Hebrew speech-to-text
FairWe sent 30 Hebrew test clips through this API. Whisper Large v3 made 28% word errors, about one word in 4. $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 | 28% | 14% | 2 of 30 | 0 of 30 | 0.087× 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 | סולטאן מרוקו בנה את העיר מחדש בתור דאר אל-ביידא והיא קיבלה את השם קזבלנקה מסוחרים ספרדים שהקימו בה מרכזי סחר. |
| Whisper Large v3 | סולטן מרוקו בנה את העיר מחדש בתור דאר אל-ביידה והיא קיבלה את השם קזאבלנקה מסחורים ספרדים שהקימו בה מרכזי שחר |
Language detection
All 10 clips we sent without a language field were identified as Hebrew. Auto-detection is safe here; sending language=he still skips the detection step.
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=he" \
-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="he", 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 Hebrew test.
FAQ
How accurate is Whisper for Hebrew?
On 30 clean read-speech clips it made 28% 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 Hebrew?
In our test, yes: all 10 clips sent without a language were identified as Hebrew. Sending language=he still saves the detection step on every request.
Can it translate Hebrew speech to English?
The API returns Hebrew text. For English, transcribe first and translate the text with a chat model on the same key.