Reference
Changelog
Dated, customer-visible changes to the API contract, limits, and served model builds. Newest first.
2026-08-11 — Documentation and availability contract
- The direct-upload
profiledefault is now documented conditionally: standard below 30.000 seconds and turbo at or above 30.000 seconds. - Realtime is explicitly documented as a private pilot with no self-serve production endpoint. File and long-audio transcription remain the generally available surfaces.
- Added an open-source local-runtime guide and a production checklist covering key safety, retries, idempotency, retention, model builds, and service status.
2026-08-08 — General availability contract
- 1,500 free audio-minutes per calendar month on every account, plus any promotional grant. At the cap, requests are refused with
402; you are never silently billed. Paid usage continues at $0.20 per audio-hour with no subscription. - Explicit error codes in the standard envelope:
403 entitlement_deniedwhen a key is not entitled to a requested feature,503 capacity_unavailablewhen turbo capacity is not available, and402 billing_blockedfor billing stops. - Every error response is exactly
{"error": {"code": "…", "message": "…"}}. Branch onerror.code. - Terms changes that affect the contract are announced at least 30 days before they take effect.
2026-08-05 — EU region cutover
- All processing runs in the EU (eu-central-1). Both
api.omi.healthandapi.eu.omi.healthare served from that region. - Result and job-metadata retention is a console dial from 1 to 72 hours, default 24 hours. Webhook jobs keep an effective 9-hour minimum so the last delivery retry can still be picked up.
2026-08-04 — Longer audio per job
- Maximum audio duration raised from 30 minutes to 2 hours (7,200 seconds); minimum lowered to 1 second.
- The
min_audio_secondsandmax_audio_secondsvalues in the job envelope remain authoritative for the live deployment.
2026-07-31 — v6 benchmark board
- The published benchmark board now covers 29 systems, including gpt-transcribe.
- Benchmark claims apply to English unless stated otherwise.
2026-07-26 — language=auto generally available (sync)
- Per-utterance automatic language detection is generally available on the synchronous endpoint with
language=auto, optionally narrowed withlanguage_hints. - Omitting
languagestill uses the key default and then English; omission never enables detection. - Automatic detection on long-audio jobs is available to named evaluation accounts while the paid entitlement is introduced.
Served model builds
Verbose responses report the exact build in metadata.model_build. Pin against it to detect a model change.
| Model | Pinned build | Since |
|---|---|---|
omi-medical-1 | omi-medical-1@9e0248f339dc | 2026-07-29 |
omi-medical-edge-1 | omi-medical-edge-1@dc854cd35087 | 2026-07-30 |