# 创建转录

## OpenAPI Specification

```yaml
openapi: 3.0.1
info:
  title: ''
  description: ''
  version: 1.0.0
paths:
  /v1/audio/transcriptions:
    post:
      summary: 创建转录
      deprecated: false
      description: |+
        了解如何将音频转换为文本。

        相关指南：[语音转文本](https://platform.openai.com/docs/guides/speech-to-text)

        将音频转录为输入语言。

      tags:
        - 模型接口/音频接口（Audio）
      parameters:
        - name: Content-Type
          in: header
          description: ''
          required: true
          example: multipart/form-data
          schema:
            type: string
        - name: Authorization
          in: header
          description: ''
          required: true
          example: Bearer {{YOUR_API_KEY}}
          schema:
            type: string
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                file:
                  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。
                  type: string
                  format: binary
                model:
                  description: 要使用的模型的 ID。仅`whisper-1`当前可用。
                  example: whisper-1
                  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](https://platform.openai.com/docs/guides/speech-to-text/prompting)音频语言相匹配。
                  example: eiusmod nulla
                  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: json
                  type: string
                temperature:
                  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](https://en.wikipedia.org/wiki/Log_probability)自动升高温度，直到达到特定阈值。

                  example: 0
                  type: number
                language:
                  description: >+
                    输入音频的语言。[以ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes)格式提供输入语言将提高准确性和延迟。

                  example: ''
                  type: string
              required:
                - file
                - model
      responses:
        '200':
          description: ''
          content:
            application/json:
              schema:
                type: object
                properties:
                  text:
                    type: string
                required:
                  - text
                x-apifox-orders:
                  - text
              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: OK
      security: []
      x-apifox-folder: 模型接口/音频接口（Audio）
      x-apifox-status: released
      x-run-in-apifox: https://app.apifox.com/web/project/2946232/apis/api-92222082-run
components:
  schemas: {}
  securitySchemes: {}
servers:
  - url: https://api.chatanywhere.tech
    description: 正式环境
security: []

```