Which one, when — curated verdict, not a benchmark table

Same $0.0021 per audio minute, so pick on shape rather than price: fun-asr is the async file model — up to 12 hours and 2GB, with speaker diarization, hotwords and sentence/word timestamps — while fun-asr-flash answers synchronously, capped at 5 minutes and 2GB, with streaming and domain-term context injection but no diarization or timestamps. The 30-language list is the same on both. Pick fun-asr for recordings, fun-asr-flash for short clips answered in the request.

Pricing

Fun-ASR Fun-ASR Flash Δ
Per audio minute $0.0021 $0.0021 =

Rates from the live catalog at build time; each model page carries the current card.

Where they sit — price per audio minute across all 11 speech-to-text models on this billing unit (log scale)

Fun-ASR · $0.0021 Fun-ASR Flash · $0.0021
$0.002 · Fun-ASR Realtime $0.016 · Chirp 2

Capabilities

Fun-ASR Fun-ASR Flash
Speaker diarization yes no
Streaming no yes
Timestamps yes

Specs

Fun-ASR Fun-ASR Flash
Input modalities audio audio
Output modalities text text
Released 2025-08-22 2026-06
Limits

Async file transcription up to 12h / 2GB

hotwords + speaker diarization

sentence/word timestamps

30+ languages incl. Chinese dialects

Synchronous fast recognition, <=5 min / <=2GB per audio

context injection for domain terms

30+ languages

no diarization

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 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

Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: Fun-ASR · Fun-ASR Flash

Switch between them with one line

Both ids are in every tab below — the highlighted pair of lines is the only edit. Same endpoint, same key, same request shape.

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.audio.transcriptions.create(
    model="fun-asr",
    # model="fun-asr-flash",  # uncomment this line, comment the one above
    file=open("meeting.mp3", "rb"),
    language="en",
)
print(resp.text)

Get an API key →

FAQ

Which is cheaper, Fun-ASR or Fun-ASR Flash?

They list the same per audio minute ($0.0021), so price does not decide this one — see the specs and capabilities below.

Can I A/B test Fun-ASR against Fun-ASR Flash without two integrations?

Yes. Both are served through the same OpenAI-compatible endpoint with one API key — switching is a one-line model-string change, so you can route a fraction of traffic to each and compare bills directly.

Do Fun-ASR and Fun-ASR Flash support speaker diarization?

The capability table above answers this per model, straight from each vendor’s documentation — diarization, streaming and timestamps are listed separately because models differ on all three.

Related comparisons

From our measured studies