Two models, one benchmark. #1 of 28 systems on medical accuracy — with zero fabricated drug names.
The most accurate medical STT we measured. Managed EU-cloud API, or self-hosted in your own tenant.
Open weights that run fully offline — for when audio can’t leave the machine.
28 systems, identical audio, one open scorer — ranked by medical-term error rate. The flagship leads the cloud APIs; the edge model leads the open ones. Full board & methodology →
Closed-source APIs
| System | M-WER | Drug |
|---|---|---|
| omi-medical-1 (ours) | 0.94% | 0.00% |
| ElevenLabs Scribe v2 | 0.97% | 0.00% |
| Google Chirp 3 | 1.11% | 1.13% |
| Gemini 3.1 Pro | 1.34% | 0.23% |
| Speechmatics Enhanced Medical | 1.36% | 1.81% |
Open models
| System | M-WER | Drug |
|---|---|---|
| omi-medical-edge-1 (ours) | 2.16% | 5.43% |
| Voxtral Mini Transcribe v2 | 2.47% | 5.66% |
| Whisper Large v3 Turbo | 2.54% | 6.11% |
| Qwen3-ASR 1.7B | 2.79% | 6.11% |
| Parakeet TDT 0.6B v2 | 3.80% | 8.60% |
Deployable open models. A 9B research model scores higher on medical terms but can’t run at edge latency.
omi-medical-1 · Cloud API
curl https://api.omi.health/v1/audio/transcriptions \
-H "Authorization: Bearer $OMI_API_KEY" \
-F model="omi-medical-1" \
-F [email protected]OpenAI-compatible — change the base URL and key. Create a free key →
omi-medical-edge-1 · On-device
pip install omi-med-stt
omi-med-stt consultation.wav
# runs offline on Mac, CUDA or CPUOpen weights, MIT runtime — audio never leaves the machine. Model card →
Free during preview — founding users keep 50% off list price.