Slovak speech-to-text
GoodWe sent 30 Slovak test clips through this API. Whisper Large v3 made 11% word errors, about one word in 9; Parakeet made 10%. $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 | 11% | 3.2% | 6 of 30 | 0 of 30 | 0.075× real time |
Parakeet TDT 0.6B v3nvidia/parakeet-tdt-0.6b-v3 | 10% | 3.4% | 7 of 30 | 0 of 30 | 0.045× real time |
Good. Usable with light review. Expect to correct a word here and there, mostly names and numbers. 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 | Prerušenie spánku je proces, ktorý spočíva v zámernom prebudení sa počas zvyčajnej doby spánku a následnom zaspaní krátko nato (10–60 minút). |
| Whisper Large v3 | Prerušenie spánku je proces, ktorý spočíva v zámernom prebudení sa počas zvyčajnej doby spánku a následnom zaspaní krátko na to 10 až 60 minút. |
| Parakeet (its median clip) | Spoken: Danielle Lantagne, expertka OSN na túto chorobu, uviedla, že za vypuknutie epidémie sú pravdepodobne zodpovedné mierové sily. Danielle Lontane, expertka OSN na túto chorobu, uviedla, že za vypuknutie epidémie sú pravdepodobne zodpovedné mierové síly. |
Language detection
Send language=sk. Of 10 clips sent without it, 9 were identified as Slovak; the others were labelled English (1). When detection is wrong, Whisper writes the transcript in the language it guessed.
Which model for Slovak
Parakeet TDT 0.6B v3 was the more accurate model on these clips (10% against 11%) and it is also the faster one. Start with nvidia/parakeet-tdt-0.6b-v3.
Side by side.
Quickstart
The request is the OpenAI transcription request with a different base URL. language is optional in the API but, as shown above, not optional in practice for Slovak.
curl https://api.inferenceapis.com/v1/audio/transcriptions \
-H "Authorization: Bearer $INFERENCE_API_KEY" \
-F "model=nvidia/parakeet-tdt-0.6b-v3" \
-F "language=sk" \
-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="nvidia/parakeet-tdt-0.6b-v3", file=f, language="sk", 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 Slovak test.
FAQ
How accurate is Whisper for Slovak?
On 30 clean read-speech clips it made 11% word errors, about one word in 9. Usable with light review. Expect to correct a word here and there, mostly names and numbers. Real recordings with noise, accents or several speakers will score worse.
Does language auto-detection work for Slovak?
Mostly. Of 10 clips sent without a language, 9 were identified as Slovak; the rest were labelled English (1). A wrong label means the transcript is written in the wrong language, so always send language=sk.
Whisper or Parakeet for Slovak?
On the same clips Whisper Large v3 scored 11% and Parakeet 10%. Parakeet was more accurate here and is also the faster model, so start with it. Both cost $0.002 per minute.
Can it translate Slovak speech to English?
The API returns Slovak text. For English, transcribe first and translate the text with a chat model on the same key.