Audio Transcription Whisper-1

POST: https://www.kkiai.com/v1/audio/transcriptions

Official documentation: https://platform.openai.com/docs/guides/speech-to-text

Request Parameters

Authorization

Add the Authorization parameter to the Header. Its value should be the Token concatenated after Bearer.

Example: Authorization: Bearer YOUR_API_KEY

Header Parameters

Parameter Name	Type	Required	Description	Example
Content-Type	string	Optional	The request content type. When using cURL with --form, this is usually generated automatically.	multipart/form-data
Authorization	string	Required	API key used for authentication.	Bearer YOUR_API_KEY

Body Parameters (multipart/form-data)

Parameter Name	Type	Required	Description
file	file	Required	The audio file object to be transcribed, not the filename. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
model	string	Required	The model ID to use. Currently only whisper-1 and gpt-4o-mini-transcribe are available.
language	string	Optional	The language of the input audio. Providing the input language in ISO-639-1 format can improve accuracy and latency.
prompt	string	Optional	An optional text prompt to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
response_format	string	Optional	The format of the transcript output. Options: json, text, srt, verbose_json, or vtt.
temperature	number	Optional	Defaults to 0. Sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will automatically increase the temperature based on log probability until a specific threshold is reached.

cURL Example

curl --location --request POST 'https://www.kkiai.com/v1/audio/transcriptions' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--form 'file=@"/path/to/audio.m4a"' \
--form 'model="whisper-1"' \
--form 'language="en"' \
--form 'prompt="This is an English audio file."' \
--form 'response_format="json"'

Response

🟢 200 Success

Response Body

Parameter Name	Type	Required	Description
text	string	Required	The transcribed text.

Response Example

{
  "text": "Hello, this is a test audio transcription."
}