Skip to content

音频转文字 gpt-4o-transcribe

OpenAPI Specification

yaml
openapi: 3.0.1
info:
  title: ''
  description: ''
  version: 1.0.0
paths:
  /v1/audio/transcriptions:
    post:
      summary: 音频转文字 gpt-4o-transcribe
      deprecated: false
      description: 官方文档:https://platform.openai.com/docs/guides/speech-to-text
      tags:
        - 聊天(Chat)/ChatGpt 接口/ChatGPT音频(Audio)
      parameters:
        - name: Content-Type
          in: header
          description: ''
          required: false
          example: multipart/form-data
          schema:
            type: string
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                file:
                  description: >+
                    要转录的音频文件对象(不是文件名),格式为:flac、mp3、mp4、mpeg、mpga、m4a、ogg、wav 或
                    webm。

                  example: file://C:\Users\Administrator\Desktop\test.m4a
                  type: string
                  format: binary
                model:
                  description: |+
                    要使用的模型 ID。目前只有 whisper-1,gpt-4o-mini-transcribe 是可用的。

                  example: gpt-4o-transcribe
                  type: string
                language:
                  description: |+
                    输入音频的语言。以 ISO-639-1 格式提供输入语言可以提高准确性和延迟。

                  example: ''
                  type: string
                prompt:
                  description: |+
                    一个可选的文本来指导模型的风格或继续之前的音频段落。提示应该与音频语言匹配。

                  example: ''
                  type: string
                response_format:
                  description: |-
                    默认为 json
                    转录输出的格式,可选择:json、text
                  example: json
                  type: string
                temperature:
                  description: >-
                    默认为 0,采样温度,between 0 和 1。更高的值像 0.8 会使输出更随机,而更低的值像 0.2
                    会使其更集中和确定性。如果设置为 0,模型将使用对数概率自动增加温度直到达到特定阈值。
                  example: 0
                  type: number
              required:
                - file
                - model
            examples: {}
      responses:
        '200':
          description: ''
          content:
            application/json:
              schema:
                type: object
                properties:
                  text:
                    type: string
                required:
                  - text
                x-apifox-orders:
                  - text
              examples:
                '1':
                  summary: 成功示例
                  value:
                    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.
                '2':
                  summary: 成功示例
                  value:
                    text: 一二三四五六七八九十
          headers: {}
          x-apifox-name: 成功
      security:
        - bearer: []
      x-apifox-folder: 聊天(Chat)/ChatGpt 接口/ChatGPT音频(Audio)
      x-apifox-status: released
      x-run-in-apifox: https://app.apifox.com/web/project/5443236/apis/api-232421914-run
components:
  schemas: {}
  securitySchemes:
    bearer:
      type: http
      scheme: bearer
servers:
  - url: https://www.anyapi.vip
    description: 正式环境
security:
  - bearer: []

AnyAPI — 专业的 AI 接口聚合服务