Transcriptions API

Upload an audio file to receive its transcript.

POST /v1/audio/transcriptions

Fields

Required	Fields
Required	file, model=kitsch-stt-v1
—	language, prompt
—	response_format=json, text
—	stream=false

Files must not exceed 25 MiB. The applicable input, instructions, and prompt fields allow up to 4,096 UTF-16 code units.

Set KITSCH_OPENAI_BASE_URL to your Audio API URL ending in /v1.

curl "$KITSCH_OPENAI_BASE_URL/audio/transcriptions" \
  -H "Authorization: Bearer $KITSCH_API_KEY" \
  -F "file=@speech.wav" -F "model=kitsch-stt-v1" \
  -F "response_format=json"

Response

{"text":"Hello.","usage":{"type":"duration","seconds":1}}

JSON: application/json. Text: text/plain; charset=utf-8.