Measurements, not promises

Last updated: September 2026

VAYS runs its AI on your device by default. Claims like that are easy to make and hard to check, so this page shows how we test: real benchmarks, run on the exact builds we ship, with the caveats spelled out.

Polish medical speech: the hardest test we could find

ADMEDVOICE is a public corpus of Polish medical dictation published in Nature Scientific Data (2025, DOI 10.1038/s41597-025-05776-1, CC BY 4.0): radiology reports, oncology notes, referrals, resuscitation records. Medical speech is a worst case for any recognizer: specialist vocabulary, drug names, dosages and units.

We measured the exact speech stack VAYS runs on-device (NVIDIA Parakeet v3, fully offline via CoreML on Apple Silicon) on the natural part of the corpus. The numbers below come from the updated engine now live in iOS 1.9 and Mac 2.8. To our knowledge this is the first published measurement of this engine on Polish medical speech.

Metric VAYS on-device stack
Recordings9,797
Audio16.3 h
Word error rate (WER)21.4%
WER, numbers normalized20.1%
Character error rate (CER)9.4%
Speed on an Apple Silicon Mac65x faster than realtime

Difficulty varies a lot by specialty: referrals and recommendations land near 10% WER, while cardiology reaches 44% (dosages, parameters, units). Part of that tail is the corpus itself: we identified 80 recordings with mismatched audio and reference text in the source data; with those filtered out, cardiology improves to about 37%.

Reference points

For context, results reported on Polish medical speech by others. Protocols differ, so treat this as orientation, not a ranking.

System WER Notes
VAYS (on-device, this measurement)21.4%Runs offline on your Mac or iPhone
Whisper-medium fine-tuned by the corpus authors9.0%Our measurement of their model on our sample; it saw part of this data in training, treat as a best case
ElevenLabs Scribe10.6%Cloud service, audio leaves the device (arXiv:2603.02246)
Whisper large, no fine-tuning42.3%Baseline reported in the same paper

The engine keeps improving

In August 2026 we updated the speech engine and re-ran the full benchmark before shipping. Accuracy held (WER 21.43% vs 21.47%), speed improved by 28%, and one bug class disappeared completely: short Polish utterances occasionally came back with stray Cyrillic characters. That happened 22 times across the corpus on the old engine and zero times on the new one.

Method and honesty

Interested in what this means for medical documentation? Read about VAYS MED.