Open source

Run medical transcription on your hardware

Omi Med STT v1 is a separate open-source, English medical transcription runtime. Audio stays in your process; no Omi API key or hosted account is required.

GitHub PyPI Model card

Install and transcribe

# Base CLI
pip install -U omi-med-stt

# Apple Silicon / MLX
pip install -U "omi-med-stt[mlx]"

omi-med-stt consultation.m4a --json

# Verify the local runtime and model artifact
omi-med-stt check

The package reads common audio formats, downmixes to mono, and resamples to 16 kHz. Model weights download on first use from the published Hugging Face repositories.

Local runtime only

The on-device model remains available for local use. It is no longer a hosted API model. Use omi-medical-1 for managed transcription; the retired hosted identifier returns 400 model_unknown.

Choose a runtime

Hardware	Runtime	Released artifact
Apple Silicon	`mlx`	MLX q8
CUDA-capable GPU	GPU runtime	Canonical published weights
Linux / Windows CPU	`cpp`	GGUF q8_0

Runtime exports have separate benchmark rows because quantization and conversion can change accuracy. Use the result for the artifact you actually deploy, not a different published artifact's number. See GitHub for the current platform-specific GPU installation command.

Cloud and local are different products

Capability	Hosted API	Open-source runtime
Processing	Managed in the EU	Inside your process
Languages	Eight supported families	English
Long jobs and webhooks	Yes	Your application owns the workflow
Speaker labels and word timing	Available by request fields	Not part of the released CLI contract
Encounter vocabulary and Patterns	Available by request fields and plan	Not part of the released CLI contract
License	Service terms	MIT runtime code; CC-BY-4.0 weights

Review transcripts before clinical use

The local runtime is speech-to-text, not a diagnostic, triage, prescribing, or clinical decision system. It is not clinically validated. Keep human review in the workflow.

Continue

Use the hosted APIAdd managed jobs, speakers, vocabulary, and automatic language detection.Production checklistOperate the hosted API safely and predictably.