> ## Documentation Index
> Fetch the complete documentation index at: https://docs.dgrid.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# 음성 인식 생성

> Transcribe uploaded audio into text with the OpenAI-compatible Whisper-style interface. Supported formats: FLAC, MP3, MP4, MPEG, MPGA, M4A, OGG, WAV, and WebM.



## OpenAPI

````yaml api-reference/openapi.json POST /v1/audio/transcriptions
openapi: 3.1.0
info:
  title: DGrid AI Gateway API
  description: >-
    A single, unified API to access 200+ leading AI models. OpenAI-, Claude-,
    and Gemini-compatible endpoints for chat, completions, embeddings, images,
    audio, and moderations.
  version: 1.0.0
  contact:
    name: DGrid AI
    url: https://dgrid.ai
servers:
  - url: https://api.dgrid.ai
    description: DGrid AI Gateway
security:
  - bearerAuth: []
paths:
  /v1/audio/transcriptions:
    post:
      tags:
        - Audio
      summary: Create transcription
      description: >-
        Transcribe uploaded audio into text with the OpenAI-compatible
        Whisper-style interface. Supported formats: FLAC, MP3, MP4, MPEG, MPGA,
        M4A, OGG, WAV, and WebM.
      operationId: createTranscription
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
                - file
                - model
              properties:
                file:
                  type: string
                  format: binary
                  description: Audio file up to 25 MB.
                model:
                  type: string
                  description: Model ID, such as `whisper-1`.
                language:
                  type: string
                  description: ISO-639-1 language code, such as `en`, `zh`, or `ko`.
                prompt:
                  type: string
                  description: Optional prompt for biasing the transcript.
                response_format:
                  type: string
                  enum:
                    - json
                    - text
                    - srt
                    - verbose_json
                    - vtt
                  default: json
                temperature:
                  type: number
                  default: 0
                  minimum: 0
                  maximum: 1
                  description: Sampling temperature.
      responses:
        '200':
          description: >-
            Transcript. When `response_format` is `verbose_json`, the response
            also includes `task`, `language`, `duration`, and per-segment timing
            metadata.
          content:
            application/json:
              schema:
                type: object
                properties:
                  text:
                    type: string
                    description: Transcript text.
        '400':
          $ref: '#/components/responses/BadRequest'
components:
  responses:
    BadRequest:
      description: Invalid request.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            param:
              type: string
            code:
              type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        Your DGrid API key. All endpoints use `Authorization: Bearer
        <DGRID_API_KEY>`.

````