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

# Create transcription

> Transcribes audio into the input language.



## OpenAPI

````yaml post /api/gateway/v1/audio/transcriptions
openapi: 3.1.0
info:
  title: Waystone API
  description: Development documentation
  version: 1.0.0
servers:
  - url: http://localhost:3000
    description: Local server
security:
  - bearerAuth: []
paths:
  /api/gateway/v1/audio/transcriptions:
    post:
      summary: Create transcription
      description: Transcribes audio into the input language.
      operationId: postApiGatewayV1AudioTranscriptions
      parameters: []
      requestBody:
        content:
          multipart/form-data:
            schema:
              allOf:
                - type: object
                  properties:
                    model:
                      type: string
                      examples:
                        - openai/gpt-4o-mini
                        - gpt-4o-mini
                      description: >-
                        <provider>/<model> to use in the query. If <model> is
                        unique across providers, can supply <model> only
                    metadata:
                      type: object
                      properties:
                        waystone:
                          type: string
                      additionalProperties:
                        type: string
                      description: >-
                        Key-value pairs of metadata for the request. Identify
                        end-users associated with the query with the `waystone`
                        metadata. All other fields are metadata for OpenAI
                        requests and are not used by Waystone.
                      examples:
                        - waystone: "{\n\t\t\t\t\t\t\"user\": {\n\t\t\t\t\t\t\t\"id\": \"user123\",\n\t\t\t\t\t\t\t\"metadata\": { \"email\": \"user@example.com\", \"name\": \"John Doe\" }\n\t\t\t\t\t\t}\n\t\t\t\t\t}"
                        - waystone: "{\n\t\t\t\t\t\t\"user\": \"user123\",\n\t\t\t\t\t\t\"group\": { \"id\": \"group123\", \"metadata\": { \"name\": \"Group Name\" } }\n\t\t\t\t\t}"
                    store:
                      type:
                        - boolean
                        - 'null'
                      default: false
                      description: >-
                        For OpenAI: Whether or not to store the output of this
                        chat completion request in OpenAI
                  required:
                    - model
                - type: object
                  properties:
                    file:
                      format: binary
                      description: >-
                        The audio file object (not file name) to transcribe, in
                        one of these formats: flac, mp3, mp4, mpeg, mpga, m4a,
                        ogg, wav, or webm.
                    language:
                      type: string
                      description: >-
                        The language of the input audio. Supplying the input
                        language in ISO-639-1 (e.g. en) format will improve
                        accuracy and latency.
                    prompt:
                      type: string
                      description: >-
                        An optional text to guide the model's style or continue
                        a previous audio segment. The prompt should match the
                        audio language.
                    response_format:
                      type: string
                      enum:
                        - json
                        - text
                        - srt
                        - verbose_json
                        - vtt
                      default: json
                      description: >-
                        The format of the transcript output, in one of these
                        options: json, text, srt, verbose_json, or vtt.
                    stream:
                      type:
                        - boolean
                        - 'null'
                      default: false
                      description: >-
                        If set to true, the model response data will be streamed
                        to the client as it is generated. Streaming availability
                        is dependent on the model provider.
      responses:
        '200':
          description: Stream of transcription events
          content:
            application/json:
              schema:
                type: array
                items:
                  type: object
                  properties:
                    delta:
                      type: string
                      description: The text delta that was additionally transcribed.
                    type:
                      type: string
                      description: The type of the event.
                    logprobs:
                      type: array
                      items:
                        type: object
                        properties:
                          bytes:
                            type: array
                            items: {}
                          logprob:
                            type: number
                          token:
                            type: string
                        required:
                          - bytes
                          - logprob
                          - token
                  required:
                    - delta
                    - type
                    - logprobs
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer

````