跳到主要内容

语音转文本 / whisper-1

OpenAPI Specification

openapi: 3.0.1
info:
title: ''
description: ''
version: 1.0.0
paths:
/v1/audio/transcriptions:
post:
summary: 语音转文本 / whisper-1
deprecated: false
description: ''
tags:
- 模型接口/Openai
parameters:
- name: Content-Type
in: header
description: ''
required: false
example: multipart/form-data
schema:
type: string
- name: Accept
in: header
description: ''
required: true
example: application/json
schema:
type: string
default: application/json
- name: Authorization
in: header
description: ''
required: true
example: sk-
schema:
type: string
default: sk-
requestBody:
content:
multipart/form-data:
schema:
type: object
properties:
file:
format: binary
type: string
description: 要转录的音频文件,采用以下格式之一:mp3、mp4、mpeg、mpga、m4a、wav 或 webm。
example: ''
model:
description: 要使用的模型的 ID。仅whisper-1当前可用。
example: ''
type: string
prompt:
description: 可选文本,用于指导模型的风格或继续之前的音频片段。提示应与音频语言相匹配。
example: ''
type: string
response_format:
description: 成绩单输出的格式,采用以下选项之一:json、text、srt、verbose_json 或 vtt。
example: ''
type: string
temperature:
type: number
description: >-
采样温度,介于 0 和 1 之间。较高的值(如 0.8)将使输出更加随机,而较低的值(如
0.2)将使输出更加集中和确定。如果设置为 0,模型将使用对数概率自动升高温度,直到达到特定阈值。
example: 0
language:
description: 输入音频的语言。以ISO-639-1格式提供输入语言将提高准确性和延迟。
example: ''
type: string
responses:
'200':
description: ''
content:
application/json:
schema:
type: object
properties: {}
example:
text: >-
Imagine the wildest idea that you've ever had, and you're
curious about how it might scale to something that's a 100, a
1,000 times bigger. This is a place where you can get to do
that.
headers: {}
x-apifox-name: 成功
security: []
x-apifox-folder: 模型接口/Openai
x-apifox-status: released
x-run-in-apifox: https://app.apifox.com/web/project/5503894/apis/api-324063691-run
components:
schemas: {}
securitySchemes: {}
servers:
- url: '{{base_url}}'
description: 测试环境
- url: https://newapi.eronmind.com
description: 正式环境
security: []