Skip to content

Output formats

Same call, different response_format: plain text for dictation, word timestamps for archives, subtitles for video.

response_formatContentContent-Type
jsontext only.application/json
textPlain text with a trailing newline.text/plain
verbose_jsontext, language, duration, segments[], and words[] on request.application/json
srtSubRip subtitles.text/plain
vttWebVTT subtitles.text/vtt

verbose_json

segments[]object[]
id, start, end, text. Sentence-level timing.
words[]object[]
word, start, end, probability. With timestamp_granularities[]=word.
durationnumber
Audio length in seconds. This is the billed duration.
verbose_json
curl https://voice.patientdesk.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer pd_live_..." \
  -F file=@toplanti.mp3 \
  -F response_format=verbose_json \
  -F "timestamp_granularities[]=word"

{
  "task": "transcribe", "language": "tr", "duration": 512.4,
  "text": "Merhaba, ben Ayşe Yılmaz. Sipariş numaram CNB123...",
  "segments": [{ "id": 0, "start": 0.0, "end": 4.2, "text": "Merhaba, ben Ayşe Yılmaz." }, ...],
  "words": [{ "word": "Merhaba,", "start": 0.0, "end": 0.6, "probability": 0.98 }, ...]
}

Subtitles

Subtitle cues follow segment boundaries and are wrapped to at most 42 characters and 2 lines.

srt
1
00:00:00,420 --> 00:00:03,100
Yarın saat on dörtteki randevumu on altıya alabilir miyiz?

2
00:00:03,600 --> 00:00:05,020
Tabii, hemen bakıyorum.