Feature guide

Speaker diarization and word timestamps

Attach who-spoke-when metadata to the sealed transcript. The decoration lanes receive the final text and audio, then map speaker labels and acoustic word boundaries without changing a single transcript word.

Request diarization

curl https://api.omi.health/v1/audio/transcriptions \
  -H "Authorization: Bearer $OMI_API_KEY" \
  -F [email protected] \
  -F model=omi-medical-1 \
  -F language=en \
  -F response_format=verbose_json \
  -F diarize=true

Use response_format=verbose_json and diarize=true. Async job JSON accepts the same Boolean plus max_speakers from 1 through 4. On the synchronous endpoint, the current preview uses the service default speaker maximum.

Response shape

{
  "text": "Where does it hurt? My chest, mostly.",
  "segments": [
    {"id":"seg_0001","speaker":"A","text":"Where does it hurt?","start":0.32,"end":1.44},
    {"id":"seg_0002","speaker":"B","text":"My chest, mostly.","start":1.76,"end":2.93}
  ],
  "words": [
    {"word":"Where","start":0.32,"end":0.58,"speaker":"A"},
    {"word":"My","start":1.76,"end":1.91,"speaker":"B"}
  ],
  "speakers": [{"speaker":"A"},{"speaker":"B"}]
}

Field	Meaning
`segments[].speaker`	Anonymous session-local label on a text segment.
`words[].speaker`	Speaker mapped to an acoustic word boundary when available.
`start / end`	Seconds from the start of the input audio.

Important semantics

Speaker labels such as A and B identify clusters within one recording; they are not names or inferred clinical roles.
Word timestamps are acoustic boundaries and may not exactly match subtitle-style display timing.
Very short interjections, overlapping speech, strong reverberation, and background speech can reduce attribution quality.
Consumers should tolerate an unattributed word or speaker transition near overlap.
Use the same speaker label only within the response that produced it; labels are not stable identities across jobs.

Zero text mutation is a product invariant

Diarization, word alignment, and speaker reconciliation are decoration lanes. They can fail explicitly, but they cannot rewrite the sealedtext field.

Continue

Realtime speaker eventsSee when labels appear on display corrections and records.Response schemasInspect the full verbose JSON field reference.