Slovenian speech-to-text
FairWe sent 30 Slovenian test clips through this API. Whisper Large v3 made 24% word errors, about one word in 4; Parakeet made 27%. $0.002 per audio minute, word timestamps, SRT and VTT subtitles, files up to 100 MB.
Measured accuracy
| Model | Word error rate | Character error rate | Clips with no errors | Empty transcripts | Speed |
|---|---|---|---|---|---|
Whisper Large v3openai/whisper-large-v3 | 24% | 7.3% | 3 of 30 | 0 of 30 | 0.081× real time |
Parakeet TDT 0.6B v3nvidia/parakeet-tdt-0.6b-v3 | 27% | 10% | 1 of 30 | 0 of 30 | 0.058× real time |
Fair. Gets the content across, but needs a human pass before it is published or quoted. The clips are clean, single-speaker read speech, so treat this as a best case for your own recordings. How we measured, and all 83 languages.
What a transcript looks like
The clip with the median error rate from the test, reference text against what the API returned.
| Spoken | Šok ob vrnitvi se zgodi prej kot kulturni šok (ni tako dolgega obdobja medenih tednov), traja dlje in je lahko resnejši. |
| Whisper Large v3 | Šok ob vrnitvi se zgodi prekot kulturni šok. Ni tako dolgega obdobja med enih tednov, traja dlej in je lahko resnejši. |
| Parakeet (its median clip) | Spoken: Na severu lahko obiščete tudi čudovito Svetišče Marije v Fatimi (sveti kraj), kraj svetovno znanih prikazovanj Marije. Na severu lahko obiščite tudi čudovito svetišče Marije u Fatimi sveti kraj, kraj na svetovno znanih prikazovan Marije. |
Language detection
All 10 clips we sent without a language field were identified as Slovenian. Auto-detection is safe here; sending language=sl still skips the detection step.
Which model for Slovenian
Whisper Large v3 was more accurate on these clips (24% against 27%). Parakeet is faster, which matters mainly on long recordings. Both cost the same. Side by side.
Quickstart
The request is the OpenAI transcription request with a different base URL. language is optional.
curl https://api.inferenceapis.com/v1/audio/transcriptions \
-H "Authorization: Bearer $INFERENCE_API_KEY" \
-F "model=openai/whisper-large-v3" \
-F "language=sl" \
-F "file=@recording.mp3" \
-F "response_format=verbose_json"import os
from openai import OpenAI
client = OpenAI(base_url="https://api.inferenceapis.com/v1", api_key=os.environ["INFERENCE_API_KEY"])
with open("recording.mp3", "rb") as f:
r = client.audio.transcriptions.create(model="openai/whisper-large-v3", file=f, language="sl", response_format="verbose_json")
print(r.text)Subtitles and timestamps
response_format=srt or vtt returns a subtitle file with cues of up to two lines, broken at sentence ends and pauses. verbose_json with timestamp_granularities[]=word returns a start and end time for every word if you want to build your own.
Cost
$0.002 per minute of audio on either model: $0.12 for an hour, $12 for a hundred hours. Duration is measured from the file you upload. There is no daily cap on minutes and no subscription; enough to run your own Slovenian test.
FAQ
How accurate is Whisper for Slovenian?
On 30 clean read-speech clips it made 24% word errors, about one word in 4. Gets the content across, but needs a human pass before it is published or quoted. Real recordings with noise, accents or several speakers will score worse.
Does language auto-detection work for Slovenian?
In our test, yes: all 10 clips sent without a language were identified as Slovenian. Sending language=sl still saves the detection step on every request.
Whisper or Parakeet for Slovenian?
On the same clips Whisper Large v3 scored 24% and Parakeet 27%. Whisper was more accurate here; Parakeet is faster, which matters mainly for long recordings. Both cost $0.002 per minute.
Can it translate Slovenian speech to English?
The API returns Slovenian text. For English, transcribe first and translate the text with a chat model on the same key.