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 profile default 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_denied when a key is not entitled to a requested feature, 503 capacity_unavailable when turbo capacity is not available, and 402 billing_blocked for billing stops.
  • Every error response is exactly {"error": {"code": "…", "message": "…"}}. Branch on error.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.health and api.eu.omi.health are 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_seconds and max_audio_seconds values 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 with language_hints.
  • Omitting language still 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.

ModelPinned buildSince
omi-medical-1omi-medical-1@9e0248f339dc2026-07-29
omi-medical-edge-1omi-medical-edge-1@dc854cd350872026-07-30