POST
Transcribe Audio
Transcribe audio file to text. STT decode controls (task/beam_size/vocabulary) fall back to the persisted capture-settings defaults when not provided per-request. POST /api/voice/transcribe All requests authenticate with your PeachDesk API key in the X-API-Key header (an interactive session token in Authorization: Bearer also works тАФ see Authentication). Use the playground to send a live request and inspect the response.

Authorizations

X-API-Key
string
header
required

Organization API key (bibha_...). Takes precedence over the session credential, and is refused outright on user-session-only and super-admin routes.

Body

multipart/form-data
file
file
required
language
string | null
model
string | null
task
string | null
beam_size
integer | null
vocabulary
string | null

Response

Successful Response

Response model for transcription.

text
string
required
duration
number
required
usage
UsageInfo ┬╖ object | null

Per-request resource usage the engine reports back to the API proxy.

The proxy meters/bills off these fields; each one maps to a rate-registry unit (TTS per character, STT per audio-second, LLM per token). Only the dimensions relevant to the request are populated тАФ the rest stay None.