We believe healthcare AI should be verifiable. We publish our benchmarks, open-source our evaluation code, and release models under permissive licences.
Our flagship medical speech-to-text — #1 of 28 systems on the sealed benchmark by Medical WER, with zero fabricated drug names. EU cloud or self-hosted.
28 systems ranked on medical audio using Medical Word Error Rate — sealed test set, open scorer, every major cloud API and medical variant.
An on-device 0.6B medical speech-to-text model, benchmarked against 28 open and cloud systems.
8 frontier AI models, with and without a deterministic safety layer. Scribes forget 43× more than they invent — in this benchmark Guard recovered every measured miss and flagged all 12 confirmed hallucinations.
A safety-first SOAP benchmark measuring hallucinations, evidence grounding, and clinical coverage.
An open 3B clinical model for structured SOAP notes, released under the MIT licence.
omi-medical-edge-1 model weights — on-device medical speech-to-text. CC-BY-4.0.
HuggingFace → omi-med-stt-runtimeRuntime CLI for omi-medical-edge-1 — MLX, NeMo, and parakeet.cpp backends. MIT licence.
GitHub → medical-STT-evalEvaluation framework for speech-to-text models on medical conversations.
GitHub → medical-note-evalSOAP note safety benchmark for hallucination, grounding, and quality.
GitHub → sum-smallOmi-Sum 3B model weights and training dataset. MIT licence.
HuggingFace →