Transcriptions (OpenAI Native Format)

Transcribe audio into text in the same language. See also Text to Speech, Translations, and the Gemini native format.

Endpoint

POST /v1/audio/transcriptions

Upload the audio file using multipart/form-data.

Request parameters

Parameter	Type	Required	Description
file	file	Yes	Audio file (mp3 / wav / m4a, etc.)
model	string	Yes	Recognition model, e.g. whisper-1
language	string	No	Audio language (ISO-639-1), improves accuracy
response_format	string	No	json (default) / text / srt / vtt
temperature	number	No	Sampling temperature, default 0

Request example

curl https://ai.youqi.tech/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-YOUR_API_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1"

Response example

{ "text": "This is the transcribed text." }

TIP

Use multipart/form-data for the binary upload, not JSON.