Aurora APIAurora API
Chat Completions FormatChatGPT APIChatGPT Audio

Audio to Text (whisper-1)

POST
/v1/audio/transcriptions

Header Parameters

Content-Type*string
Authorization*string

Request Body

multipart/form-data

model*string

The model ID to use. Currently only whisper-1 is available.

file*string

The audio file object to transcribe (not the file name). Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

language?string

The language of the input audio. Providing the input language in ISO-639-1 format improves accuracy and latency.

prompt?string

An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

response_format?string

The format of the transcription output. Options: json, text, srt, verbose_json, or vtt.

Default"json"
temperature?number

Defaults to 0. Sampling temperature between 0 and 1. Higher values like 0.8 make output more random, lower values like 0.2 make it more focused and deterministic. If set to 0, the model will automatically increase the temperature using log probability until a certain threshold is reached.

Default0

Response Body

application/json

curl -X POST "https://loading/v1/audio/transcriptions" \  -H "Content-Type: string" \  -H "Authorization: string" \  -F model="whisper-1" \  -F file="" \  -F language="zh" \  -F prompt="这是一段中文音频" \  -F response_format="json" \  -F temperature=""
{
  "text": "12345678910"
}

How is this guide?

Last updated on