Skip to content

Transcription

Send an audio file, get the text. Same contract as OpenAI audio/transcriptions; your existing Whisper client works unchanged.

POST/v1/audio/transcriptionsTry it
curl https://voice.patientdesk.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer pd_live_..." \
  -F file=@kayit.m4a \
  -F response_format=json

Form fields

Send multipart/form-data. wav, mp3, m4a, webm, ogg and flac are accepted. Files longer than 30 s are split and re-joined automatically.

filefilerequired
The audio file. Up to 100 MB and 2 hours.
modelstring
duyu-1. whisper-1 is accepted for compatibility.
Defaultduyu-1
language"tr" | "auto"
The language spoken.
Defaulttr
promptstring
Spelling and vocabulary hint: drug names, person names, ID numbers. The model prefers these spellings.
response_formatstring
json, text, verbose_json, srt, vtt. See Output formats.
Defaultjson
timestamp_granularities[]string[]
segment and/or word; only with verbose_json.
temperaturenumber
0–1.
Default0

Response

{ "text": "Merhaba, ben Ayşe Yılmaz. Sipariş numaram CNB123." }

Billing

Duyu is billed per audio hour: files at $0.125 · ₺6, live streams at $0.225 · ₺11. What counts is the length of the audio (duration in a verbose_json response; stopped.audio_s on a stream), not the processing time. See Pricing.