Create translation

POSThttps://api.openai.com/v1/audio/translations

Transcribes audio into the input language.

Request

Authorization: Bearer Token

Provide your bearer token in the

Authorization

header when making requests to protected resources.

示例

Authorization: Bearer 2f68dbbf-519d-4f01-9636-e2421b68f379

Header 参数

Content-Type

string

必需

示例值:

multipart/form-data

string

必需

示例值:

application/json

Authorization

string

可选

示例值:

Bearer

Body 参数multipart/form-data

file

必需

The audio file object (not file name) translate, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.

model

string

必需

ID of the model to use. Only whisper-1 is currently available.

示例值:

whisper-1

prompt

string

可选

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

response_format

string

可选

The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.

示例值:

json

temperature

number

可选

The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.

示例值:

Request samples

返回响应

OK(200)

HTTP Code: 200

Content Type : JSONapplication/json

text

string

必需

{
  "text": "Hello, my name is Wolfgang and I come from Germany. Where are you heading today?"
}

最后修改时间： 10 天前